/Users/minipro/quantdiff/work/llama-b11869/src/build/bin/llama-server -m /Users/minipro/quantdiff/models/campaign/3376b755f9ab/Sage-A1.5.i1-IQ3_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 0.00.049.375 W Setting 'enable_thinking' via --chat-template-kwargs is deprecated. Use --reasoning on / --reasoning off instead. 0.00.049.438 I srv llama_server: initializing ... 0.00.049.444 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.049.524 I srv init_listene: The UI is disabled 0.00.049.525 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.049.563 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) 0.00.051.217 I srv load_model: loading model '/Users/minipro/quantdiff/models/campaign/3376b755f9ab/Sage-A1.5.i1-IQ3_M.gguf' 0.00.350.205 W model has unused tensor blk.40.attn_norm.weight (size = 8192 bytes) -- ignoring 0.00.350.216 W model has unused tensor blk.40.post_attention_norm.weight (size = 8192 bytes) -- ignoring 0.00.350.222 W model has unused tensor blk.40.attn_q.weight (size = 7208960 bytes) -- ignoring 0.00.350.225 W model has unused tensor blk.40.attn_k.weight (size = 450560 bytes) -- ignoring 0.00.350.228 W model has unused tensor blk.40.attn_v.weight (size = 589824 bytes) -- ignoring 0.00.350.235 W model has unused tensor blk.40.attn_output.weight (size = 4718592 bytes) -- ignoring 0.00.350.237 W model has unused tensor blk.40.attn_q_norm.weight (size = 1024 bytes) -- ignoring 0.00.350.239 W model has unused tensor blk.40.attn_k_norm.weight (size = 1024 bytes) -- ignoring 0.00.350.241 W model has unused tensor blk.40.ffn_gate_inp.weight (size = 2097152 bytes) -- ignoring 0.00.350.243 W model has unused tensor blk.40.ffn_down_exps.weight (size = 115343360 bytes) -- ignoring 0.00.350.248 W model has unused tensor blk.40.ffn_gate_exps.weight (size = 115343360 bytes) -- ignoring 0.00.350.250 W model has unused tensor blk.40.ffn_up_exps.weight (size = 115343360 bytes) -- ignoring 0.00.350.253 W model has unused tensor blk.40.ffn_gate_inp_shexp.weight (size = 8192 bytes) -- ignoring 0.00.350.255 W model has unused tensor blk.40.ffn_gate_shexp.weight (size = 450560 bytes) -- ignoring 0.00.350.257 W model has unused tensor blk.40.ffn_up_shexp.weight (size = 450560 bytes) -- ignoring 0.00.350.259 W model has unused tensor blk.40.ffn_down_shexp.weight (size = 450560 bytes) -- ignoring 0.00.350.262 W model has unused tensor blk.40.nextn.eh_proj.weight (size = 3604480 bytes) -- ignoring 0.00.350.265 W model has unused tensor blk.40.nextn.enorm.weight (size = 8192 bytes) -- ignoring 0.00.350.267 W model has unused tensor blk.40.nextn.hnorm.weight (size = 8192 bytes) -- ignoring 0.00.350.274 W model has unused tensor blk.40.nextn.shared_head_norm.weight (size = 8192 bytes) -- ignoring 0.01.085.939 I cmn init: llama threadpool init, n_threads = 8 0.01.178.451 I srv load_model: initializing, n_slots = 4, n_ctx_slot = 4096, kv_unified = 'false' 0.01.183.331 W srv init: chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve) 0.01.183.344 I srv server_run_i: model loaded 0.01.183.346 I srv server_on_li: listening on http://127.0.0.1:8091 0.31.889.285 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.31.889.320 I slot launch_slot_: id 0 | task 2 | processing task, is_child = 0 0.31.889.321 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.31.889.342 I slot launch_slot_: id 1 | task 0 | processing task, is_child = 0 0.31.889.343 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.31.889.356 I slot launch_slot_: id 2 | task 1 | processing task, is_child = 0 0.31.889.357 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.31.889.370 I slot launch_slot_: id 3 | task 3 | processing task, is_child = 0 0.33.001.936 I slot print_timing: id 0 | task 2 | prompt eval time = 1062.04 ms / 130 tokens ( 8.17 ms per token, 122.41 tokens per second) 0.33.001.938 I slot print_timing: id 0 | task 2 | eval time = 50.51 ms / 2 tokens ( 50.51 ms per token, 19.80 tokens per second) 0.33.001.939 I slot print_timing: id 0 | task 2 | total time = 1112.55 ms / 132 tokens 0.33.001.939 I slot print_timing: id 0 | task 2 | graphs reused = 1 0.33.001.939 I slot print_timing: id 0 | task 2 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.001.958 I slot release: id 0 | task 2 | stop processing: n_tokens = 131, truncated = 0 0.33.002.116 I slot print_timing: id 1 | task 0 | prompt eval time = 1062.33 ms / 115 tokens ( 9.24 ms per token, 108.25 tokens per second) 0.33.002.118 I slot print_timing: id 1 | task 0 | eval time = 50.40 ms / 2 tokens ( 50.40 ms per token, 19.84 tokens per second) 0.33.002.119 I slot print_timing: id 1 | task 0 | total time = 1112.73 ms / 117 tokens 0.33.002.119 I slot print_timing: id 1 | task 0 | graphs reused = 1 0.33.002.119 I slot print_timing: id 1 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.002.134 I slot release: id 1 | task 0 | stop processing: n_tokens = 116, truncated = 0 0.33.002.310 I slot print_timing: id 2 | task 1 | prompt eval time = 1062.63 ms / 122 tokens ( 8.71 ms per token, 114.81 tokens per second) 0.33.002.311 I slot print_timing: id 2 | task 1 | eval time = 50.29 ms / 2 tokens ( 50.29 ms per token, 19.88 tokens per second) 0.33.002.311 I slot print_timing: id 2 | task 1 | total time = 1112.92 ms / 124 tokens 0.33.002.312 I slot print_timing: id 2 | task 1 | graphs reused = 1 0.33.002.312 I slot print_timing: id 2 | task 1 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.002.320 I slot release: id 2 | task 1 | stop processing: n_tokens = 123, truncated = 0 0.33.002.491 I slot print_timing: id 3 | task 3 | prompt eval time = 1063.00 ms / 115 tokens ( 9.24 ms per token, 108.18 tokens per second) 0.33.002.492 I slot print_timing: id 3 | task 3 | eval time = 50.10 ms / 2 tokens ( 50.10 ms per token, 19.96 tokens per second) 0.33.002.493 I slot print_timing: id 3 | task 3 | total time = 1113.10 ms / 117 tokens 0.33.002.493 I slot print_timing: id 3 | task 3 | graphs reused = 1 0.33.002.493 I slot print_timing: id 3 | task 3 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.002.500 I slot release: id 3 | task 3 | stop processing: n_tokens = 116, truncated = 0 0.33.010.096 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.269 (> 0.100 thold), f_keep = 0.221 0.33.019.514 I slot launch_slot_: id 0 | task 7 | processing task, is_child = 0 0.33.047.069 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.191 (> 0.100 thold), f_keep = 0.250 0.33.047.136 I slot launch_slot_: id 1 | task 8 | processing task, is_child = 0 0.33.047.172 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.140 (> 0.100 thold), f_keep = 0.228 0.33.047.224 I slot launch_slot_: id 2 | task 9 | processing task, is_child = 0 0.33.047.243 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.241 0.33.047.282 I slot launch_slot_: id 3 | task 10 | processing task, is_child = 0 0.34.605.190 I slot print_timing: id 0 | task 7 | prompt eval time = 1507.84 ms / 108 tokens ( 13.96 ms per token, 71.63 tokens per second) 0.34.605.192 I slot print_timing: id 0 | task 7 | eval time = 50.06 ms / 2 tokens ( 50.06 ms per token, 19.98 tokens per second) 0.34.605.192 I slot print_timing: id 0 | task 7 | total time = 1557.90 ms / 110 tokens 0.34.605.193 I slot print_timing: id 0 | task 7 | graphs reused = 1 0.34.605.193 I slot print_timing: id 0 | task 7 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.605.215 I slot release: id 0 | task 7 | stop processing: n_tokens = 109, truncated = 0 0.34.605.381 I slot print_timing: id 1 | task 8 | prompt eval time = 1507.99 ms / 152 tokens ( 9.92 ms per token, 100.80 tokens per second) 0.34.605.383 I slot print_timing: id 1 | task 8 | eval time = 50.08 ms / 2 tokens ( 50.08 ms per token, 19.97 tokens per second) 0.34.605.383 I slot print_timing: id 1 | task 8 | total time = 1558.07 ms / 154 tokens 0.34.605.383 I slot print_timing: id 1 | task 8 | graphs reused = 1 0.34.605.384 I slot print_timing: id 1 | task 8 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.605.401 I slot release: id 1 | task 8 | stop processing: n_tokens = 153, truncated = 0 0.34.605.573 I slot print_timing: id 2 | task 9 | prompt eval time = 1508.14 ms / 200 tokens ( 7.54 ms per token, 132.61 tokens per second) 0.34.605.575 I slot print_timing: id 2 | task 9 | eval time = 50.11 ms / 2 tokens ( 50.11 ms per token, 19.96 tokens per second) 0.34.605.576 I slot print_timing: id 2 | task 9 | total time = 1558.25 ms / 202 tokens 0.34.605.576 I slot print_timing: id 2 | task 9 | graphs reused = 1 0.34.605.576 I slot print_timing: id 2 | task 9 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.605.593 I slot release: id 2 | task 9 | stop processing: n_tokens = 201, truncated = 0 0.34.605.770 I slot print_timing: id 3 | task 10 | prompt eval time = 1508.29 ms / 160 tokens ( 9.43 ms per token, 106.08 tokens per second) 0.34.605.772 I slot print_timing: id 3 | task 10 | eval time = 50.14 ms / 2 tokens ( 50.14 ms per token, 19.94 tokens per second) 0.34.605.772 I slot print_timing: id 3 | task 10 | total time = 1558.43 ms / 162 tokens 0.34.605.772 I slot print_timing: id 3 | task 10 | graphs reused = 1 0.34.605.773 I slot print_timing: id 3 | task 10 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.605.783 I slot release: id 3 | task 10 | stop processing: n_tokens = 161, truncated = 0 0.34.610.741 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.224 (> 0.100 thold), f_keep = 0.257 0.34.620.706 I slot launch_slot_: id 0 | task 16 | processing task, is_child = 0 0.34.649.575 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 0.34.649.633 I slot launch_slot_: id 1 | task 14 | processing task, is_child = 0 0.34.649.671 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.239 (> 0.100 thold), f_keep = 0.139 0.34.649.706 I slot launch_slot_: id 2 | task 15 | processing task, is_child = 0 0.34.649.724 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.187 (> 0.100 thold), f_keep = 0.174 0.34.649.756 I slot launch_slot_: id 3 | task 17 | processing task, is_child = 0 0.35.889.787 I slot print_timing: id 0 | task 16 | prompt eval time = 1189.90 ms / 125 tokens ( 9.52 ms per token, 105.05 tokens per second) 0.35.889.789 I slot print_timing: id 0 | task 16 | eval time = 50.12 ms / 2 tokens ( 50.12 ms per token, 19.95 tokens per second) 0.35.889.789 I slot print_timing: id 0 | task 16 | total time = 1240.02 ms / 127 tokens 0.35.889.790 I slot print_timing: id 0 | task 16 | graphs reused = 1 0.35.889.790 I slot print_timing: id 0 | task 16 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.889.809 I slot release: id 0 | task 16 | stop processing: n_tokens = 126, truncated = 0 0.35.889.960 I slot print_timing: id 1 | task 14 | prompt eval time = 1190.05 ms / 118 tokens ( 10.09 ms per token, 99.16 tokens per second) 0.35.889.962 I slot print_timing: id 1 | task 14 | eval time = 50.14 ms / 2 tokens ( 50.14 ms per token, 19.95 tokens per second) 0.35.889.962 I slot print_timing: id 1 | task 14 | total time = 1240.18 ms / 120 tokens 0.35.889.963 I slot print_timing: id 1 | task 14 | graphs reused = 1 0.35.889.963 I slot print_timing: id 1 | task 14 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.889.975 I slot release: id 1 | task 14 | stop processing: n_tokens = 119, truncated = 0 0.35.890.148 I slot print_timing: id 2 | task 15 | prompt eval time = 1190.20 ms / 117 tokens ( 10.17 ms per token, 98.30 tokens per second) 0.35.890.149 I slot print_timing: id 2 | task 15 | eval time = 50.16 ms / 2 tokens ( 50.16 ms per token, 19.94 tokens per second) 0.35.890.150 I slot print_timing: id 2 | task 15 | total time = 1240.36 ms / 119 tokens 0.35.890.150 I slot print_timing: id 2 | task 15 | graphs reused = 1 0.35.890.150 I slot print_timing: id 2 | task 15 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.890.157 I slot release: id 2 | task 15 | stop processing: n_tokens = 118, truncated = 0 0.35.890.335 I slot print_timing: id 3 | task 17 | prompt eval time = 1190.35 ms / 150 tokens ( 7.94 ms per token, 126.01 tokens per second) 0.35.890.337 I slot print_timing: id 3 | task 17 | eval time = 50.18 ms / 2 tokens ( 50.18 ms per token, 19.93 tokens per second) 0.35.890.337 I slot print_timing: id 3 | task 17 | total time = 1240.53 ms / 152 tokens 0.35.890.337 I slot print_timing: id 3 | task 17 | graphs reused = 1 0.35.890.338 I slot print_timing: id 3 | task 17 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.890.349 I slot release: id 3 | task 17 | stop processing: n_tokens = 151, truncated = 0 0.35.895.232 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.235 (> 0.100 thold), f_keep = 0.222 0.35.904.382 I slot launch_slot_: id 0 | task 21 | processing task, is_child = 0 0.35.932.315 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.206 (> 0.100 thold), f_keep = 0.235 0.35.932.368 I slot launch_slot_: id 1 | task 22 | processing task, is_child = 0 0.35.932.399 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.196 (> 0.100 thold), f_keep = 0.237 0.35.932.433 I slot launch_slot_: id 2 | task 23 | processing task, is_child = 0 0.35.932.451 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.155 (> 0.100 thold), f_keep = 0.185 0.35.932.487 I slot launch_slot_: id 3 | task 24 | processing task, is_child = 0 0.37.410.842 I slot print_timing: id 0 | task 21 | prompt eval time = 1428.13 ms / 119 tokens ( 12.00 ms per token, 83.33 tokens per second) 0.37.410.844 I slot print_timing: id 0 | task 21 | eval time = 50.21 ms / 2 tokens ( 50.21 ms per token, 19.92 tokens per second) 0.37.410.845 I slot print_timing: id 0 | task 21 | total time = 1478.34 ms / 121 tokens 0.37.410.845 I slot print_timing: id 0 | task 21 | graphs reused = 1 0.37.410.846 I slot print_timing: id 0 | task 21 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.410.867 I slot release: id 0 | task 21 | stop processing: n_tokens = 120, truncated = 0 0.37.411.021 I slot print_timing: id 1 | task 22 | prompt eval time = 1428.28 ms / 136 tokens ( 10.50 ms per token, 95.22 tokens per second) 0.37.411.024 I slot print_timing: id 1 | task 22 | eval time = 50.24 ms / 2 tokens ( 50.24 ms per token, 19.91 tokens per second) 0.37.411.025 I slot print_timing: id 1 | task 22 | total time = 1478.51 ms / 138 tokens 0.37.411.025 I slot print_timing: id 1 | task 22 | graphs reused = 1 0.37.411.025 I slot print_timing: id 1 | task 22 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.411.037 I slot release: id 1 | task 22 | stop processing: n_tokens = 137, truncated = 0 0.37.411.212 I slot print_timing: id 2 | task 23 | prompt eval time = 1428.43 ms / 143 tokens ( 9.99 ms per token, 100.11 tokens per second) 0.37.411.214 I slot print_timing: id 2 | task 23 | eval time = 50.26 ms / 2 tokens ( 50.26 ms per token, 19.90 tokens per second) 0.37.411.214 I slot print_timing: id 2 | task 23 | total time = 1478.69 ms / 145 tokens 0.37.411.214 I slot print_timing: id 2 | task 23 | graphs reused = 1 0.37.411.215 I slot print_timing: id 2 | task 23 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.411.227 I slot release: id 2 | task 23 | stop processing: n_tokens = 144, truncated = 0 0.37.411.388 I slot print_timing: id 3 | task 24 | prompt eval time = 1428.59 ms / 181 tokens ( 7.89 ms per token, 126.70 tokens per second) 0.37.411.389 I slot print_timing: id 3 | task 24 | eval time = 50.27 ms / 2 tokens ( 50.27 ms per token, 19.89 tokens per second) 0.37.411.390 I slot print_timing: id 3 | task 24 | total time = 1478.86 ms / 183 tokens 0.37.411.390 I slot print_timing: id 3 | task 24 | graphs reused = 1 0.37.411.390 I slot print_timing: id 3 | task 24 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.411.401 I slot release: id 3 | task 24 | stop processing: n_tokens = 182, truncated = 0 0.37.416.214 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.214 (> 0.100 thold), f_keep = 0.233 0.37.427.841 I slot launch_slot_: id 0 | task 28 | processing task, is_child = 0 0.37.452.613 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.204 0.37.454.056 I slot launch_slot_: id 1 | task 29 | processing task, is_child = 0 0.37.454.098 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.194 (> 0.100 thold), f_keep = 0.194 0.37.454.133 I slot launch_slot_: id 2 | task 30 | processing task, is_child = 0 0.37.454.154 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.157 (> 0.100 thold), f_keep = 0.154 0.37.454.187 I slot launch_slot_: id 3 | task 31 | processing task, is_child = 0 0.38.906.988 I slot print_timing: id 0 | task 28 | prompt eval time = 1402.59 ms / 131 tokens ( 10.71 ms per token, 93.40 tokens per second) 0.38.906.990 I slot print_timing: id 0 | task 28 | eval time = 50.20 ms / 2 tokens ( 50.20 ms per token, 19.92 tokens per second) 0.38.906.990 I slot print_timing: id 0 | task 28 | total time = 1452.79 ms / 133 tokens 0.38.906.991 I slot print_timing: id 0 | task 28 | graphs reused = 1 0.38.906.991 I slot print_timing: id 0 | task 28 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.907.014 I slot release: id 0 | task 28 | stop processing: n_tokens = 132, truncated = 0 0.38.907.175 I slot print_timing: id 1 | task 29 | prompt eval time = 1402.73 ms / 122 tokens ( 11.50 ms per token, 86.97 tokens per second) 0.38.907.180 I slot print_timing: id 1 | task 29 | eval time = 50.23 ms / 2 tokens ( 50.23 ms per token, 19.91 tokens per second) 0.38.907.180 I slot print_timing: id 1 | task 29 | total time = 1452.96 ms / 124 tokens 0.38.907.181 I slot print_timing: id 1 | task 29 | graphs reused = 1 0.38.907.181 I slot print_timing: id 1 | task 29 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.907.192 I slot release: id 1 | task 29 | stop processing: n_tokens = 123, truncated = 0 0.38.907.365 I slot print_timing: id 2 | task 30 | prompt eval time = 1402.89 ms / 144 tokens ( 9.74 ms per token, 102.65 tokens per second) 0.38.907.367 I slot print_timing: id 2 | task 30 | eval time = 50.24 ms / 2 tokens ( 50.24 ms per token, 19.90 tokens per second) 0.38.907.368 I slot print_timing: id 2 | task 30 | total time = 1453.13 ms / 146 tokens 0.38.907.368 I slot print_timing: id 2 | task 30 | graphs reused = 1 0.38.907.368 I slot print_timing: id 2 | task 30 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.907.379 I slot release: id 2 | task 30 | stop processing: n_tokens = 145, truncated = 0 0.38.907.566 I slot print_timing: id 3 | task 31 | prompt eval time = 1403.08 ms / 178 tokens ( 7.88 ms per token, 126.86 tokens per second) 0.38.907.568 I slot print_timing: id 3 | task 31 | eval time = 50.24 ms / 2 tokens ( 50.24 ms per token, 19.90 tokens per second) 0.38.907.568 I slot print_timing: id 3 | task 31 | total time = 1453.32 ms / 180 tokens 0.38.907.568 I slot print_timing: id 3 | task 31 | graphs reused = 1 0.38.907.569 I slot print_timing: id 3 | task 31 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.907.580 I slot release: id 3 | task 31 | stop processing: n_tokens = 179, truncated = 0 0.38.912.545 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.242 (> 0.100 thold), f_keep = 0.220 0.38.919.911 I slot launch_slot_: id 0 | task 36 | processing task, is_child = 0 0.38.947.890 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.248 (> 0.100 thold), f_keep = 0.228 0.38.947.948 I slot launch_slot_: id 1 | task 35 | processing task, is_child = 0 0.38.947.988 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.201 (> 0.100 thold), f_keep = 0.162 0.38.948.021 I slot launch_slot_: id 3 | task 37 | processing task, is_child = 0 0.38.948.039 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.197 (> 0.100 thold), f_keep = 0.193 0.38.948.074 I slot launch_slot_: id 2 | task 38 | processing task, is_child = 0 0.40.179.227 I slot print_timing: id 0 | task 36 | prompt eval time = 1181.07 ms / 120 tokens ( 9.84 ms per token, 101.60 tokens per second) 0.40.179.232 I slot print_timing: id 0 | task 36 | eval time = 50.07 ms / 2 tokens ( 50.07 ms per token, 19.97 tokens per second) 0.40.179.233 I slot print_timing: id 0 | task 36 | total time = 1231.14 ms / 122 tokens 0.40.179.233 I slot print_timing: id 0 | task 36 | graphs reused = 1 0.40.179.234 I slot print_timing: id 0 | task 36 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.179.256 I slot release: id 0 | task 36 | stop processing: n_tokens = 121, truncated = 0 0.40.179.408 I slot print_timing: id 1 | task 35 | prompt eval time = 1181.25 ms / 113 tokens ( 10.45 ms per token, 95.66 tokens per second) 0.40.179.409 I slot print_timing: id 1 | task 35 | eval time = 50.06 ms / 2 tokens ( 50.06 ms per token, 19.98 tokens per second) 0.40.179.410 I slot print_timing: id 1 | task 35 | total time = 1231.31 ms / 115 tokens 0.40.179.410 I slot print_timing: id 1 | task 35 | graphs reused = 1 0.40.179.410 I slot print_timing: id 1 | task 35 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.179.421 I slot release: id 1 | task 35 | stop processing: n_tokens = 114, truncated = 0 0.40.179.589 I slot print_timing: id 2 | task 38 | prompt eval time = 1181.44 ms / 142 tokens ( 8.32 ms per token, 120.19 tokens per second) 0.40.179.590 I slot print_timing: id 2 | task 38 | eval time = 50.04 ms / 2 tokens ( 50.04 ms per token, 19.98 tokens per second) 0.40.179.591 I slot print_timing: id 2 | task 38 | total time = 1231.48 ms / 144 tokens 0.40.179.591 I slot print_timing: id 2 | task 38 | graphs reused = 1 0.40.179.591 I slot print_timing: id 2 | task 38 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.179.603 I slot release: id 2 | task 38 | stop processing: n_tokens = 143, truncated = 0 0.40.179.785 I slot print_timing: id 3 | task 37 | prompt eval time = 1181.63 ms / 144 tokens ( 8.21 ms per token, 121.87 tokens per second) 0.40.179.786 I slot print_timing: id 3 | task 37 | eval time = 50.04 ms / 2 tokens ( 50.04 ms per token, 19.98 tokens per second) 0.40.179.787 I slot print_timing: id 3 | task 37 | total time = 1231.67 ms / 146 tokens 0.40.179.787 I slot print_timing: id 3 | task 37 | graphs reused = 1 0.40.179.787 I slot print_timing: id 3 | task 37 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.179.795 I slot release: id 3 | task 37 | stop processing: n_tokens = 145, truncated = 0 0.40.184.718 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.257 (> 0.100 thold), f_keep = 0.231 0.40.195.291 I slot launch_slot_: id 0 | task 43 | processing task, is_child = 0 0.40.226.541 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.196 (> 0.100 thold), f_keep = 0.246 0.40.226.606 I slot launch_slot_: id 1 | task 42 | processing task, is_child = 0 0.40.226.643 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.196 0.40.226.678 I slot launch_slot_: id 2 | task 44 | processing task, is_child = 0 0.40.226.698 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.250 (> 0.100 thold), f_keep = 0.193 0.40.226.733 I slot launch_slot_: id 3 | task 45 | processing task, is_child = 0 0.41.476.636 I slot print_timing: id 0 | task 43 | prompt eval time = 1199.79 ms / 109 tokens ( 11.01 ms per token, 90.85 tokens per second) 0.41.476.639 I slot print_timing: id 0 | task 43 | eval time = 50.10 ms / 2 tokens ( 50.10 ms per token, 19.96 tokens per second) 0.41.476.639 I slot print_timing: id 0 | task 43 | total time = 1249.89 ms / 111 tokens 0.41.476.639 I slot print_timing: id 0 | task 43 | graphs reused = 1 0.41.476.640 I slot print_timing: id 0 | task 43 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.476.658 I slot release: id 0 | task 43 | stop processing: n_tokens = 110, truncated = 0 0.41.476.816 I slot print_timing: id 1 | task 42 | prompt eval time = 1199.97 ms / 143 tokens ( 8.39 ms per token, 119.17 tokens per second) 0.41.476.818 I slot print_timing: id 1 | task 42 | eval time = 50.09 ms / 2 tokens ( 50.09 ms per token, 19.97 tokens per second) 0.41.476.819 I slot print_timing: id 1 | task 42 | total time = 1250.06 ms / 145 tokens 0.41.476.819 I slot print_timing: id 1 | task 42 | graphs reused = 1 0.41.476.819 I slot print_timing: id 1 | task 42 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.476.833 I slot release: id 1 | task 42 | stop processing: n_tokens = 144, truncated = 0 0.41.476.994 I slot print_timing: id 2 | task 44 | prompt eval time = 1200.15 ms / 123 tokens ( 9.76 ms per token, 102.49 tokens per second) 0.41.476.995 I slot print_timing: id 2 | task 44 | eval time = 50.07 ms / 2 tokens ( 50.07 ms per token, 19.97 tokens per second) 0.41.476.996 I slot print_timing: id 2 | task 44 | total time = 1250.22 ms / 125 tokens 0.41.476.996 I slot print_timing: id 2 | task 44 | graphs reused = 1 0.41.476.996 I slot print_timing: id 2 | task 44 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.477.009 I slot release: id 2 | task 44 | stop processing: n_tokens = 124, truncated = 0 0.41.477.173 I slot print_timing: id 3 | task 45 | prompt eval time = 1200.36 ms / 112 tokens ( 10.72 ms per token, 93.31 tokens per second) 0.41.477.175 I slot print_timing: id 3 | task 45 | eval time = 50.03 ms / 2 tokens ( 50.03 ms per token, 19.99 tokens per second) 0.41.477.175 I slot print_timing: id 3 | task 45 | total time = 1250.39 ms / 114 tokens 0.41.477.175 I slot print_timing: id 3 | task 45 | graphs reused = 1 0.41.477.175 I slot print_timing: id 3 | task 45 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.477.183 I slot release: id 3 | task 45 | stop processing: n_tokens = 113, truncated = 0 0.41.482.181 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 0.41.492.436 I slot launch_slot_: id 0 | task 49 | processing task, is_child = 0 0.41.523.914 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.259 (> 0.100 thold), f_keep = 0.257 0.41.523.965 I slot launch_slot_: id 3 | task 50 | processing task, is_child = 0 0.41.524.000 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.217 (> 0.100 thold), f_keep = 0.194 0.41.525.459 I slot launch_slot_: id 1 | task 51 | processing task, is_child = 0 0.41.525.482 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.206 (> 0.100 thold), f_keep = 0.226 0.41.525.512 I slot launch_slot_: id 2 | task 52 | processing task, is_child = 0 0.42.824.640 I slot print_timing: id 0 | task 49 | prompt eval time = 1248.55 ms / 102 tokens ( 12.24 ms per token, 81.69 tokens per second) 0.42.824.642 I slot print_timing: id 0 | task 49 | eval time = 50.57 ms / 2 tokens ( 50.57 ms per token, 19.78 tokens per second) 0.42.824.643 I slot print_timing: id 0 | task 49 | total time = 1299.12 ms / 104 tokens 0.42.824.643 I slot print_timing: id 0 | task 49 | graphs reused = 1 0.42.824.643 I slot print_timing: id 0 | task 49 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.824.666 I slot release: id 0 | task 49 | stop processing: n_tokens = 103, truncated = 0 0.42.824.817 I slot print_timing: id 1 | task 51 | prompt eval time = 1248.74 ms / 129 tokens ( 9.68 ms per token, 103.30 tokens per second) 0.42.824.818 I slot print_timing: id 1 | task 51 | eval time = 50.55 ms / 2 tokens ( 50.55 ms per token, 19.78 tokens per second) 0.42.824.819 I slot print_timing: id 1 | task 51 | total time = 1299.29 ms / 131 tokens 0.42.824.819 I slot print_timing: id 1 | task 51 | graphs reused = 1 0.42.824.819 I slot print_timing: id 1 | task 51 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.824.832 I slot release: id 1 | task 51 | stop processing: n_tokens = 130, truncated = 0 0.42.825.007 I slot print_timing: id 2 | task 52 | prompt eval time = 1248.95 ms / 136 tokens ( 9.18 ms per token, 108.89 tokens per second) 0.42.825.009 I slot print_timing: id 2 | task 52 | eval time = 50.52 ms / 2 tokens ( 50.52 ms per token, 19.79 tokens per second) 0.42.825.010 I slot print_timing: id 2 | task 52 | total time = 1299.47 ms / 138 tokens 0.42.825.010 I slot print_timing: id 2 | task 52 | graphs reused = 1 0.42.825.010 I slot print_timing: id 2 | task 52 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.825.033 I slot release: id 2 | task 52 | stop processing: n_tokens = 137, truncated = 0 0.42.825.208 I slot print_timing: id 3 | task 50 | prompt eval time = 1249.15 ms / 112 tokens ( 11.15 ms per token, 89.66 tokens per second) 0.42.825.213 I slot print_timing: id 3 | task 50 | eval time = 50.51 ms / 2 tokens ( 50.51 ms per token, 19.80 tokens per second) 0.42.825.214 I slot print_timing: id 3 | task 50 | total time = 1299.66 ms / 114 tokens 0.42.825.214 I slot print_timing: id 3 | task 50 | graphs reused = 1 0.42.825.214 I slot print_timing: id 3 | task 50 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.825.224 I slot release: id 3 | task 50 | stop processing: n_tokens = 113, truncated = 0 0.42.830.252 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.158 (> 0.100 thold), f_keep = 0.272 0.42.833.687 I slot launch_slot_: id 0 | task 57 | processing task, is_child = 0 0.42.865.879 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.154 (> 0.100 thold), f_keep = 0.215 0.42.865.945 I slot launch_slot_: id 1 | task 56 | processing task, is_child = 0 0.42.865.981 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.212 (> 0.100 thold), f_keep = 0.204 0.42.866.020 I slot launch_slot_: id 2 | task 58 | processing task, is_child = 0 0.42.866.039 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 0.42.866.078 I slot launch_slot_: id 3 | task 59 | processing task, is_child = 0 0.44.414.793 I slot print_timing: id 0 | task 57 | prompt eval time = 1498.76 ms / 177 tokens ( 8.47 ms per token, 118.10 tokens per second) 0.44.414.795 I slot print_timing: id 0 | task 57 | eval time = 49.95 ms / 2 tokens ( 49.95 ms per token, 20.02 tokens per second) 0.44.414.796 I slot print_timing: id 0 | task 57 | total time = 1548.71 ms / 179 tokens 0.44.414.796 I slot print_timing: id 0 | task 57 | graphs reused = 1 0.44.414.796 I slot print_timing: id 0 | task 57 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.414.817 I slot release: id 0 | task 57 | stop processing: n_tokens = 178, truncated = 0 0.44.414.974 I slot print_timing: id 1 | task 56 | prompt eval time = 1498.89 ms / 182 tokens ( 8.24 ms per token, 121.42 tokens per second) 0.44.414.976 I slot print_timing: id 1 | task 56 | eval time = 49.98 ms / 2 tokens ( 49.98 ms per token, 20.01 tokens per second) 0.44.414.976 I slot print_timing: id 1 | task 56 | total time = 1548.87 ms / 184 tokens 0.44.414.977 I slot print_timing: id 1 | task 56 | graphs reused = 1 0.44.414.977 I slot print_timing: id 1 | task 56 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.414.992 I slot release: id 1 | task 56 | stop processing: n_tokens = 183, truncated = 0 0.44.415.158 I slot print_timing: id 2 | task 58 | prompt eval time = 1499.04 ms / 132 tokens ( 11.36 ms per token, 88.06 tokens per second) 0.44.415.160 I slot print_timing: id 2 | task 58 | eval time = 50.00 ms / 2 tokens ( 50.00 ms per token, 20.00 tokens per second) 0.44.415.161 I slot print_timing: id 2 | task 58 | total time = 1549.04 ms / 134 tokens 0.44.415.161 I slot print_timing: id 2 | task 58 | graphs reused = 1 0.44.415.161 I slot print_timing: id 2 | task 58 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.415.173 I slot release: id 2 | task 58 | stop processing: n_tokens = 133, truncated = 0 0.44.415.337 I slot print_timing: id 3 | task 59 | prompt eval time = 1499.19 ms / 166 tokens ( 9.03 ms per token, 110.73 tokens per second) 0.44.415.339 I slot print_timing: id 3 | task 59 | eval time = 50.02 ms / 2 tokens ( 50.02 ms per token, 19.99 tokens per second) 0.44.415.340 I slot print_timing: id 3 | task 59 | total time = 1549.21 ms / 168 tokens 0.44.415.340 I slot print_timing: id 3 | task 59 | graphs reused = 1 0.44.415.340 I slot print_timing: id 3 | task 59 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.415.349 I slot release: id 3 | task 59 | stop processing: n_tokens = 167, truncated = 0 0.44.420.167 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.157 0.44.430.662 I slot launch_slot_: id 0 | task 63 | processing task, is_child = 0 0.44.461.934 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.153 0.44.461.994 I slot launch_slot_: id 1 | task 64 | processing task, is_child = 0 0.44.462.026 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.200 (> 0.100 thold), f_keep = 0.211 0.44.463.459 I slot launch_slot_: id 2 | task 66 | processing task, is_child = 0 0.44.463.482 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.166 (> 0.100 thold), f_keep = 0.168 0.44.463.516 I slot launch_slot_: id 3 | task 65 | processing task, is_child = 0 0.45.910.524 I slot print_timing: id 0 | task 63 | prompt eval time = 1396.76 ms / 123 tokens ( 11.36 ms per token, 88.06 tokens per second) 0.45.910.530 I slot print_timing: id 0 | task 63 | eval time = 50.24 ms / 2 tokens ( 50.24 ms per token, 19.91 tokens per second) 0.45.910.530 I slot print_timing: id 0 | task 63 | total time = 1447.00 ms / 125 tokens 0.45.910.531 I slot print_timing: id 0 | task 63 | graphs reused = 1 0.45.910.531 I slot print_timing: id 0 | task 63 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.910.550 I slot release: id 0 | task 63 | stop processing: n_tokens = 124, truncated = 0 0.45.910.706 I slot print_timing: id 1 | task 64 | prompt eval time = 1396.94 ms / 149 tokens ( 9.38 ms per token, 106.66 tokens per second) 0.45.910.710 I slot print_timing: id 1 | task 64 | eval time = 50.23 ms / 2 tokens ( 50.23 ms per token, 19.91 tokens per second) 0.45.910.710 I slot print_timing: id 1 | task 64 | total time = 1447.17 ms / 151 tokens 0.45.910.711 I slot print_timing: id 1 | task 64 | graphs reused = 1 0.45.910.711 I slot print_timing: id 1 | task 64 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.910.724 I slot release: id 1 | task 64 | stop processing: n_tokens = 150, truncated = 0 0.45.910.894 I slot print_timing: id 2 | task 66 | prompt eval time = 1397.13 ms / 140 tokens ( 9.98 ms per token, 100.21 tokens per second) 0.45.910.895 I slot print_timing: id 2 | task 66 | eval time = 50.21 ms / 2 tokens ( 50.21 ms per token, 19.92 tokens per second) 0.45.910.896 I slot print_timing: id 2 | task 66 | total time = 1447.34 ms / 142 tokens 0.45.910.896 I slot print_timing: id 2 | task 66 | graphs reused = 1 0.45.910.896 I slot print_timing: id 2 | task 66 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.910.906 I slot release: id 2 | task 66 | stop processing: n_tokens = 141, truncated = 0 0.45.911.066 I slot print_timing: id 3 | task 65 | prompt eval time = 1397.32 ms / 169 tokens ( 8.27 ms per token, 120.95 tokens per second) 0.45.911.069 I slot print_timing: id 3 | task 65 | eval time = 50.18 ms / 2 tokens ( 50.18 ms per token, 19.93 tokens per second) 0.45.911.069 I slot print_timing: id 3 | task 65 | total time = 1447.50 ms / 171 tokens 0.45.911.070 I slot print_timing: id 3 | task 65 | graphs reused = 1 0.45.911.070 I slot print_timing: id 3 | task 65 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.911.082 I slot release: id 3 | task 65 | stop processing: n_tokens = 170, truncated = 0 0.45.915.989 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.219 (> 0.100 thold), f_keep = 0.226 0.45.923.401 I slot launch_slot_: id 0 | task 70 | processing task, is_child = 0 0.45.950.997 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.172 (> 0.100 thold), f_keep = 0.187 0.45.951.050 I slot launch_slot_: id 1 | task 72 | processing task, is_child = 0 0.45.951.083 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.261 (> 0.100 thold), f_keep = 0.206 0.45.951.115 I slot launch_slot_: id 2 | task 71 | processing task, is_child = 0 0.45.951.139 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.174 (> 0.100 thold), f_keep = 0.165 0.45.951.172 I slot launch_slot_: id 3 | task 73 | processing task, is_child = 0 0.47.490.815 I slot print_timing: id 0 | task 70 | prompt eval time = 1489.43 ms / 128 tokens ( 11.64 ms per token, 85.94 tokens per second) 0.47.490.818 I slot print_timing: id 0 | task 70 | eval time = 50.20 ms / 2 tokens ( 50.20 ms per token, 19.92 tokens per second) 0.47.490.819 I slot print_timing: id 0 | task 70 | total time = 1539.63 ms / 130 tokens 0.47.490.819 I slot print_timing: id 0 | task 70 | graphs reused = 1 0.47.490.819 I slot print_timing: id 0 | task 70 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.490.837 I slot release: id 0 | task 70 | stop processing: n_tokens = 129, truncated = 0 0.47.490.987 I slot print_timing: id 1 | task 72 | prompt eval time = 1489.61 ms / 163 tokens ( 9.14 ms per token, 109.42 tokens per second) 0.47.490.988 I slot print_timing: id 1 | task 72 | eval time = 50.19 ms / 2 tokens ( 50.19 ms per token, 19.93 tokens per second) 0.47.490.989 I slot print_timing: id 1 | task 72 | total time = 1539.80 ms / 165 tokens 0.47.490.989 I slot print_timing: id 1 | task 72 | graphs reused = 1 0.47.490.989 I slot print_timing: id 1 | task 72 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.491.003 I slot release: id 1 | task 72 | stop processing: n_tokens = 164, truncated = 0 0.47.491.188 I slot print_timing: id 2 | task 71 | prompt eval time = 1489.79 ms / 111 tokens ( 13.42 ms per token, 74.51 tokens per second) 0.47.491.189 I slot print_timing: id 2 | task 71 | eval time = 50.19 ms / 2 tokens ( 50.19 ms per token, 19.92 tokens per second) 0.47.491.190 I slot print_timing: id 2 | task 71 | total time = 1539.98 ms / 113 tokens 0.47.491.190 I slot print_timing: id 2 | task 71 | graphs reused = 1 0.47.491.191 I slot print_timing: id 2 | task 71 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.491.200 I slot release: id 2 | task 71 | stop processing: n_tokens = 112, truncated = 0 0.47.491.370 I slot print_timing: id 3 | task 73 | prompt eval time = 1489.99 ms / 161 tokens ( 9.25 ms per token, 108.05 tokens per second) 0.47.491.373 I slot print_timing: id 3 | task 73 | eval time = 50.16 ms / 2 tokens ( 50.16 ms per token, 19.94 tokens per second) 0.47.491.373 I slot print_timing: id 3 | task 73 | total time = 1540.15 ms / 163 tokens 0.47.491.373 I slot print_timing: id 3 | task 73 | graphs reused = 1 0.47.491.373 I slot print_timing: id 3 | task 73 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.491.382 I slot release: id 3 | task 73 | stop processing: n_tokens = 162, truncated = 0 0.47.496.299 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.266 (> 0.100 thold), f_keep = 0.177 0.47.506.609 I slot launch_slot_: id 1 | task 77 | processing task, is_child = 0 0.47.538.034 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.250 (> 0.100 thold), f_keep = 0.217 0.47.538.089 I slot launch_slot_: id 0 | task 78 | processing task, is_child = 0 0.47.538.123 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.168 (> 0.100 thold), f_keep = 0.250 0.47.538.154 I slot launch_slot_: id 2 | task 79 | processing task, is_child = 0 0.47.538.174 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.177 (> 0.100 thold), f_keep = 0.179 0.47.538.208 I slot launch_slot_: id 3 | task 80 | processing task, is_child = 0 0.48.850.196 I slot print_timing: id 0 | task 78 | prompt eval time = 1261.40 ms / 112 tokens ( 11.26 ms per token, 88.79 tokens per second) 0.48.850.201 I slot print_timing: id 0 | task 78 | eval time = 50.58 ms / 2 tokens ( 50.58 ms per token, 19.77 tokens per second) 0.48.850.202 I slot print_timing: id 0 | task 78 | total time = 1311.98 ms / 114 tokens 0.48.850.202 I slot print_timing: id 0 | task 78 | graphs reused = 1 0.48.850.202 I slot print_timing: id 0 | task 78 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.850.221 I slot release: id 0 | task 78 | stop processing: n_tokens = 113, truncated = 0 0.48.850.373 I slot print_timing: id 1 | task 77 | prompt eval time = 1261.60 ms / 109 tokens ( 11.57 ms per token, 86.40 tokens per second) 0.48.850.374 I slot print_timing: id 1 | task 77 | eval time = 50.55 ms / 2 tokens ( 50.55 ms per token, 19.78 tokens per second) 0.48.850.375 I slot print_timing: id 1 | task 77 | total time = 1312.15 ms / 111 tokens 0.48.850.375 I slot print_timing: id 1 | task 77 | graphs reused = 1 0.48.850.375 I slot print_timing: id 1 | task 77 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.850.386 I slot release: id 1 | task 77 | stop processing: n_tokens = 110, truncated = 0 0.48.850.566 I slot print_timing: id 2 | task 79 | prompt eval time = 1261.80 ms / 167 tokens ( 7.56 ms per token, 132.35 tokens per second) 0.48.850.568 I slot print_timing: id 2 | task 79 | eval time = 50.53 ms / 2 tokens ( 50.53 ms per token, 19.79 tokens per second) 0.48.850.569 I slot print_timing: id 2 | task 79 | total time = 1312.33 ms / 169 tokens 0.48.850.569 I slot print_timing: id 2 | task 79 | graphs reused = 1 0.48.850.569 I slot print_timing: id 2 | task 79 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.850.587 I slot release: id 2 | task 79 | stop processing: n_tokens = 168, truncated = 0 0.48.850.767 I slot print_timing: id 3 | task 80 | prompt eval time = 1261.99 ms / 164 tokens ( 7.70 ms per token, 129.95 tokens per second) 0.48.850.770 I slot print_timing: id 3 | task 80 | eval time = 50.52 ms / 2 tokens ( 50.52 ms per token, 19.79 tokens per second) 0.48.850.770 I slot print_timing: id 3 | task 80 | total time = 1312.52 ms / 166 tokens 0.48.850.771 I slot print_timing: id 3 | task 80 | graphs reused = 1 0.48.850.771 I slot print_timing: id 3 | task 80 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.850.780 I slot release: id 3 | task 80 | stop processing: n_tokens = 165, truncated = 0 0.48.855.651 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.248 0.48.867.525 I slot launch_slot_: id 0 | task 84 | processing task, is_child = 0 0.48.891.551 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.190 (> 0.100 thold), f_keep = 0.255 0.48.891.604 I slot launch_slot_: id 1 | task 85 | processing task, is_child = 0 0.48.891.638 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.214 (> 0.100 thold), f_keep = 0.167 0.48.891.671 I slot launch_slot_: id 2 | task 86 | processing task, is_child = 0 0.48.891.690 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.233 (> 0.100 thold), f_keep = 0.170 0.48.891.724 I slot launch_slot_: id 3 | task 87 | processing task, is_child = 0 0.50.138.589 I slot print_timing: id 0 | task 84 | prompt eval time = 1196.58 ms / 122 tokens ( 9.81 ms per token, 101.96 tokens per second) 0.50.138.591 I slot print_timing: id 0 | task 84 | eval time = 50.27 ms / 2 tokens ( 50.27 ms per token, 19.89 tokens per second) 0.50.138.592 I slot print_timing: id 0 | task 84 | total time = 1246.86 ms / 124 tokens 0.50.138.593 I slot print_timing: id 0 | task 84 | graphs reused = 1 0.50.138.593 I slot print_timing: id 0 | task 84 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.138.623 I slot release: id 0 | task 84 | stop processing: n_tokens = 123, truncated = 0 0.50.138.774 I slot print_timing: id 1 | task 85 | prompt eval time = 1196.73 ms / 147 tokens ( 8.14 ms per token, 122.84 tokens per second) 0.50.138.777 I slot print_timing: id 1 | task 85 | eval time = 50.30 ms / 2 tokens ( 50.30 ms per token, 19.88 tokens per second) 0.50.138.777 I slot print_timing: id 1 | task 85 | total time = 1247.03 ms / 149 tokens 0.50.138.777 I slot print_timing: id 1 | task 85 | graphs reused = 1 0.50.138.778 I slot print_timing: id 1 | task 85 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.138.791 I slot release: id 1 | task 85 | stop processing: n_tokens = 148, truncated = 0 0.50.138.969 I slot print_timing: id 2 | task 86 | prompt eval time = 1196.89 ms / 131 tokens ( 9.14 ms per token, 109.45 tokens per second) 0.50.138.971 I slot print_timing: id 2 | task 86 | eval time = 50.33 ms / 2 tokens ( 50.33 ms per token, 19.87 tokens per second) 0.50.138.972 I slot print_timing: id 2 | task 86 | total time = 1247.21 ms / 133 tokens 0.50.138.972 I slot print_timing: id 2 | task 86 | graphs reused = 1 0.50.138.972 I slot print_timing: id 2 | task 86 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.138.980 I slot release: id 2 | task 86 | stop processing: n_tokens = 132, truncated = 0 0.50.139.166 I slot print_timing: id 3 | task 87 | prompt eval time = 1197.04 ms / 120 tokens ( 9.98 ms per token, 100.25 tokens per second) 0.50.139.168 I slot print_timing: id 3 | task 87 | eval time = 50.36 ms / 2 tokens ( 50.36 ms per token, 19.86 tokens per second) 0.50.139.168 I slot print_timing: id 3 | task 87 | total time = 1247.40 ms / 122 tokens 0.50.139.169 I slot print_timing: id 3 | task 87 | graphs reused = 1 0.50.139.169 I slot print_timing: id 3 | task 87 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.139.177 I slot release: id 3 | task 87 | stop processing: n_tokens = 121, truncated = 0 0.50.144.057 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.221 (> 0.100 thold), f_keep = 0.236 0.50.154.333 I slot launch_slot_: id 0 | task 91 | processing task, is_child = 0 0.50.185.089 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.226 (> 0.100 thold), f_keep = 0.189 0.50.185.144 I slot launch_slot_: id 1 | task 92 | processing task, is_child = 0 0.50.185.176 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.194 (> 0.100 thold), f_keep = 0.212 0.50.185.208 I slot launch_slot_: id 2 | task 93 | processing task, is_child = 0 0.50.185.226 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 0.50.186.655 I slot launch_slot_: id 3 | task 94 | processing task, is_child = 0 0.51.441.306 I slot print_timing: id 0 | task 91 | prompt eval time = 1204.39 ms / 131 tokens ( 9.19 ms per token, 108.77 tokens per second) 0.51.441.308 I slot print_timing: id 0 | task 91 | eval time = 50.25 ms / 2 tokens ( 50.25 ms per token, 19.90 tokens per second) 0.51.441.309 I slot print_timing: id 0 | task 91 | total time = 1254.64 ms / 133 tokens 0.51.441.309 I slot print_timing: id 0 | task 91 | graphs reused = 1 0.51.441.310 I slot print_timing: id 0 | task 91 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.441.328 I slot release: id 0 | task 91 | stop processing: n_tokens = 132, truncated = 0 0.51.441.480 I slot print_timing: id 1 | task 92 | prompt eval time = 1204.59 ms / 124 tokens ( 9.71 ms per token, 102.94 tokens per second) 0.51.441.484 I slot print_timing: id 1 | task 92 | eval time = 50.22 ms / 2 tokens ( 50.22 ms per token, 19.91 tokens per second) 0.51.441.484 I slot print_timing: id 1 | task 92 | total time = 1254.81 ms / 126 tokens 0.51.441.485 I slot print_timing: id 1 | task 92 | graphs reused = 1 0.51.441.485 I slot print_timing: id 1 | task 92 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.441.495 I slot release: id 1 | task 92 | stop processing: n_tokens = 125, truncated = 0 0.51.441.660 I slot print_timing: id 2 | task 93 | prompt eval time = 1204.78 ms / 144 tokens ( 8.37 ms per token, 119.52 tokens per second) 0.51.441.666 I slot print_timing: id 2 | task 93 | eval time = 50.20 ms / 2 tokens ( 50.20 ms per token, 19.92 tokens per second) 0.51.441.666 I slot print_timing: id 2 | task 93 | total time = 1254.97 ms / 146 tokens 0.51.441.666 I slot print_timing: id 2 | task 93 | graphs reused = 1 0.51.441.667 I slot print_timing: id 2 | task 93 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.441.676 I slot release: id 2 | task 93 | stop processing: n_tokens = 145, truncated = 0 0.51.441.846 I slot print_timing: id 3 | task 94 | prompt eval time = 1204.98 ms / 141 tokens ( 8.55 ms per token, 117.01 tokens per second) 0.51.441.848 I slot print_timing: id 3 | task 94 | eval time = 50.17 ms / 2 tokens ( 50.17 ms per token, 19.93 tokens per second) 0.51.441.848 I slot print_timing: id 3 | task 94 | total time = 1255.15 ms / 143 tokens 0.51.441.849 I slot print_timing: id 3 | task 94 | graphs reused = 1 0.51.441.849 I slot print_timing: id 3 | task 94 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.441.856 I slot release: id 3 | task 94 | stop processing: n_tokens = 142, truncated = 0 0.51.447.066 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.231 (> 0.100 thold), f_keep = 0.212 0.51.454.344 I slot launch_slot_: id 0 | task 98 | processing task, is_child = 0 0.51.482.258 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.271 (> 0.100 thold), f_keep = 0.200 0.51.482.316 I slot launch_slot_: id 2 | task 100 | processing task, is_child = 0 0.51.482.355 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.237 (> 0.100 thold), f_keep = 0.224 0.51.482.391 I slot launch_slot_: id 1 | task 99 | processing task, is_child = 0 0.51.482.410 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.169 (> 0.100 thold), f_keep = 0.204 0.51.482.443 I slot launch_slot_: id 3 | task 101 | processing task, is_child = 0 0.52.812.741 I slot print_timing: id 0 | task 98 | prompt eval time = 1279.90 ms / 121 tokens ( 10.58 ms per token, 94.54 tokens per second) 0.52.812.742 I slot print_timing: id 0 | task 98 | eval time = 50.39 ms / 2 tokens ( 50.39 ms per token, 19.85 tokens per second) 0.52.812.743 I slot print_timing: id 0 | task 98 | total time = 1330.29 ms / 123 tokens 0.52.812.743 I slot print_timing: id 0 | task 98 | graphs reused = 1 0.52.812.744 I slot print_timing: id 0 | task 98 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.812.762 I slot release: id 0 | task 98 | stop processing: n_tokens = 122, truncated = 0 0.52.812.916 I slot print_timing: id 1 | task 99 | prompt eval time = 1280.10 ms / 118 tokens ( 10.85 ms per token, 92.18 tokens per second) 0.52.812.921 I slot print_timing: id 1 | task 99 | eval time = 50.35 ms / 2 tokens ( 50.35 ms per token, 19.86 tokens per second) 0.52.812.921 I slot print_timing: id 1 | task 99 | total time = 1330.45 ms / 120 tokens 0.52.812.922 I slot print_timing: id 1 | task 99 | graphs reused = 1 0.52.812.922 I slot print_timing: id 1 | task 99 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.812.932 I slot release: id 1 | task 99 | stop processing: n_tokens = 119, truncated = 0 0.52.813.113 I slot print_timing: id 2 | task 100 | prompt eval time = 1280.29 ms / 107 tokens ( 11.97 ms per token, 83.57 tokens per second) 0.52.813.115 I slot print_timing: id 2 | task 100 | eval time = 50.35 ms / 2 tokens ( 50.35 ms per token, 19.86 tokens per second) 0.52.813.115 I slot print_timing: id 2 | task 100 | total time = 1330.64 ms / 109 tokens 0.52.813.116 I slot print_timing: id 2 | task 100 | graphs reused = 1 0.52.813.116 I slot print_timing: id 2 | task 100 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.813.123 I slot release: id 2 | task 100 | stop processing: n_tokens = 108, truncated = 0 0.52.813.293 I slot print_timing: id 3 | task 101 | prompt eval time = 1280.49 ms / 172 tokens ( 7.44 ms per token, 134.32 tokens per second) 0.52.813.295 I slot print_timing: id 3 | task 101 | eval time = 50.31 ms / 2 tokens ( 50.31 ms per token, 19.88 tokens per second) 0.52.813.296 I slot print_timing: id 3 | task 101 | total time = 1330.80 ms / 174 tokens 0.52.813.296 I slot print_timing: id 3 | task 101 | graphs reused = 1 0.52.813.296 I slot print_timing: id 3 | task 101 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.813.306 I slot release: id 3 | task 101 | stop processing: n_tokens = 173, truncated = 0 0.52.817.575 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.213 (> 0.100 thold), f_keep = 0.244 0.52.829.181 I slot launch_slot_: id 1 | task 105 | processing task, is_child = 0 0.52.853.047 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.250 (> 0.100 thold), f_keep = 0.269 0.52.853.098 I slot launch_slot_: id 2 | task 106 | processing task, is_child = 0 0.52.853.131 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.117 (> 0.100 thold), f_keep = 0.230 0.52.853.163 I slot launch_slot_: id 0 | task 107 | processing task, is_child = 0 0.52.853.182 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.158 (> 0.100 thold), f_keep = 0.162 0.52.853.217 I slot launch_slot_: id 3 | task 108 | processing task, is_child = 0 0.54.563.331 I slot print_timing: id 0 | task 107 | prompt eval time = 1659.99 ms / 240 tokens ( 6.92 ms per token, 144.58 tokens per second) 0.54.563.333 I slot print_timing: id 0 | task 107 | eval time = 50.12 ms / 2 tokens ( 50.12 ms per token, 19.95 tokens per second) 0.54.563.334 I slot print_timing: id 0 | task 107 | total time = 1710.11 ms / 242 tokens 0.54.563.335 I slot print_timing: id 0 | task 107 | graphs reused = 1 0.54.563.335 I slot print_timing: id 0 | task 107 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.563.362 I slot release: id 0 | task 107 | stop processing: n_tokens = 241, truncated = 0 0.54.563.511 I slot print_timing: id 1 | task 105 | prompt eval time = 1660.17 ms / 136 tokens ( 12.21 ms per token, 81.92 tokens per second) 0.54.563.513 I slot print_timing: id 1 | task 105 | eval time = 50.10 ms / 2 tokens ( 50.10 ms per token, 19.96 tokens per second) 0.54.563.513 I slot print_timing: id 1 | task 105 | total time = 1710.27 ms / 138 tokens 0.54.563.513 I slot print_timing: id 1 | task 105 | graphs reused = 1 0.54.563.514 I slot print_timing: id 1 | task 105 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.563.525 I slot release: id 1 | task 105 | stop processing: n_tokens = 137, truncated = 0 0.54.563.692 I slot print_timing: id 2 | task 106 | prompt eval time = 1660.36 ms / 116 tokens ( 14.31 ms per token, 69.86 tokens per second) 0.54.563.697 I slot print_timing: id 2 | task 106 | eval time = 50.08 ms / 2 tokens ( 50.08 ms per token, 19.97 tokens per second) 0.54.563.698 I slot print_timing: id 2 | task 106 | total time = 1710.44 ms / 118 tokens 0.54.563.698 I slot print_timing: id 2 | task 106 | graphs reused = 1 0.54.563.698 I slot print_timing: id 2 | task 106 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.563.710 I slot release: id 2 | task 106 | stop processing: n_tokens = 117, truncated = 0 0.54.563.867 I slot print_timing: id 3 | task 108 | prompt eval time = 1660.56 ms / 177 tokens ( 9.38 ms per token, 106.59 tokens per second) 0.54.563.869 I slot print_timing: id 3 | task 108 | eval time = 50.05 ms / 2 tokens ( 50.05 ms per token, 19.98 tokens per second) 0.54.563.869 I slot print_timing: id 3 | task 108 | total time = 1710.60 ms / 179 tokens 0.54.563.870 I slot print_timing: id 3 | task 108 | graphs reused = 1 0.54.563.870 I slot print_timing: id 3 | task 108 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.563.882 I slot release: id 3 | task 108 | stop processing: n_tokens = 178, truncated = 0 0.54.568.644 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.218 (> 0.100 thold), f_keep = 0.265 0.54.579.273 I slot launch_slot_: id 2 | task 112 | processing task, is_child = 0 0.54.617.615 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.187 (> 0.100 thold), f_keep = 0.212 0.54.619.228 I slot launch_slot_: id 1 | task 114 | processing task, is_child = 0 0.54.619.275 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.116 0.54.619.319 I slot launch_slot_: id 0 | task 113 | processing task, is_child = 0 0.54.619.341 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.124 (> 0.100 thold), f_keep = 0.157 0.54.619.385 I slot launch_slot_: id 3 | task 115 | processing task, is_child = 0 0.56.346.818 I slot print_timing: id 0 | task 113 | prompt eval time = 1676.94 ms / 160 tokens ( 10.48 ms per token, 95.41 tokens per second) 0.56.346.821 I slot print_timing: id 0 | task 113 | eval time = 50.46 ms / 2 tokens ( 50.46 ms per token, 19.82 tokens per second) 0.56.346.822 I slot print_timing: id 0 | task 113 | total time = 1727.40 ms / 162 tokens 0.56.346.822 I slot print_timing: id 0 | task 113 | graphs reused = 1 0.56.346.823 I slot print_timing: id 0 | task 113 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.346.845 I slot release: id 0 | task 113 | stop processing: n_tokens = 161, truncated = 0 0.56.347.001 I slot print_timing: id 1 | task 114 | prompt eval time = 1677.11 ms / 155 tokens ( 10.82 ms per token, 92.42 tokens per second) 0.56.347.004 I slot print_timing: id 1 | task 114 | eval time = 50.45 ms / 2 tokens ( 50.45 ms per token, 19.82 tokens per second) 0.56.347.004 I slot print_timing: id 1 | task 114 | total time = 1727.56 ms / 157 tokens 0.56.347.004 I slot print_timing: id 1 | task 114 | graphs reused = 1 0.56.347.004 I slot print_timing: id 1 | task 114 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.347.018 I slot release: id 1 | task 114 | stop processing: n_tokens = 156, truncated = 0 0.56.347.185 I slot print_timing: id 2 | task 112 | prompt eval time = 1677.30 ms / 142 tokens ( 11.81 ms per token, 84.66 tokens per second) 0.56.347.191 I slot print_timing: id 2 | task 112 | eval time = 50.43 ms / 2 tokens ( 50.43 ms per token, 19.83 tokens per second) 0.56.347.191 I slot print_timing: id 2 | task 112 | total time = 1727.73 ms / 144 tokens 0.56.347.192 I slot print_timing: id 2 | task 112 | graphs reused = 1 0.56.347.192 I slot print_timing: id 2 | task 112 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.347.201 I slot release: id 2 | task 112 | stop processing: n_tokens = 143, truncated = 0 0.56.347.360 I slot print_timing: id 3 | task 115 | prompt eval time = 1677.50 ms / 226 tokens ( 7.42 ms per token, 134.72 tokens per second) 0.56.347.362 I slot print_timing: id 3 | task 115 | eval time = 50.40 ms / 2 tokens ( 50.40 ms per token, 19.84 tokens per second) 0.56.347.362 I slot print_timing: id 3 | task 115 | total time = 1727.90 ms / 228 tokens 0.56.347.362 I slot print_timing: id 3 | task 115 | graphs reused = 1 0.56.347.362 I slot print_timing: id 3 | task 115 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.347.377 I slot release: id 3 | task 115 | stop processing: n_tokens = 227, truncated = 0 0.56.352.536 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.295 (> 0.100 thold), f_keep = 0.217 0.56.368.514 I slot launch_slot_: id 2 | task 119 | processing task, is_child = 0 0.56.405.289 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.254 (> 0.100 thold), f_keep = 0.186 0.56.405.375 I slot launch_slot_: id 1 | task 120 | processing task, is_child = 0 0.56.405.422 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.174 0.56.405.470 I slot launch_slot_: id 0 | task 121 | processing task, is_child = 0 0.56.405.493 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 0.56.406.979 I slot launch_slot_: id 3 | task 122 | processing task, is_child = 0 0.57.854.323 I slot print_timing: id 0 | task 121 | prompt eval time = 1396.97 ms / 141 tokens ( 9.91 ms per token, 100.93 tokens per second) 0.57.854.325 I slot print_timing: id 0 | task 121 | eval time = 50.36 ms / 2 tokens ( 50.36 ms per token, 19.86 tokens per second) 0.57.854.326 I slot print_timing: id 0 | task 121 | total time = 1447.33 ms / 143 tokens 0.57.854.326 I slot print_timing: id 0 | task 121 | graphs reused = 1 0.57.854.327 I slot print_timing: id 0 | task 121 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.854.347 I slot release: id 0 | task 121 | stop processing: n_tokens = 142, truncated = 0 0.57.854.496 I slot print_timing: id 1 | task 120 | prompt eval time = 1397.15 ms / 114 tokens ( 12.26 ms per token, 81.59 tokens per second) 0.57.854.499 I slot print_timing: id 1 | task 120 | eval time = 50.34 ms / 2 tokens ( 50.34 ms per token, 19.87 tokens per second) 0.57.854.499 I slot print_timing: id 1 | task 120 | total time = 1447.49 ms / 116 tokens 0.57.854.499 I slot print_timing: id 1 | task 120 | graphs reused = 1 0.57.854.500 I slot print_timing: id 1 | task 120 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.854.511 I slot release: id 1 | task 120 | stop processing: n_tokens = 115, truncated = 0 0.57.854.685 I slot print_timing: id 2 | task 119 | prompt eval time = 1397.34 ms / 105 tokens ( 13.31 ms per token, 75.14 tokens per second) 0.57.854.686 I slot print_timing: id 2 | task 119 | eval time = 50.32 ms / 2 tokens ( 50.32 ms per token, 19.87 tokens per second) 0.57.854.687 I slot print_timing: id 2 | task 119 | total time = 1447.66 ms / 107 tokens 0.57.854.687 I slot print_timing: id 2 | task 119 | graphs reused = 1 0.57.854.687 I slot print_timing: id 2 | task 119 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.854.697 I slot release: id 2 | task 119 | stop processing: n_tokens = 106, truncated = 0 0.57.854.878 I slot print_timing: id 3 | task 122 | prompt eval time = 1397.55 ms / 192 tokens ( 7.28 ms per token, 137.38 tokens per second) 0.57.854.880 I slot print_timing: id 3 | task 122 | eval time = 50.30 ms / 2 tokens ( 50.30 ms per token, 19.88 tokens per second) 0.57.854.880 I slot print_timing: id 3 | task 122 | total time = 1447.84 ms / 194 tokens 0.57.854.880 I slot print_timing: id 3 | task 122 | graphs reused = 1 0.57.854.880 I slot print_timing: id 3 | task 122 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.854.891 I slot release: id 3 | task 122 | stop processing: n_tokens = 193, truncated = 0 0.57.859.789 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.269 (> 0.100 thold), f_keep = 0.252 0.57.871.319 I slot launch_slot_: id 1 | task 126 | processing task, is_child = 0 0.57.907.758 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.238 (> 0.100 thold), f_keep = 0.274 0.57.907.832 I slot launch_slot_: id 2 | task 127 | processing task, is_child = 0 0.57.907.871 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.207 (> 0.100 thold), f_keep = 0.197 0.57.907.916 I slot launch_slot_: id 0 | task 128 | processing task, is_child = 0 0.57.907.938 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.163 (> 0.100 thold), f_keep = 0.145 0.57.907.985 I slot launch_slot_: id 3 | task 129 | processing task, is_child = 0 0.59.335.758 I slot print_timing: id 0 | task 128 | prompt eval time = 1377.59 ms / 135 tokens ( 10.20 ms per token, 98.00 tokens per second) 0.59.335.760 I slot print_timing: id 0 | task 128 | eval time = 50.16 ms / 2 tokens ( 50.16 ms per token, 19.94 tokens per second) 0.59.335.764 I slot print_timing: id 0 | task 128 | total time = 1427.75 ms / 137 tokens 0.59.335.764 I slot print_timing: id 0 | task 128 | graphs reused = 1 0.59.335.765 I slot print_timing: id 0 | task 128 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.335.786 I slot release: id 0 | task 128 | stop processing: n_tokens = 136, truncated = 0 0.59.335.952 I slot print_timing: id 1 | task 126 | prompt eval time = 1377.78 ms / 108 tokens ( 12.76 ms per token, 78.39 tokens per second) 0.59.335.954 I slot print_timing: id 1 | task 126 | eval time = 50.16 ms / 2 tokens ( 50.16 ms per token, 19.94 tokens per second) 0.59.335.955 I slot print_timing: id 1 | task 126 | total time = 1427.94 ms / 110 tokens 0.59.335.955 I slot print_timing: id 1 | task 126 | graphs reused = 1 0.59.335.955 I slot print_timing: id 1 | task 126 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.335.965 I slot release: id 1 | task 126 | stop processing: n_tokens = 109, truncated = 0 0.59.336.146 I slot print_timing: id 2 | task 127 | prompt eval time = 1377.97 ms / 122 tokens ( 11.29 ms per token, 88.54 tokens per second) 0.59.336.148 I slot print_timing: id 2 | task 127 | eval time = 50.15 ms / 2 tokens ( 50.15 ms per token, 19.94 tokens per second) 0.59.336.148 I slot print_timing: id 2 | task 127 | total time = 1428.12 ms / 124 tokens 0.59.336.149 I slot print_timing: id 2 | task 127 | graphs reused = 1 0.59.336.149 I slot print_timing: id 2 | task 127 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.336.159 I slot release: id 2 | task 127 | stop processing: n_tokens = 123, truncated = 0 0.59.336.340 I slot print_timing: id 3 | task 129 | prompt eval time = 1378.17 ms / 172 tokens ( 8.01 ms per token, 124.80 tokens per second) 0.59.336.342 I slot print_timing: id 3 | task 129 | eval time = 50.14 ms / 2 tokens ( 50.14 ms per token, 19.94 tokens per second) 0.59.336.343 I slot print_timing: id 3 | task 129 | total time = 1428.30 ms / 174 tokens 0.59.336.343 I slot print_timing: id 3 | task 129 | graphs reused = 1 0.59.336.344 I slot print_timing: id 3 | task 129 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.336.354 I slot release: id 3 | task 129 | stop processing: n_tokens = 173, truncated = 0 0.59.341.257 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.242 (> 0.100 thold), f_keep = 0.266 0.59.341.281 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.188 MiB) 0.59.346.538 I slot launch_slot_: id 1 | task 133 | processing task, is_child = 0 0.59.359.188 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.032 MiB) 0.59.362.586 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.895 MiB) 0.59.372.842 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 0.59.372.915 I slot launch_slot_: id 0 | task 134 | processing task, is_child = 0 0.59.372.952 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.209 (> 0.100 thold), f_keep = 0.228 0.59.372.996 I slot launch_slot_: id 2 | task 135 | processing task, is_child = 0 0.59.373.018 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.176 (> 0.100 thold), f_keep = 0.162 0.59.373.063 I slot launch_slot_: id 3 | task 136 | processing task, is_child = 0 1.00.752.335 I slot print_timing: id 0 | task 134 | prompt eval time = 1329.15 ms / 135 tokens ( 9.85 ms per token, 101.57 tokens per second) 1.00.752.338 I slot print_timing: id 0 | task 134 | eval time = 50.12 ms / 2 tokens ( 50.12 ms per token, 19.95 tokens per second) 1.00.752.339 I slot print_timing: id 0 | task 134 | total time = 1379.26 ms / 137 tokens 1.00.752.339 I slot print_timing: id 0 | task 134 | graphs reused = 1 1.00.752.340 I slot print_timing: id 0 | task 134 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.752.358 I slot release: id 0 | task 134 | stop processing: n_tokens = 136, truncated = 0 1.00.752.508 I slot print_timing: id 1 | task 133 | prompt eval time = 1329.32 ms / 120 tokens ( 11.08 ms per token, 90.27 tokens per second) 1.00.752.511 I slot print_timing: id 1 | task 133 | eval time = 50.10 ms / 2 tokens ( 50.10 ms per token, 19.96 tokens per second) 1.00.752.511 I slot print_timing: id 1 | task 133 | total time = 1379.42 ms / 122 tokens 1.00.752.511 I slot print_timing: id 1 | task 133 | graphs reused = 1 1.00.752.512 I slot print_timing: id 1 | task 133 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.752.523 I slot release: id 1 | task 133 | stop processing: n_tokens = 121, truncated = 0 1.00.752.699 I slot print_timing: id 2 | task 135 | prompt eval time = 1329.52 ms / 134 tokens ( 9.92 ms per token, 100.79 tokens per second) 1.00.752.700 I slot print_timing: id 2 | task 135 | eval time = 50.08 ms / 2 tokens ( 50.08 ms per token, 19.97 tokens per second) 1.00.752.701 I slot print_timing: id 2 | task 135 | total time = 1379.60 ms / 136 tokens 1.00.752.701 I slot print_timing: id 2 | task 135 | graphs reused = 1 1.00.752.701 I slot print_timing: id 2 | task 135 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.752.710 I slot release: id 2 | task 135 | stop processing: n_tokens = 135, truncated = 0 1.00.752.881 I slot print_timing: id 3 | task 136 | prompt eval time = 1329.73 ms / 159 tokens ( 8.36 ms per token, 119.57 tokens per second) 1.00.752.883 I slot print_timing: id 3 | task 136 | eval time = 50.04 ms / 2 tokens ( 50.04 ms per token, 19.98 tokens per second) 1.00.752.883 I slot print_timing: id 3 | task 136 | total time = 1379.77 ms / 161 tokens 1.00.752.883 I slot print_timing: id 3 | task 136 | graphs reused = 1 1.00.752.883 I slot print_timing: id 3 | task 136 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.752.892 I slot release: id 3 | task 136 | stop processing: n_tokens = 160, truncated = 0 1.00.757.790 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 1.00.757.812 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.618 MiB) 1.00.761.185 I slot launch_slot_: id 0 | task 140 | processing task, is_child = 0 1.00.761.206 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.557 MiB) 1.00.764.505 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.775 MiB) 1.00.767.856 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.091 MiB) 1.00.779.416 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.163 (> 0.100 thold), f_keep = 0.231 1.00.779.462 I slot launch_slot_: id 1 | task 141 | processing task, is_child = 0 1.00.779.502 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.160 (> 0.100 thold), f_keep = 0.207 1.00.779.538 I slot launch_slot_: id 2 | task 143 | processing task, is_child = 0 1.00.779.558 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 1.00.779.592 I slot launch_slot_: id 3 | task 142 | processing task, is_child = 0 1.02.227.539 I slot print_timing: id 0 | task 140 | prompt eval time = 1397.65 ms / 130 tokens ( 10.75 ms per token, 93.01 tokens per second) 1.02.227.542 I slot print_timing: id 0 | task 140 | eval time = 50.29 ms / 2 tokens ( 50.29 ms per token, 19.88 tokens per second) 1.02.227.542 I slot print_timing: id 0 | task 140 | total time = 1447.94 ms / 132 tokens 1.02.227.543 I slot print_timing: id 0 | task 140 | graphs reused = 1 1.02.227.543 I slot print_timing: id 0 | task 140 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.227.566 I slot release: id 0 | task 140 | stop processing: n_tokens = 131, truncated = 0 1.02.227.719 I slot print_timing: id 1 | task 141 | prompt eval time = 1397.80 ms / 172 tokens ( 8.13 ms per token, 123.05 tokens per second) 1.02.227.720 I slot print_timing: id 1 | task 141 | eval time = 50.31 ms / 2 tokens ( 50.31 ms per token, 19.88 tokens per second) 1.02.227.721 I slot print_timing: id 1 | task 141 | total time = 1448.11 ms / 174 tokens 1.02.227.721 I slot print_timing: id 1 | task 141 | graphs reused = 1 1.02.227.721 I slot print_timing: id 1 | task 141 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.227.735 I slot release: id 1 | task 141 | stop processing: n_tokens = 173, truncated = 0 1.02.227.906 I slot print_timing: id 2 | task 143 | prompt eval time = 1397.99 ms / 175 tokens ( 7.99 ms per token, 125.18 tokens per second) 1.02.227.907 I slot print_timing: id 2 | task 143 | eval time = 50.29 ms / 2 tokens ( 50.29 ms per token, 19.88 tokens per second) 1.02.227.908 I slot print_timing: id 2 | task 143 | total time = 1448.28 ms / 177 tokens 1.02.227.908 I slot print_timing: id 2 | task 143 | graphs reused = 1 1.02.227.908 I slot print_timing: id 2 | task 143 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.227.921 I slot release: id 2 | task 143 | stop processing: n_tokens = 176, truncated = 0 1.02.228.099 I slot print_timing: id 3 | task 142 | prompt eval time = 1398.19 ms / 180 tokens ( 7.77 ms per token, 128.74 tokens per second) 1.02.228.101 I slot print_timing: id 3 | task 142 | eval time = 50.28 ms / 2 tokens ( 50.28 ms per token, 19.89 tokens per second) 1.02.228.101 I slot print_timing: id 3 | task 142 | total time = 1448.47 ms / 182 tokens 1.02.228.102 I slot print_timing: id 3 | task 142 | graphs reused = 1 1.02.228.102 I slot print_timing: id 3 | task 142 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.228.113 I slot release: id 3 | task 142 | stop processing: n_tokens = 181, truncated = 0 1.02.232.781 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.243 (> 0.100 thold), f_keep = 0.214 1.02.232.807 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.934 MiB) 1.02.245.127 I slot launch_slot_: id 0 | task 148 | processing task, is_child = 0 1.02.245.157 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.579 MiB) 1.02.255.170 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.973 MiB) 1.02.265.390 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.306 MiB) 1.02.274.946 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 1.02.276.443 I slot launch_slot_: id 1 | task 147 | processing task, is_child = 0 1.02.276.487 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.159 1.02.276.527 I slot launch_slot_: id 2 | task 149 | processing task, is_child = 0 1.02.276.549 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 1.02.278.436 I slot launch_slot_: id 3 | task 150 | processing task, is_child = 0 1.03.317.452 I slot print_timing: id 0 | task 148 | prompt eval time = 988.39 ms / 115 tokens ( 8.59 ms per token, 116.35 tokens per second) 1.03.317.454 I slot print_timing: id 0 | task 148 | eval time = 50.61 ms / 2 tokens ( 50.61 ms per token, 19.76 tokens per second) 1.03.317.454 I slot print_timing: id 0 | task 148 | total time = 1039.00 ms / 117 tokens 1.03.317.455 I slot print_timing: id 0 | task 148 | graphs reused = 1 1.03.317.455 I slot print_timing: id 0 | task 148 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.317.474 I slot release: id 0 | task 148 | stop processing: n_tokens = 116, truncated = 0 1.03.317.634 I slot print_timing: id 1 | task 147 | prompt eval time = 988.54 ms / 115 tokens ( 8.60 ms per token, 116.33 tokens per second) 1.03.317.636 I slot print_timing: id 1 | task 147 | eval time = 50.63 ms / 2 tokens ( 50.63 ms per token, 19.75 tokens per second) 1.03.317.636 I slot print_timing: id 1 | task 147 | total time = 1039.17 ms / 117 tokens 1.03.317.636 I slot print_timing: id 1 | task 147 | graphs reused = 1 1.03.317.637 I slot print_timing: id 1 | task 147 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.317.646 I slot release: id 1 | task 147 | stop processing: n_tokens = 116, truncated = 0 1.03.317.821 I slot print_timing: id 2 | task 149 | prompt eval time = 988.72 ms / 123 tokens ( 8.04 ms per token, 124.40 tokens per second) 1.03.317.825 I slot print_timing: id 2 | task 149 | eval time = 50.62 ms / 2 tokens ( 50.62 ms per token, 19.75 tokens per second) 1.03.317.826 I slot print_timing: id 2 | task 149 | total time = 1039.35 ms / 125 tokens 1.03.317.826 I slot print_timing: id 2 | task 149 | graphs reused = 1 1.03.317.826 I slot print_timing: id 2 | task 149 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.317.837 I slot release: id 2 | task 149 | stop processing: n_tokens = 124, truncated = 0 1.03.318.015 I slot print_timing: id 3 | task 150 | prompt eval time = 988.90 ms / 123 tokens ( 8.04 ms per token, 124.38 tokens per second) 1.03.318.016 I slot print_timing: id 3 | task 150 | eval time = 50.62 ms / 2 tokens ( 50.62 ms per token, 19.75 tokens per second) 1.03.318.017 I slot print_timing: id 3 | task 150 | total time = 1039.52 ms / 125 tokens 1.03.318.017 I slot print_timing: id 3 | task 150 | graphs reused = 1 1.03.318.017 I slot print_timing: id 3 | task 150 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.318.034 I slot release: id 3 | task 150 | stop processing: n_tokens = 124, truncated = 0 1.03.323.065 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.219 (> 0.100 thold), f_keep = 0.241 1.03.328.146 I slot launch_slot_: id 0 | task 155 | processing task, is_child = 0 1.03.334.754 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.442 MiB) 1.03.338.031 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 1.03.338.084 I slot launch_slot_: id 1 | task 154 | processing task, is_child = 0 1.03.338.120 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.215 (> 0.100 thold), f_keep = 0.226 1.03.338.158 I slot launch_slot_: id 2 | task 156 | processing task, is_child = 0 1.03.338.178 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.226 1.03.338.213 I slot launch_slot_: id 3 | task 157 | processing task, is_child = 0 1.04.499.996 I slot print_timing: id 0 | task 155 | prompt eval time = 1111.73 ms / 128 tokens ( 8.69 ms per token, 115.14 tokens per second) 1.04.499.998 I slot print_timing: id 0 | task 155 | eval time = 50.05 ms / 2 tokens ( 50.05 ms per token, 19.98 tokens per second) 1.04.500.000 I slot print_timing: id 0 | task 155 | total time = 1161.78 ms / 130 tokens 1.04.500.000 I slot print_timing: id 0 | task 155 | graphs reused = 1 1.04.500.000 I slot print_timing: id 0 | task 155 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.500.019 I slot release: id 0 | task 155 | stop processing: n_tokens = 129, truncated = 0 1.04.500.174 I slot print_timing: id 1 | task 154 | prompt eval time = 1111.88 ms / 127 tokens ( 8.75 ms per token, 114.22 tokens per second) 1.04.500.176 I slot print_timing: id 1 | task 154 | eval time = 50.06 ms / 2 tokens ( 50.06 ms per token, 19.97 tokens per second) 1.04.500.177 I slot print_timing: id 1 | task 154 | total time = 1161.94 ms / 129 tokens 1.04.500.177 I slot print_timing: id 1 | task 154 | graphs reused = 1 1.04.500.177 I slot print_timing: id 1 | task 154 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.500.187 I slot release: id 1 | task 154 | stop processing: n_tokens = 128, truncated = 0 1.04.500.355 I slot print_timing: id 2 | task 156 | prompt eval time = 1112.08 ms / 130 tokens ( 8.55 ms per token, 116.90 tokens per second) 1.04.500.357 I slot print_timing: id 2 | task 156 | eval time = 50.03 ms / 2 tokens ( 50.03 ms per token, 19.99 tokens per second) 1.04.500.358 I slot print_timing: id 2 | task 156 | total time = 1162.11 ms / 132 tokens 1.04.500.358 I slot print_timing: id 2 | task 156 | graphs reused = 1 1.04.500.358 I slot print_timing: id 2 | task 156 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.500.368 I slot release: id 2 | task 156 | stop processing: n_tokens = 131, truncated = 0 1.04.500.534 I slot print_timing: id 3 | task 157 | prompt eval time = 1112.27 ms / 141 tokens ( 7.89 ms per token, 126.77 tokens per second) 1.04.500.535 I slot print_timing: id 3 | task 157 | eval time = 50.01 ms / 2 tokens ( 50.01 ms per token, 20.00 tokens per second) 1.04.500.536 I slot print_timing: id 3 | task 157 | total time = 1162.28 ms / 143 tokens 1.04.500.536 I slot print_timing: id 3 | task 157 | graphs reused = 1 1.04.500.536 I slot print_timing: id 3 | task 157 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.500.546 I slot release: id 3 | task 157 | stop processing: n_tokens = 142, truncated = 0 1.04.505.034 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 1.04.505.114 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.186 MiB) 1.04.510.000 I slot launch_slot_: id 0 | task 163 | processing task, is_child = 0 1.04.510.021 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.208 MiB) 1.04.513.495 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.032 MiB) 1.04.516.892 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.462 MiB) 1.04.520.927 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.219 1.04.520.980 I slot launch_slot_: id 1 | task 161 | processing task, is_child = 0 1.04.521.014 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.267 (> 0.100 thold), f_keep = 0.214 1.04.522.461 I slot launch_slot_: id 2 | task 162 | processing task, is_child = 0 1.04.522.481 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.174 (> 0.100 thold), f_keep = 0.197 1.04.522.519 I slot launch_slot_: id 3 | task 164 | processing task, is_child = 0 1.05.873.899 I slot print_timing: id 0 | task 163 | prompt eval time = 1300.90 ms / 129 tokens ( 10.08 ms per token, 99.16 tokens per second) 1.05.873.902 I slot print_timing: id 0 | task 163 | eval time = 50.47 ms / 2 tokens ( 50.47 ms per token, 19.81 tokens per second) 1.05.873.902 I slot print_timing: id 0 | task 163 | total time = 1351.37 ms / 131 tokens 1.05.873.903 I slot print_timing: id 0 | task 163 | graphs reused = 1 1.05.873.903 I slot print_timing: id 0 | task 163 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.873.922 I slot release: id 0 | task 163 | stop processing: n_tokens = 130, truncated = 0 1.05.874.079 I slot print_timing: id 1 | task 161 | prompt eval time = 1301.06 ms / 123 tokens ( 10.58 ms per token, 94.54 tokens per second) 1.05.874.083 I slot print_timing: id 1 | task 161 | eval time = 50.48 ms / 2 tokens ( 50.48 ms per token, 19.81 tokens per second) 1.05.874.084 I slot print_timing: id 1 | task 161 | total time = 1351.54 ms / 125 tokens 1.05.874.084 I slot print_timing: id 1 | task 161 | graphs reused = 1 1.05.874.084 I slot print_timing: id 1 | task 161 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.874.094 I slot release: id 1 | task 161 | stop processing: n_tokens = 124, truncated = 0 1.05.874.273 I slot print_timing: id 2 | task 162 | prompt eval time = 1301.24 ms / 105 tokens ( 12.39 ms per token, 80.69 tokens per second) 1.05.874.277 I slot print_timing: id 2 | task 162 | eval time = 50.48 ms / 2 tokens ( 50.48 ms per token, 19.81 tokens per second) 1.05.874.278 I slot print_timing: id 2 | task 162 | total time = 1351.72 ms / 107 tokens 1.05.874.278 I slot print_timing: id 2 | task 162 | graphs reused = 1 1.05.874.278 I slot print_timing: id 2 | task 162 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.874.287 I slot release: id 2 | task 162 | stop processing: n_tokens = 106, truncated = 0 1.05.874.456 I slot print_timing: id 3 | task 164 | prompt eval time = 1301.45 ms / 161 tokens ( 8.08 ms per token, 123.71 tokens per second) 1.05.874.459 I slot print_timing: id 3 | task 164 | eval time = 50.45 ms / 2 tokens ( 50.45 ms per token, 19.82 tokens per second) 1.05.874.460 I slot print_timing: id 3 | task 164 | total time = 1351.90 ms / 163 tokens 1.05.874.460 I slot print_timing: id 3 | task 164 | graphs reused = 1 1.05.874.460 I slot print_timing: id 3 | task 164 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.874.472 I slot release: id 3 | task 164 | stop processing: n_tokens = 162, truncated = 0 1.05.879.357 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.264 (> 0.100 thold), f_keep = 0.274 1.05.882.903 I slot launch_slot_: id 2 | task 168 | processing task, is_child = 0 1.05.882.925 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.127 MiB) 1.05.887.009 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.993 MiB) 1.05.891.162 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.856 MiB) 1.05.895.210 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 1.05.895.256 I slot launch_slot_: id 0 | task 169 | processing task, is_child = 0 1.05.895.291 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.182 (> 0.100 thold), f_keep = 0.226 1.05.895.325 I slot launch_slot_: id 1 | task 170 | processing task, is_child = 0 1.05.895.345 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.171 (> 0.100 thold), f_keep = 0.173 1.05.895.386 I slot launch_slot_: id 3 | task 171 | processing task, is_child = 0 1.07.350.903 I slot print_timing: id 0 | task 169 | prompt eval time = 1405.13 ms / 141 tokens ( 9.97 ms per token, 100.35 tokens per second) 1.07.350.905 I slot print_timing: id 0 | task 169 | eval time = 50.38 ms / 2 tokens ( 50.38 ms per token, 19.85 tokens per second) 1.07.350.905 I slot print_timing: id 0 | task 169 | total time = 1455.51 ms / 143 tokens 1.07.350.906 I slot print_timing: id 0 | task 169 | graphs reused = 1 1.07.350.906 I slot print_timing: id 0 | task 169 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.350.925 I slot release: id 0 | task 169 | stop processing: n_tokens = 142, truncated = 0 1.07.351.079 I slot print_timing: id 1 | task 170 | prompt eval time = 1405.27 ms / 154 tokens ( 9.13 ms per token, 109.59 tokens per second) 1.07.351.080 I slot print_timing: id 1 | task 170 | eval time = 50.40 ms / 2 tokens ( 50.40 ms per token, 19.84 tokens per second) 1.07.351.081 I slot print_timing: id 1 | task 170 | total time = 1455.67 ms / 156 tokens 1.07.351.081 I slot print_timing: id 1 | task 170 | graphs reused = 1 1.07.351.081 I slot print_timing: id 1 | task 170 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.351.095 I slot release: id 1 | task 170 | stop processing: n_tokens = 155, truncated = 0 1.07.351.260 I slot print_timing: id 2 | task 168 | prompt eval time = 1405.46 ms / 110 tokens ( 12.78 ms per token, 78.27 tokens per second) 1.07.351.261 I slot print_timing: id 2 | task 168 | eval time = 50.38 ms / 2 tokens ( 50.38 ms per token, 19.85 tokens per second) 1.07.351.262 I slot print_timing: id 2 | task 168 | total time = 1455.84 ms / 112 tokens 1.07.351.262 I slot print_timing: id 2 | task 168 | graphs reused = 1 1.07.351.262 I slot print_timing: id 2 | task 168 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.351.270 I slot release: id 2 | task 168 | stop processing: n_tokens = 111, truncated = 0 1.07.351.435 I slot print_timing: id 3 | task 171 | prompt eval time = 1405.66 ms / 164 tokens ( 8.57 ms per token, 116.67 tokens per second) 1.07.351.439 I slot print_timing: id 3 | task 171 | eval time = 50.34 ms / 2 tokens ( 50.34 ms per token, 19.86 tokens per second) 1.07.351.440 I slot print_timing: id 3 | task 171 | total time = 1456.00 ms / 166 tokens 1.07.351.440 I slot print_timing: id 3 | task 171 | graphs reused = 1 1.07.351.440 I slot print_timing: id 3 | task 171 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.351.451 I slot release: id 3 | task 171 | stop processing: n_tokens = 165, truncated = 0 1.07.356.350 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 1.07.356.378 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.423 MiB) 1.07.360.613 I slot launch_slot_: id 2 | task 175 | processing task, is_child = 0 1.07.360.634 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.462 MiB) 1.07.365.597 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.442 MiB) 1.07.377.973 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.051 MiB) 1.07.390.849 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.204 (> 0.100 thold), f_keep = 0.197 1.07.390.920 I slot launch_slot_: id 0 | task 177 | processing task, is_child = 0 1.07.390.957 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.255 (> 0.100 thold), f_keep = 0.181 1.07.390.992 I slot launch_slot_: id 1 | task 176 | processing task, is_child = 0 1.07.391.014 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.189 (> 0.100 thold), f_keep = 0.170 1.07.391.049 I slot launch_slot_: id 3 | task 178 | processing task, is_child = 0 1.08.661.811 I slot print_timing: id 0 | task 177 | prompt eval time = 1220.31 ms / 137 tokens ( 8.91 ms per token, 112.27 tokens per second) 1.08.661.814 I slot print_timing: id 0 | task 177 | eval time = 50.45 ms / 2 tokens ( 50.45 ms per token, 19.82 tokens per second) 1.08.661.815 I slot print_timing: id 0 | task 177 | total time = 1270.75 ms / 139 tokens 1.08.661.815 I slot print_timing: id 0 | task 177 | graphs reused = 1 1.08.661.816 I slot print_timing: id 0 | task 177 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.661.840 I slot release: id 0 | task 177 | stop processing: n_tokens = 138, truncated = 0 1.08.661.994 I slot print_timing: id 1 | task 176 | prompt eval time = 1220.49 ms / 110 tokens ( 11.10 ms per token, 90.13 tokens per second) 1.08.661.996 I slot print_timing: id 1 | task 176 | eval time = 50.43 ms / 2 tokens ( 50.43 ms per token, 19.83 tokens per second) 1.08.661.997 I slot print_timing: id 1 | task 176 | total time = 1270.92 ms / 112 tokens 1.08.661.997 I slot print_timing: id 1 | task 176 | graphs reused = 1 1.08.661.998 I slot print_timing: id 1 | task 176 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.662.007 I slot release: id 1 | task 176 | stop processing: n_tokens = 111, truncated = 0 1.08.662.178 I slot print_timing: id 2 | task 175 | prompt eval time = 1220.69 ms / 110 tokens ( 11.10 ms per token, 90.11 tokens per second) 1.08.662.185 I slot print_timing: id 2 | task 175 | eval time = 50.41 ms / 2 tokens ( 50.41 ms per token, 19.84 tokens per second) 1.08.662.185 I slot print_timing: id 2 | task 175 | total time = 1271.10 ms / 112 tokens 1.08.662.186 I slot print_timing: id 2 | task 175 | graphs reused = 1 1.08.662.186 I slot print_timing: id 2 | task 175 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.662.194 I slot release: id 2 | task 175 | stop processing: n_tokens = 111, truncated = 0 1.08.662.375 I slot print_timing: id 3 | task 178 | prompt eval time = 1220.90 ms / 148 tokens ( 8.25 ms per token, 121.22 tokens per second) 1.08.662.379 I slot print_timing: id 3 | task 178 | eval time = 50.38 ms / 2 tokens ( 50.38 ms per token, 19.85 tokens per second) 1.08.662.379 I slot print_timing: id 3 | task 178 | total time = 1271.28 ms / 150 tokens 1.08.662.380 I slot print_timing: id 3 | task 178 | graphs reused = 1 1.08.662.380 I slot print_timing: id 3 | task 178 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.662.388 I slot release: id 3 | task 178 | stop processing: n_tokens = 149, truncated = 0 1.08.666.841 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.203 1.08.666.868 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.641 MiB) 1.08.670.394 I slot launch_slot_: id 0 | task 182 | processing task, is_child = 0 1.08.670.417 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.169 MiB) 1.08.674.460 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.306 MiB) 1.08.678.511 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.107 MiB) 1.08.682.509 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.184 (> 0.100 thold), f_keep = 0.252 1.08.682.565 I slot launch_slot_: id 1 | task 184 | processing task, is_child = 0 1.08.682.605 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.259 (> 0.100 thold), f_keep = 0.261 1.08.682.641 I slot launch_slot_: id 2 | task 183 | processing task, is_child = 0 1.08.682.661 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.215 (> 0.100 thold), f_keep = 0.188 1.08.682.711 I slot launch_slot_: id 3 | task 185 | processing task, is_child = 0 1.10.023.167 I slot print_timing: id 0 | task 182 | prompt eval time = 1290.01 ms / 123 tokens ( 10.49 ms per token, 95.35 tokens per second) 1.10.023.169 I slot print_timing: id 0 | task 182 | eval time = 50.44 ms / 2 tokens ( 50.44 ms per token, 19.83 tokens per second) 1.10.023.169 I slot print_timing: id 0 | task 182 | total time = 1340.45 ms / 125 tokens 1.10.023.170 I slot print_timing: id 0 | task 182 | graphs reused = 1 1.10.023.170 I slot print_timing: id 0 | task 182 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.023.193 I slot release: id 0 | task 182 | stop processing: n_tokens = 124, truncated = 0 1.10.023.348 I slot print_timing: id 1 | task 184 | prompt eval time = 1290.18 ms / 152 tokens ( 8.49 ms per token, 117.81 tokens per second) 1.10.023.350 I slot print_timing: id 1 | task 184 | eval time = 50.43 ms / 2 tokens ( 50.43 ms per token, 19.83 tokens per second) 1.10.023.351 I slot print_timing: id 1 | task 184 | total time = 1340.61 ms / 154 tokens 1.10.023.351 I slot print_timing: id 1 | task 184 | graphs reused = 1 1.10.023.351 I slot print_timing: id 1 | task 184 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.023.369 I slot release: id 1 | task 184 | stop processing: n_tokens = 153, truncated = 0 1.10.023.532 I slot print_timing: id 2 | task 183 | prompt eval time = 1290.36 ms / 112 tokens ( 11.52 ms per token, 86.80 tokens per second) 1.10.023.538 I slot print_timing: id 2 | task 183 | eval time = 50.42 ms / 2 tokens ( 50.42 ms per token, 19.83 tokens per second) 1.10.023.538 I slot print_timing: id 2 | task 183 | total time = 1340.78 ms / 114 tokens 1.10.023.538 I slot print_timing: id 2 | task 183 | graphs reused = 1 1.10.023.539 I slot print_timing: id 2 | task 183 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.023.547 I slot release: id 2 | task 183 | stop processing: n_tokens = 113, truncated = 0 1.10.023.710 I slot print_timing: id 3 | task 185 | prompt eval time = 1290.57 ms / 130 tokens ( 9.93 ms per token, 100.73 tokens per second) 1.10.023.712 I slot print_timing: id 3 | task 185 | eval time = 50.38 ms / 2 tokens ( 50.38 ms per token, 19.85 tokens per second) 1.10.023.712 I slot print_timing: id 3 | task 185 | total time = 1340.95 ms / 132 tokens 1.10.023.712 I slot print_timing: id 3 | task 185 | graphs reused = 1 1.10.023.712 I slot print_timing: id 3 | task 185 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.023.723 I slot release: id 3 | task 185 | stop processing: n_tokens = 131, truncated = 0 1.10.028.998 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.227 (> 0.100 thold), f_keep = 0.221 1.10.029.078 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.205 MiB) 1.10.033.373 I slot launch_slot_: id 3 | task 190 | processing task, is_child = 0 1.10.033.396 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.227 MiB) 1.10.037.505 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.892 MiB) 1.10.042.576 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.051 MiB) 1.10.045.999 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.254 (> 0.100 thold), f_keep = 0.257 1.10.046.043 I slot launch_slot_: id 2 | task 189 | processing task, is_child = 0 1.10.046.078 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.178 (> 0.100 thold), f_keep = 0.226 1.10.046.112 I slot launch_slot_: id 0 | task 191 | processing task, is_child = 0 1.10.046.131 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.169 (> 0.100 thold), f_keep = 0.183 1.10.046.166 I slot launch_slot_: id 1 | task 192 | processing task, is_child = 0 1.11.408.534 I slot print_timing: id 0 | task 191 | prompt eval time = 1311.83 ms / 157 tokens ( 8.36 ms per token, 119.68 tokens per second) 1.11.408.536 I slot print_timing: id 0 | task 191 | eval time = 50.53 ms / 2 tokens ( 50.53 ms per token, 19.79 tokens per second) 1.11.408.537 I slot print_timing: id 0 | task 191 | total time = 1362.36 ms / 159 tokens 1.11.408.537 I slot print_timing: id 0 | task 191 | graphs reused = 1 1.11.408.537 I slot print_timing: id 0 | task 191 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.408.557 I slot release: id 0 | task 191 | stop processing: n_tokens = 158, truncated = 0 1.11.408.714 I slot print_timing: id 1 | task 192 | prompt eval time = 1311.99 ms / 166 tokens ( 7.90 ms per token, 126.53 tokens per second) 1.11.408.719 I slot print_timing: id 1 | task 192 | eval time = 50.54 ms / 2 tokens ( 50.54 ms per token, 19.79 tokens per second) 1.11.408.719 I slot print_timing: id 1 | task 192 | total time = 1362.53 ms / 168 tokens 1.11.408.719 I slot print_timing: id 1 | task 192 | graphs reused = 1 1.11.408.720 I slot print_timing: id 1 | task 192 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.408.738 I slot release: id 1 | task 192 | stop processing: n_tokens = 167, truncated = 0 1.11.408.902 I slot print_timing: id 2 | task 189 | prompt eval time = 1312.18 ms / 114 tokens ( 11.51 ms per token, 86.88 tokens per second) 1.11.408.904 I slot print_timing: id 2 | task 189 | eval time = 50.52 ms / 2 tokens ( 50.52 ms per token, 19.79 tokens per second) 1.11.408.904 I slot print_timing: id 2 | task 189 | total time = 1362.70 ms / 116 tokens 1.11.408.904 I slot print_timing: id 2 | task 189 | graphs reused = 1 1.11.408.905 I slot print_timing: id 2 | task 189 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.408.916 I slot release: id 2 | task 189 | stop processing: n_tokens = 115, truncated = 0 1.11.409.095 I slot print_timing: id 3 | task 190 | prompt eval time = 1312.39 ms / 128 tokens ( 10.25 ms per token, 97.53 tokens per second) 1.11.409.098 I slot print_timing: id 3 | task 190 | eval time = 50.50 ms / 2 tokens ( 50.50 ms per token, 19.80 tokens per second) 1.11.409.098 I slot print_timing: id 3 | task 190 | total time = 1362.88 ms / 130 tokens 1.11.409.098 I slot print_timing: id 3 | task 190 | graphs reused = 1 1.11.409.099 I slot print_timing: id 3 | task 190 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.409.110 I slot release: id 3 | task 190 | stop processing: n_tokens = 129, truncated = 0 1.11.414.092 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.177 1.11.414.128 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.560 MiB) 1.11.419.153 I slot launch_slot_: id 0 | task 196 | processing task, is_child = 0 1.11.430.684 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.384 MiB) 1.11.434.623 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.951 MiB) 1.11.438.663 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.259 (> 0.100 thold), f_keep = 0.168 1.11.438.726 I slot launch_slot_: id 1 | task 197 | processing task, is_child = 0 1.11.438.766 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.183 (> 0.100 thold), f_keep = 0.243 1.11.438.806 I slot launch_slot_: id 2 | task 198 | processing task, is_child = 0 1.11.438.830 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.156 (> 0.100 thold), f_keep = 0.217 1.11.438.876 I slot launch_slot_: id 3 | task 199 | processing task, is_child = 0 1.12.963.560 I slot print_timing: id 0 | task 196 | prompt eval time = 1474.04 ms / 141 tokens ( 10.45 ms per token, 95.66 tokens per second) 1.12.963.563 I slot print_timing: id 0 | task 196 | eval time = 50.63 ms / 2 tokens ( 50.63 ms per token, 19.75 tokens per second) 1.12.963.564 I slot print_timing: id 0 | task 196 | total time = 1524.67 ms / 143 tokens 1.12.963.564 I slot print_timing: id 0 | task 196 | graphs reused = 1 1.12.963.564 I slot print_timing: id 0 | task 196 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.963.583 I slot release: id 0 | task 196 | stop processing: n_tokens = 142, truncated = 0 1.12.963.743 I slot print_timing: id 1 | task 197 | prompt eval time = 1474.22 ms / 108 tokens ( 13.65 ms per token, 73.26 tokens per second) 1.12.963.745 I slot print_timing: id 1 | task 197 | eval time = 50.62 ms / 2 tokens ( 50.62 ms per token, 19.75 tokens per second) 1.12.963.745 I slot print_timing: id 1 | task 197 | total time = 1524.84 ms / 110 tokens 1.12.963.746 I slot print_timing: id 1 | task 197 | graphs reused = 1 1.12.963.746 I slot print_timing: id 1 | task 197 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.963.757 I slot release: id 1 | task 197 | stop processing: n_tokens = 109, truncated = 0 1.12.963.929 I slot print_timing: id 2 | task 198 | prompt eval time = 1474.41 ms / 153 tokens ( 9.64 ms per token, 103.77 tokens per second) 1.12.963.932 I slot print_timing: id 2 | task 198 | eval time = 50.61 ms / 2 tokens ( 50.61 ms per token, 19.76 tokens per second) 1.12.963.933 I slot print_timing: id 2 | task 198 | total time = 1525.01 ms / 155 tokens 1.12.963.933 I slot print_timing: id 2 | task 198 | graphs reused = 1 1.12.963.933 I slot print_timing: id 2 | task 198 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.963.952 I slot release: id 2 | task 198 | stop processing: n_tokens = 154, truncated = 0 1.12.964.118 I slot print_timing: id 3 | task 199 | prompt eval time = 1474.60 ms / 179 tokens ( 8.24 ms per token, 121.39 tokens per second) 1.12.964.120 I slot print_timing: id 3 | task 199 | eval time = 50.59 ms / 2 tokens ( 50.59 ms per token, 19.77 tokens per second) 1.12.964.120 I slot print_timing: id 3 | task 199 | total time = 1525.19 ms / 181 tokens 1.12.964.120 I slot print_timing: id 3 | task 199 | graphs reused = 1 1.12.964.121 I slot print_timing: id 3 | task 199 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.964.132 I slot release: id 3 | task 199 | stop processing: n_tokens = 180, truncated = 0 1.12.968.997 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.241 (> 0.100 thold), f_keep = 0.197 1.12.969.022 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.834 MiB) 1.12.974.403 I slot launch_slot_: id 0 | task 203 | processing task, is_child = 0 1.12.977.698 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.149 MiB) 1.12.981.584 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.794 MiB) 1.12.995.960 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.209 (> 0.100 thold), f_keep = 0.257 1.12.996.017 I slot launch_slot_: id 1 | task 204 | processing task, is_child = 0 1.12.996.055 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.177 (> 0.100 thold), f_keep = 0.182 1.12.996.092 I slot launch_slot_: id 2 | task 205 | processing task, is_child = 0 1.12.996.114 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.207 (> 0.100 thold), f_keep = 0.156 1.12.996.158 I slot launch_slot_: id 3 | task 206 | processing task, is_child = 0 1.14.313.399 I slot print_timing: id 0 | task 203 | prompt eval time = 1266.78 ms / 116 tokens ( 10.92 ms per token, 91.57 tokens per second) 1.14.313.401 I slot print_timing: id 0 | task 203 | eval time = 50.45 ms / 2 tokens ( 50.45 ms per token, 19.82 tokens per second) 1.14.313.401 I slot print_timing: id 0 | task 203 | total time = 1317.23 ms / 118 tokens 1.14.313.402 I slot print_timing: id 0 | task 203 | graphs reused = 1 1.14.313.402 I slot print_timing: id 0 | task 203 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.313.420 I slot release: id 0 | task 203 | stop processing: n_tokens = 117, truncated = 0 1.14.313.571 I slot print_timing: id 1 | task 204 | prompt eval time = 1266.92 ms / 134 tokens ( 9.45 ms per token, 105.77 tokens per second) 1.14.313.573 I slot print_timing: id 1 | task 204 | eval time = 50.47 ms / 2 tokens ( 50.47 ms per token, 19.81 tokens per second) 1.14.313.573 I slot print_timing: id 1 | task 204 | total time = 1317.39 ms / 136 tokens 1.14.313.574 I slot print_timing: id 1 | task 204 | graphs reused = 1 1.14.313.574 I slot print_timing: id 1 | task 204 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.313.590 I slot release: id 1 | task 204 | stop processing: n_tokens = 135, truncated = 0 1.14.313.755 I slot print_timing: id 2 | task 205 | prompt eval time = 1267.10 ms / 158 tokens ( 8.02 ms per token, 124.69 tokens per second) 1.14.313.756 I slot print_timing: id 2 | task 205 | eval time = 50.46 ms / 2 tokens ( 50.46 ms per token, 19.82 tokens per second) 1.14.313.757 I slot print_timing: id 2 | task 205 | total time = 1317.56 ms / 160 tokens 1.14.313.757 I slot print_timing: id 2 | task 205 | graphs reused = 1 1.14.313.758 I slot print_timing: id 2 | task 205 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.313.771 I slot release: id 2 | task 205 | stop processing: n_tokens = 159, truncated = 0 1.14.313.951 I slot print_timing: id 3 | task 206 | prompt eval time = 1267.29 ms / 135 tokens ( 9.39 ms per token, 106.53 tokens per second) 1.14.313.952 I slot print_timing: id 3 | task 206 | eval time = 50.46 ms / 2 tokens ( 50.46 ms per token, 19.82 tokens per second) 1.14.313.953 I slot print_timing: id 3 | task 206 | total time = 1317.74 ms / 137 tokens 1.14.313.953 I slot print_timing: id 3 | task 206 | graphs reused = 1 1.14.313.953 I slot print_timing: id 3 | task 206 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.313.963 I slot release: id 3 | task 206 | stop processing: n_tokens = 136, truncated = 0 1.14.318.978 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 1.14.319.006 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.912 MiB) 1.14.324.687 I slot launch_slot_: id 0 | task 210 | processing task, is_child = 0 1.14.328.083 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.853 MiB) 1.14.332.273 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.032 MiB) 1.14.338.114 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 1.14.339.571 I slot launch_slot_: id 1 | task 211 | processing task, is_child = 0 1.14.339.613 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.176 1.14.339.648 I slot launch_slot_: id 2 | task 212 | processing task, is_child = 0 1.14.339.670 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.178 (> 0.100 thold), f_keep = 0.206 1.14.339.704 I slot launch_slot_: id 3 | task 213 | processing task, is_child = 0 1.15.631.877 I slot print_timing: id 0 | task 210 | prompt eval time = 1241.79 ms / 122 tokens ( 10.18 ms per token, 98.25 tokens per second) 1.15.631.879 I slot print_timing: id 0 | task 210 | eval time = 50.37 ms / 2 tokens ( 50.37 ms per token, 19.85 tokens per second) 1.15.631.879 I slot print_timing: id 0 | task 210 | total time = 1292.16 ms / 124 tokens 1.15.631.880 I slot print_timing: id 0 | task 210 | graphs reused = 1 1.15.631.880 I slot print_timing: id 0 | task 210 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.631.902 I slot release: id 0 | task 210 | stop processing: n_tokens = 123, truncated = 0 1.15.632.055 I slot print_timing: id 1 | task 211 | prompt eval time = 1241.94 ms / 117 tokens ( 10.61 ms per token, 94.21 tokens per second) 1.15.632.058 I slot print_timing: id 1 | task 211 | eval time = 50.39 ms / 2 tokens ( 50.39 ms per token, 19.84 tokens per second) 1.15.632.059 I slot print_timing: id 1 | task 211 | total time = 1292.33 ms / 119 tokens 1.15.632.059 I slot print_timing: id 1 | task 211 | graphs reused = 1 1.15.632.059 I slot print_timing: id 1 | task 211 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.632.068 I slot release: id 1 | task 211 | stop processing: n_tokens = 118, truncated = 0 1.15.632.237 I slot print_timing: id 2 | task 212 | prompt eval time = 1242.13 ms / 149 tokens ( 8.34 ms per token, 119.95 tokens per second) 1.15.632.240 I slot print_timing: id 2 | task 212 | eval time = 50.37 ms / 2 tokens ( 50.37 ms per token, 19.85 tokens per second) 1.15.632.241 I slot print_timing: id 2 | task 212 | total time = 1292.50 ms / 151 tokens 1.15.632.241 I slot print_timing: id 2 | task 212 | graphs reused = 1 1.15.632.242 I slot print_timing: id 2 | task 212 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.632.252 I slot release: id 2 | task 212 | stop processing: n_tokens = 150, truncated = 0 1.15.632.433 I slot print_timing: id 3 | task 213 | prompt eval time = 1242.34 ms / 157 tokens ( 7.91 ms per token, 126.37 tokens per second) 1.15.632.435 I slot print_timing: id 3 | task 213 | eval time = 50.35 ms / 2 tokens ( 50.35 ms per token, 19.86 tokens per second) 1.15.632.436 I slot print_timing: id 3 | task 213 | total time = 1292.69 ms / 159 tokens 1.15.632.436 I slot print_timing: id 3 | task 213 | graphs reused = 1 1.15.632.436 I slot print_timing: id 3 | task 213 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.632.445 I slot release: id 3 | task 213 | stop processing: n_tokens = 158, truncated = 0 1.15.637.258 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.228 1.15.640.856 I slot launch_slot_: id 0 | task 217 | processing task, is_child = 0 1.15.640.879 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.521 MiB) 1.15.646.809 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.208 MiB) 1.15.652.728 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.993 MiB) 1.15.658.920 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.237 1.15.658.971 I slot launch_slot_: id 1 | task 218 | processing task, is_child = 0 1.15.659.009 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.181 (> 0.100 thold), f_keep = 0.187 1.15.659.063 I slot launch_slot_: id 2 | task 219 | processing task, is_child = 0 1.15.659.085 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.182 (> 0.100 thold), f_keep = 0.177 1.15.659.130 I slot launch_slot_: id 3 | task 220 | processing task, is_child = 0 1.17.111.552 I slot print_timing: id 0 | task 217 | prompt eval time = 1402.04 ms / 149 tokens ( 9.41 ms per token, 106.27 tokens per second) 1.17.111.556 I slot print_timing: id 0 | task 217 | eval time = 50.38 ms / 2 tokens ( 50.38 ms per token, 19.85 tokens per second) 1.17.111.556 I slot print_timing: id 0 | task 217 | total time = 1452.41 ms / 151 tokens 1.17.111.557 I slot print_timing: id 0 | task 217 | graphs reused = 1 1.17.111.557 I slot print_timing: id 0 | task 217 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.111.580 I slot release: id 0 | task 217 | stop processing: n_tokens = 150, truncated = 0 1.17.111.735 I slot print_timing: id 1 | task 218 | prompt eval time = 1402.20 ms / 160 tokens ( 8.76 ms per token, 114.11 tokens per second) 1.17.111.738 I slot print_timing: id 1 | task 218 | eval time = 50.38 ms / 2 tokens ( 50.38 ms per token, 19.85 tokens per second) 1.17.111.738 I slot print_timing: id 1 | task 218 | total time = 1452.58 ms / 162 tokens 1.17.111.738 I slot print_timing: id 1 | task 218 | graphs reused = 1 1.17.111.739 I slot print_timing: id 1 | task 218 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.111.753 I slot release: id 1 | task 218 | stop processing: n_tokens = 161, truncated = 0 1.17.111.915 I slot print_timing: id 2 | task 219 | prompt eval time = 1402.40 ms / 155 tokens ( 9.05 ms per token, 110.52 tokens per second) 1.17.111.917 I slot print_timing: id 2 | task 219 | eval time = 50.35 ms / 2 tokens ( 50.35 ms per token, 19.86 tokens per second) 1.17.111.917 I slot print_timing: id 2 | task 219 | total time = 1452.75 ms / 157 tokens 1.17.111.918 I slot print_timing: id 2 | task 219 | graphs reused = 1 1.17.111.918 I slot print_timing: id 2 | task 219 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.111.936 I slot release: id 2 | task 219 | stop processing: n_tokens = 156, truncated = 0 1.17.112.097 I slot print_timing: id 3 | task 220 | prompt eval time = 1402.59 ms / 154 tokens ( 9.11 ms per token, 109.80 tokens per second) 1.17.112.100 I slot print_timing: id 3 | task 220 | eval time = 50.33 ms / 2 tokens ( 50.33 ms per token, 19.87 tokens per second) 1.17.112.101 I slot print_timing: id 3 | task 220 | total time = 1452.92 ms / 156 tokens 1.17.112.101 I slot print_timing: id 3 | task 220 | graphs reused = 1 1.17.112.101 I slot print_timing: id 3 | task 220 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.112.110 I slot release: id 3 | task 220 | stop processing: n_tokens = 155, truncated = 0 1.17.117.093 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.275 (> 0.100 thold), f_keep = 0.187 1.17.117.121 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.208 MiB) 1.17.121.851 I slot launch_slot_: id 0 | task 224 | processing task, is_child = 0 1.17.125.279 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.071 MiB) 1.17.137.347 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.462 MiB) 1.17.149.009 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.262 (> 0.100 thold), f_keep = 0.174 1.17.149.074 I slot launch_slot_: id 1 | task 225 | processing task, is_child = 0 1.17.149.112 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.246 (> 0.100 thold), f_keep = 0.179 1.17.149.148 I slot launch_slot_: id 2 | task 226 | processing task, is_child = 0 1.17.149.169 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.151 (> 0.100 thold), f_keep = 0.181 1.17.149.214 I slot launch_slot_: id 3 | task 227 | processing task, is_child = 0 1.18.471.792 I slot print_timing: id 0 | task 224 | prompt eval time = 1272.23 ms / 102 tokens ( 12.47 ms per token, 80.17 tokens per second) 1.18.471.794 I slot print_timing: id 0 | task 224 | eval time = 50.34 ms / 2 tokens ( 50.34 ms per token, 19.87 tokens per second) 1.18.471.795 I slot print_timing: id 0 | task 224 | total time = 1322.57 ms / 104 tokens 1.18.471.795 I slot print_timing: id 0 | task 224 | graphs reused = 1 1.18.471.796 I slot print_timing: id 0 | task 224 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.471.813 I slot release: id 0 | task 224 | stop processing: n_tokens = 103, truncated = 0 1.18.471.970 I slot print_timing: id 1 | task 225 | prompt eval time = 1272.38 ms / 107 tokens ( 11.89 ms per token, 84.09 tokens per second) 1.18.471.972 I slot print_timing: id 1 | task 225 | eval time = 50.36 ms / 2 tokens ( 50.36 ms per token, 19.86 tokens per second) 1.18.471.972 I slot print_timing: id 1 | task 225 | total time = 1322.73 ms / 109 tokens 1.18.471.972 I slot print_timing: id 1 | task 225 | graphs reused = 1 1.18.471.973 I slot print_timing: id 1 | task 225 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.471.987 I slot release: id 1 | task 225 | stop processing: n_tokens = 108, truncated = 0 1.18.472.153 I slot print_timing: id 2 | task 226 | prompt eval time = 1272.54 ms / 114 tokens ( 11.16 ms per token, 89.58 tokens per second) 1.18.472.155 I slot print_timing: id 2 | task 226 | eval time = 50.36 ms / 2 tokens ( 50.36 ms per token, 19.86 tokens per second) 1.18.472.155 I slot print_timing: id 2 | task 226 | total time = 1322.90 ms / 116 tokens 1.18.472.156 I slot print_timing: id 2 | task 226 | graphs reused = 1 1.18.472.156 I slot print_timing: id 2 | task 226 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.472.164 I slot release: id 2 | task 226 | stop processing: n_tokens = 115, truncated = 0 1.18.472.347 I slot print_timing: id 3 | task 227 | prompt eval time = 1272.74 ms / 185 tokens ( 6.88 ms per token, 145.36 tokens per second) 1.18.472.349 I slot print_timing: id 3 | task 227 | eval time = 50.34 ms / 2 tokens ( 50.34 ms per token, 19.86 tokens per second) 1.18.472.349 I slot print_timing: id 3 | task 227 | total time = 1323.08 ms / 187 tokens 1.18.472.350 I slot print_timing: id 3 | task 227 | graphs reused = 1 1.18.472.350 I slot print_timing: id 3 | task 227 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.472.360 I slot release: id 3 | task 227 | stop processing: n_tokens = 186, truncated = 0 1.18.477.177 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.264 (> 0.100 thold), f_keep = 0.282 1.18.477.201 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.403 MiB) 1.18.483.012 I slot launch_slot_: id 0 | task 231 | processing task, is_child = 0 1.18.483.033 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.954 MiB) 1.18.490.591 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.012 MiB) 1.18.494.079 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.010 MiB) 1.18.509.529 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.259 1.18.509.589 I slot launch_slot_: id 1 | task 232 | processing task, is_child = 0 1.18.509.629 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.222 (> 0.100 thold), f_keep = 0.243 1.18.509.670 I slot launch_slot_: id 2 | task 233 | processing task, is_child = 0 1.18.509.692 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 1.18.509.740 I slot launch_slot_: id 3 | task 234 | processing task, is_child = 0 1.19.895.662 I slot print_timing: id 0 | task 231 | prompt eval time = 1335.34 ms / 110 tokens ( 12.14 ms per token, 82.38 tokens per second) 1.19.895.664 I slot print_timing: id 0 | task 231 | eval time = 50.57 ms / 2 tokens ( 50.57 ms per token, 19.77 tokens per second) 1.19.895.665 I slot print_timing: id 0 | task 231 | total time = 1385.91 ms / 112 tokens 1.19.895.665 I slot print_timing: id 0 | task 231 | graphs reused = 1 1.19.895.666 I slot print_timing: id 0 | task 231 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.895.684 I slot release: id 0 | task 231 | stop processing: n_tokens = 111, truncated = 0 1.19.895.837 I slot print_timing: id 1 | task 232 | prompt eval time = 1335.51 ms / 122 tokens ( 10.95 ms per token, 91.35 tokens per second) 1.19.895.841 I slot print_timing: id 1 | task 232 | eval time = 50.57 ms / 2 tokens ( 50.57 ms per token, 19.77 tokens per second) 1.19.895.842 I slot print_timing: id 1 | task 232 | total time = 1386.08 ms / 124 tokens 1.19.895.843 I slot print_timing: id 1 | task 232 | graphs reused = 1 1.19.895.843 I slot print_timing: id 1 | task 232 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.895.856 I slot release: id 1 | task 232 | stop processing: n_tokens = 123, truncated = 0 1.19.896.028 I slot print_timing: id 2 | task 233 | prompt eval time = 1335.70 ms / 126 tokens ( 10.60 ms per token, 94.33 tokens per second) 1.19.896.029 I slot print_timing: id 2 | task 233 | eval time = 50.55 ms / 2 tokens ( 50.55 ms per token, 19.78 tokens per second) 1.19.896.030 I slot print_timing: id 2 | task 233 | total time = 1386.25 ms / 128 tokens 1.19.896.030 I slot print_timing: id 2 | task 233 | graphs reused = 1 1.19.896.030 I slot print_timing: id 2 | task 233 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.896.041 I slot release: id 2 | task 233 | stop processing: n_tokens = 127, truncated = 0 1.19.896.207 I slot print_timing: id 3 | task 234 | prompt eval time = 1335.90 ms / 164 tokens ( 8.15 ms per token, 122.76 tokens per second) 1.19.896.210 I slot print_timing: id 3 | task 234 | eval time = 50.52 ms / 2 tokens ( 50.52 ms per token, 19.80 tokens per second) 1.19.896.210 I slot print_timing: id 3 | task 234 | total time = 1386.42 ms / 166 tokens 1.19.896.211 I slot print_timing: id 3 | task 234 | graphs reused = 1 1.19.896.211 I slot print_timing: id 3 | task 234 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.896.220 I slot release: id 3 | task 234 | stop processing: n_tokens = 165, truncated = 0 1.19.900.926 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.224 (> 0.100 thold), f_keep = 0.252 1.19.900.950 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 130.339 MiB) 1.19.908.433 I slot launch_slot_: id 0 | task 238 | processing task, is_child = 0 1.19.908.454 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.306 MiB) 1.19.913.978 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.107 MiB) 1.19.919.716 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.423 MiB) 1.19.924.980 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.228 1.19.925.024 I slot launch_slot_: id 1 | task 239 | processing task, is_child = 0 1.19.925.061 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.204 (> 0.100 thold), f_keep = 0.220 1.19.926.517 I slot launch_slot_: id 2 | task 240 | processing task, is_child = 0 1.19.926.540 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.203 (> 0.100 thold), f_keep = 0.170 1.19.927.967 I slot launch_slot_: id 3 | task 241 | processing task, is_child = 0 1.21.134.606 I slot print_timing: id 0 | task 238 | prompt eval time = 1156.13 ms / 125 tokens ( 9.25 ms per token, 108.12 tokens per second) 1.21.134.608 I slot print_timing: id 0 | task 238 | eval time = 50.50 ms / 2 tokens ( 50.50 ms per token, 19.80 tokens per second) 1.21.134.609 I slot print_timing: id 0 | task 238 | total time = 1206.63 ms / 127 tokens 1.21.134.610 I slot print_timing: id 0 | task 238 | graphs reused = 1 1.21.134.610 I slot print_timing: id 0 | task 238 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.134.629 I slot release: id 0 | task 238 | stop processing: n_tokens = 126, truncated = 0 1.21.134.785 I slot print_timing: id 1 | task 239 | prompt eval time = 1156.29 ms / 122 tokens ( 9.48 ms per token, 105.51 tokens per second) 1.21.134.787 I slot print_timing: id 1 | task 239 | eval time = 50.50 ms / 2 tokens ( 50.50 ms per token, 19.80 tokens per second) 1.21.134.788 I slot print_timing: id 1 | task 239 | total time = 1206.80 ms / 124 tokens 1.21.134.788 I slot print_timing: id 1 | task 239 | graphs reused = 1 1.21.134.789 I slot print_timing: id 1 | task 239 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.134.799 I slot release: id 1 | task 239 | stop processing: n_tokens = 123, truncated = 0 1.21.134.970 I slot print_timing: id 2 | task 240 | prompt eval time = 1156.48 ms / 137 tokens ( 8.44 ms per token, 118.46 tokens per second) 1.21.134.972 I slot print_timing: id 2 | task 240 | eval time = 50.49 ms / 2 tokens ( 50.49 ms per token, 19.81 tokens per second) 1.21.134.972 I slot print_timing: id 2 | task 240 | total time = 1206.97 ms / 139 tokens 1.21.134.972 I slot print_timing: id 2 | task 240 | graphs reused = 1 1.21.134.973 I slot print_timing: id 2 | task 240 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.134.987 I slot release: id 2 | task 240 | stop processing: n_tokens = 138, truncated = 0 1.21.135.146 I slot print_timing: id 3 | task 241 | prompt eval time = 1156.68 ms / 138 tokens ( 8.38 ms per token, 119.31 tokens per second) 1.21.135.149 I slot print_timing: id 3 | task 241 | eval time = 50.45 ms / 2 tokens ( 50.45 ms per token, 19.82 tokens per second) 1.21.135.149 I slot print_timing: id 3 | task 241 | total time = 1207.14 ms / 140 tokens 1.21.135.149 I slot print_timing: id 3 | task 241 | graphs reused = 1 1.21.135.150 I slot print_timing: id 3 | task 241 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.135.159 I slot release: id 3 | task 241 | stop processing: n_tokens = 139, truncated = 0 1.21.140.180 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.233 (> 0.100 thold), f_keep = 0.222 1.21.145.518 I slot launch_slot_: id 0 | task 245 | processing task, is_child = 0 1.21.149.107 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.775 MiB) 1.21.154.522 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.677 MiB) 1.21.160.602 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.200 (> 0.100 thold), f_keep = 0.228 1.21.160.650 I slot launch_slot_: id 1 | task 247 | processing task, is_child = 0 1.21.160.683 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.177 (> 0.100 thold), f_keep = 0.203 1.21.162.113 I slot launch_slot_: id 2 | task 246 | processing task, is_child = 0 1.21.162.133 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.167 (> 0.100 thold), f_keep = 0.201 1.21.162.168 I slot launch_slot_: id 3 | task 248 | processing task, is_child = 0 1.22.630.246 I slot print_timing: id 0 | task 245 | prompt eval time = 1417.78 ms / 120 tokens ( 11.81 ms per token, 84.64 tokens per second) 1.22.630.248 I slot print_timing: id 0 | task 245 | eval time = 50.28 ms / 2 tokens ( 50.28 ms per token, 19.89 tokens per second) 1.22.630.248 I slot print_timing: id 0 | task 245 | total time = 1468.06 ms / 122 tokens 1.22.630.249 I slot print_timing: id 0 | task 245 | graphs reused = 1 1.22.630.249 I slot print_timing: id 0 | task 245 | graph reallocs = 0 / 0 (same size) / (changed size) 1.22.630.276 I slot release: id 0 | task 245 | stop processing: n_tokens = 121, truncated = 0 1.22.630.434 I slot print_timing: id 1 | task 247 | prompt eval time = 1417.92 ms / 140 tokens ( 10.13 ms per token, 98.74 tokens per second) 1.22.630.436 I slot print_timing: id 1 | task 247 | eval time = 50.32 ms / 2 tokens ( 50.32 ms per token, 19.87 tokens per second) 1.22.630.436 I slot print_timing: id 1 | task 247 | total time = 1468.25 ms / 142 tokens 1.22.630.436 I slot print_timing: id 1 | task 247 | graphs reused = 1 1.22.630.437 I slot print_timing: id 1 | task 247 | graph reallocs = 0 / 0 (same size) / (changed size) 1.22.630.450 I slot release: id 1 | task 247 | stop processing: n_tokens = 141, truncated = 0 1.22.630.638 I slot print_timing: id 2 | task 246 | prompt eval time = 1418.12 ms / 158 tokens ( 8.98 ms per token, 111.42 tokens per second) 1.22.630.639 I slot print_timing: id 2 | task 246 | eval time = 50.32 ms / 2 tokens ( 50.32 ms per token, 19.87 tokens per second) 1.22.630.640 I slot print_timing: id 2 | task 246 | total time = 1468.44 ms / 160 tokens 1.22.630.640 I slot print_timing: id 2 | task 246 | graphs reused = 1 1.22.630.640 I slot print_timing: id 2 | task 246 | graph reallocs = 0 / 0 (same size) / (changed size) 1.22.630.650 I slot release: id 2 | task 246 | stop processing: n_tokens = 159, truncated = 0 1.22.630.811 I slot print_timing: id 3 | task 248 | prompt eval time = 1418.31 ms / 168 tokens ( 8.44 ms per token, 118.45 tokens per second) 1.22.630.812 I slot print_timing: id 3 | task 248 | eval time = 50.29 ms / 2 tokens ( 50.29 ms per token, 19.88 tokens per second) 1.22.630.812 I slot print_timing: id 3 | task 248 | total time = 1468.60 ms / 170 tokens 1.22.630.812 I slot print_timing: id 3 | task 248 | graphs reused = 1 1.22.630.813 I slot print_timing: id 3 | task 248 | graph reallocs = 0 / 0 (same size) / (changed size) 1.22.630.821 I slot release: id 3 | task 248 | stop processing: n_tokens = 169, truncated = 0 1.22.635.764 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.272 (> 0.100 thold), f_keep = 0.231 1.22.639.394 I slot launch_slot_: id 0 | task 252 | processing task, is_child = 0 1.22.639.415 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 130.065 MiB) 1.22.647.759 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.403 MiB) 1.22.651.538 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.401 MiB) 1.22.658.045 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.211 (> 0.100 thold), f_keep = 0.199 1.22.659.557 I slot launch_slot_: id 1 | task 253 | processing task, is_child = 0 1.22.659.603 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.154 (> 0.100 thold), f_keep = 0.176 1.22.659.648 I slot launch_slot_: id 2 | task 254 | processing task, is_child = 0 1.22.659.668 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 1.22.659.707 I slot launch_slot_: id 3 | task 255 | processing task, is_child = 0 1.24.203.625 I slot print_timing: id 0 | task 252 | prompt eval time = 1493.25 ms / 103 tokens ( 14.50 ms per token, 68.98 tokens per second) 1.24.203.627 I slot print_timing: id 0 | task 252 | eval time = 50.66 ms / 2 tokens ( 50.66 ms per token, 19.74 tokens per second) 1.24.203.628 I slot print_timing: id 0 | task 252 | total time = 1543.91 ms / 105 tokens 1.24.203.629 I slot print_timing: id 0 | task 252 | graphs reused = 1 1.24.203.629 I slot print_timing: id 0 | task 252 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.203.647 I slot release: id 0 | task 252 | stop processing: n_tokens = 104, truncated = 0 1.24.203.801 I slot print_timing: id 1 | task 253 | prompt eval time = 1493.44 ms / 133 tokens ( 11.23 ms per token, 89.06 tokens per second) 1.24.203.804 I slot print_timing: id 1 | task 253 | eval time = 50.63 ms / 2 tokens ( 50.63 ms per token, 19.75 tokens per second) 1.24.203.804 I slot print_timing: id 1 | task 253 | total time = 1544.08 ms / 135 tokens 1.24.203.805 I slot print_timing: id 1 | task 253 | graphs reused = 1 1.24.203.805 I slot print_timing: id 1 | task 253 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.203.823 I slot release: id 1 | task 253 | stop processing: n_tokens = 134, truncated = 0 1.24.203.999 I slot print_timing: id 2 | task 254 | prompt eval time = 1493.63 ms / 182 tokens ( 8.21 ms per token, 121.85 tokens per second) 1.24.204.001 I slot print_timing: id 2 | task 254 | eval time = 50.63 ms / 2 tokens ( 50.63 ms per token, 19.75 tokens per second) 1.24.204.001 I slot print_timing: id 2 | task 254 | total time = 1544.26 ms / 184 tokens 1.24.204.001 I slot print_timing: id 2 | task 254 | graphs reused = 1 1.24.204.001 I slot print_timing: id 2 | task 254 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.204.018 I slot release: id 2 | task 254 | stop processing: n_tokens = 183, truncated = 0 1.24.204.192 I slot print_timing: id 3 | task 255 | prompt eval time = 1493.82 ms / 155 tokens ( 9.64 ms per token, 103.76 tokens per second) 1.24.204.194 I slot print_timing: id 3 | task 255 | eval time = 50.62 ms / 2 tokens ( 50.62 ms per token, 19.75 tokens per second) 1.24.204.194 I slot print_timing: id 3 | task 255 | total time = 1544.44 ms / 157 tokens 1.24.204.194 I slot print_timing: id 3 | task 255 | graphs reused = 1 1.24.204.195 I slot print_timing: id 3 | task 255 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.204.207 I slot release: id 3 | task 255 | stop processing: n_tokens = 156, truncated = 0 1.24.208.829 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.226 (> 0.100 thold), f_keep = 0.269 1.24.212.301 I slot launch_slot_: id 0 | task 259 | processing task, is_child = 0 1.24.212.327 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.286 MiB) 1.24.215.946 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.032 MiB) 1.24.219.341 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.010 MiB) 1.24.222.652 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.194 (> 0.100 thold), f_keep = 0.209 1.24.222.711 I slot launch_slot_: id 1 | task 260 | processing task, is_child = 0 1.24.953.633 I slot print_timing: id 0 | task 259 | prompt eval time = 695.57 ms / 124 tokens ( 5.61 ms per token, 178.27 tokens per second) 1.24.953.635 I slot print_timing: id 0 | task 259 | eval time = 35.30 ms / 2 tokens ( 35.30 ms per token, 28.32 tokens per second) 1.24.953.636 I slot print_timing: id 0 | task 259 | total time = 730.87 ms / 126 tokens 1.24.953.636 I slot print_timing: id 0 | task 259 | graphs reused = 1 1.24.953.637 I slot print_timing: id 0 | task 259 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.953.657 I slot release: id 0 | task 259 | stop processing: n_tokens = 125, truncated = 0 1.24.953.794 I slot print_timing: id 1 | task 260 | prompt eval time = 695.76 ms / 144 tokens ( 4.83 ms per token, 206.97 tokens per second) 1.24.953.796 I slot print_timing: id 1 | task 260 | eval time = 35.26 ms / 2 tokens ( 35.26 ms per token, 28.36 tokens per second) 1.24.953.796 I slot print_timing: id 1 | task 260 | total time = 731.02 ms / 146 tokens 1.24.953.797 I slot print_timing: id 1 | task 260 | graphs reused = 1 1.24.953.797 I slot print_timing: id 1 | task 260 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.953.806 I slot release: id 1 | task 260 | stop processing: n_tokens = 145, truncated = 0 1.24.968.672 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 183, t_last = 388525624499 1.24.968.773 I slot launch_slot_: id 2 | task 264 | processing task, is_child = 0 1.24.968.793 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.286 MiB) 1.24.974.133 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.266 MiB) 1.24.979.423 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 156, t_last = 388525624688 1.24.979.461 I slot launch_slot_: id 3 | task 265 | processing task, is_child = 0 1.24.979.500 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 125, t_last = 388526374138 1.24.979.533 I slot launch_slot_: id 0 | task 266 | processing task, is_child = 0 1.24.979.552 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 145, t_last = 388526374287 1.24.979.584 I slot launch_slot_: id 1 | task 267 | processing task, is_child = 0 1.29.938.893 I slot print_timing: id 0 | task 266 | prompt processing, n_tokens = 727, progress = 0.58, t = 4.96 s / 146.59 tokens per second 1.30.027.312 I slot print_timing: id 1 | task 267 | prompt processing, n_tokens = 718, progress = 0.58, t = 4.96 s / 144.78 tokens per second 1.30.030.293 I slot print_timing: id 2 | task 264 | prompt processing, n_tokens = 699, progress = 0.58, t = 4.96 s / 140.95 tokens per second 1.30.032.465 I slot print_timing: id 3 | task 265 | prompt processing, n_tokens = 714, progress = 0.58, t = 4.96 s / 143.97 tokens per second 1.33.099.086 I slot print_timing: id 0 | task 266 | prompt processing, n_tokens = 1125, progress = 0.91, t = 8.12 s / 138.56 tokens per second 1.33.188.282 I slot print_timing: id 1 | task 267 | prompt processing, n_tokens = 1125, progress = 0.91, t = 8.12 s / 138.56 tokens per second 1.33.192.568 I slot print_timing: id 2 | task 264 | prompt processing, n_tokens = 1125, progress = 0.93, t = 8.12 s / 138.56 tokens per second 1.33.194.590 I slot print_timing: id 3 | task 265 | prompt processing, n_tokens = 1125, progress = 0.91, t = 8.12 s / 138.56 tokens per second 1.34.122.627 I slot print_timing: id 0 | task 266 | prompt processing, n_tokens = 1239, progress = 1.00, t = 9.14 s / 135.51 tokens per second 1.34.212.014 I slot print_timing: id 1 | task 267 | prompt processing, n_tokens = 1230, progress = 1.00, t = 9.14 s / 134.53 tokens per second 1.34.215.068 I slot print_timing: id 2 | task 264 | prompt processing, n_tokens = 1211, progress = 1.00, t = 9.14 s / 132.45 tokens per second 1.34.217.317 I slot print_timing: id 3 | task 265 | prompt processing, n_tokens = 1226, progress = 1.00, t = 9.14 s / 134.09 tokens per second 1.37.442.724 I slot print_timing: id 2 | task 264 | prompt eval time = 9349.90 ms / 1215 tokens ( 7.70 ms per token, 129.95 tokens per second) 1.37.442.729 I slot print_timing: id 2 | task 264 | eval time = 3113.20 ms / 63 tokens ( 50.21 ms per token, 19.92 tokens per second) 1.37.442.730 I slot print_timing: id 2 | task 264 | total time = 12463.10 ms / 1278 tokens 1.37.442.731 I slot print_timing: id 2 | task 264 | graphs reused = 63 1.37.442.732 I slot print_timing: id 2 | task 264 | graph reallocs = 0 / 0 (same size) / (changed size) 1.37.442.832 I slot release: id 2 | task 264 | stop processing: n_tokens = 1277, truncated = 0 1.37.503.925 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.897 1.37.504.003 I slot launch_slot_: id 2 | task 337 | processing task, is_child = 0 1.38.331.765 I slot print_timing: id 3 | task 265 | prompt eval time = 9350.10 ms / 1230 tokens ( 7.60 ms per token, 131.55 tokens per second) 1.38.331.770 I slot print_timing: id 3 | task 265 | eval time = 4002.02 ms / 72 tokens ( 56.37 ms per token, 17.74 tokens per second) 1.38.331.771 I slot print_timing: id 3 | task 265 | total time = 13352.12 ms / 1302 tokens 1.38.331.771 I slot print_timing: id 3 | task 265 | graphs reused = 68 1.38.331.771 I slot print_timing: id 3 | task 265 | graph reallocs = 0 / 0 (same size) / (changed size) 1.38.331.816 I slot release: id 3 | task 265 | stop processing: n_tokens = 1301, truncated = 0 1.38.375.937 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.881 1.38.375.975 I slot launch_slot_: id 3 | task 347 | processing task, is_child = 0 1.39.392.138 I slot print_timing: id 1 | task 267 | prompt eval time = 9349.71 ms / 1234 tokens ( 7.58 ms per token, 131.98 tokens per second) 1.39.392.140 I slot print_timing: id 1 | task 267 | eval time = 5062.82 ms / 85 tokens ( 60.27 ms per token, 16.59 tokens per second) 1.39.392.140 I slot print_timing: id 1 | task 267 | total time = 14412.53 ms / 1319 tokens 1.39.392.141 I slot print_timing: id 1 | task 267 | graphs reused = 77 1.39.392.141 I slot print_timing: id 1 | task 267 | graph reallocs = 0 / 0 (same size) / (changed size) 1.39.392.188 I slot release: id 1 | task 267 | stop processing: n_tokens = 1318, truncated = 0 1.39.449.279 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 1.39.449.315 I slot launch_slot_: id 1 | task 361 | processing task, is_child = 0 1.40.593.102 I slot print_timing: id 0 | task 266 | n_gen = 100, tg = 15.80 t/s, tg_3s = 15.96 t/s 1.43.118.799 I slot print_timing: id 2 | task 337 | prompt eval time = 529.04 ms / 132 tokens ( 4.01 ms per token, 249.51 tokens per second) 1.43.118.804 I slot print_timing: id 2 | task 337 | eval time = 5085.73 ms / 85 tokens ( 60.54 ms per token, 16.52 tokens per second) 1.43.118.805 I slot print_timing: id 2 | task 337 | total time = 5614.78 ms / 217 tokens 1.43.118.805 I slot print_timing: id 2 | task 337 | graphs reused = 138 1.43.118.806 I slot print_timing: id 2 | task 337 | graph reallocs = 0 / 0 (same size) / (changed size) 1.43.118.895 I slot release: id 2 | task 337 | stop processing: n_tokens = 1341, truncated = 0 1.43.180.009 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.855 1.43.180.072 I slot launch_slot_: id 2 | task 427 | processing task, is_child = 0 1.43.688.086 I slot print_timing: id 0 | task 266 | n_gen = 153, tg = 16.24 t/s, tg_3s = 17.12 t/s 1.44.086.223 I slot print_timing: id 3 | task 347 | prompt eval time = 520.06 ms / 139 tokens ( 3.74 ms per token, 267.28 tokens per second) 1.44.086.228 I slot print_timing: id 3 | task 347 | eval time = 5190.18 ms / 87 tokens ( 60.35 ms per token, 16.57 tokens per second) 1.44.086.229 I slot print_timing: id 3 | task 347 | total time = 5710.24 ms / 226 tokens 1.44.086.229 I slot print_timing: id 3 | task 347 | graphs reused = 145 1.44.086.229 I slot print_timing: id 3 | task 347 | graph reallocs = 0 / 0 (same size) / (changed size) 1.44.086.288 I slot release: id 3 | task 347 | stop processing: n_tokens = 1350, truncated = 0 1.44.130.582 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.849 1.44.130.614 I slot launch_slot_: id 3 | task 439 | processing task, is_child = 0 1.45.814.205 I slot print_timing: id 1 | task 361 | n_gen = 100, tg = 17.02 t/s, tg_3s = 17.19 t/s 1.46.723.566 I slot print_timing: id 0 | task 266 | n_gen = 205, tg = 16.46 t/s, tg_3s = 17.13 t/s 1.47.277.211 I slot print_timing: id 0 | task 266 | prompt eval time = 9349.53 ms / 1243 tokens ( 7.52 ms per token, 132.95 tokens per second) 1.47.277.220 I slot print_timing: id 0 | task 266 | eval time = 12948.08 ms / 216 tokens ( 60.22 ms per token, 16.60 tokens per second) 1.47.277.221 I slot print_timing: id 0 | task 266 | total time = 22297.62 ms / 1459 tokens 1.47.277.222 I slot print_timing: id 0 | task 266 | graphs reused = 196 1.47.277.223 I slot print_timing: id 0 | task 266 | graph reallocs = 0 / 0 (same size) / (changed size) 1.47.277.314 I slot release: id 0 | task 266 | stop processing: n_tokens = 1458, truncated = 0 1.47.325.947 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.886 (> 0.100 thold), f_keep = 0.786 1.47.326.008 I slot launch_slot_: id 0 | task 495 | processing task, is_child = 0 1.47.881.094 I slot print_timing: id 1 | task 361 | prompt eval time = 549.14 ms / 139 tokens ( 3.95 ms per token, 253.12 tokens per second) 1.47.881.100 I slot print_timing: id 1 | task 361 | eval time = 7882.63 ms / 132 tokens ( 60.17 ms per token, 16.62 tokens per second) 1.47.881.100 I slot print_timing: id 1 | task 361 | total time = 8431.77 ms / 271 tokens 1.47.881.100 I slot print_timing: id 1 | task 361 | graphs reused = 197 1.47.881.101 I slot print_timing: id 1 | task 361 | graph reallocs = 0 / 0 (same size) / (changed size) 1.47.881.150 I slot release: id 1 | task 361 | stop processing: n_tokens = 1395, truncated = 0 1.47.938.177 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.822 1.47.938.211 I slot launch_slot_: id 1 | task 499 | processing task, is_child = 0 1.49.953.211 I slot print_timing: id 2 | task 427 | n_gen = 100, tg = 15.80 t/s, tg_3s = 15.96 t/s 1.50.151.089 I slot print_timing: id 3 | task 439 | prompt eval time = 523.85 ms / 141 tokens ( 3.72 ms per token, 269.16 tokens per second) 1.50.151.095 I slot print_timing: id 3 | task 439 | eval time = 5496.62 ms / 93 tokens ( 59.75 ms per token, 16.74 tokens per second) 1.50.151.095 I slot print_timing: id 3 | task 439 | total time = 6020.47 ms / 234 tokens 1.50.151.095 I slot print_timing: id 3 | task 439 | graphs reused = 230 1.50.151.096 I slot print_timing: id 3 | task 439 | graph reallocs = 0 / 0 (same size) / (changed size) 1.50.151.144 I slot release: id 3 | task 439 | stop processing: n_tokens = 1358, truncated = 0 1.50.195.577 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.844 1.50.195.615 I slot launch_slot_: id 3 | task 537 | processing task, is_child = 0 1.51.136.073 I slot print_timing: id 2 | task 427 | prompt eval time = 508.42 ms / 114 tokens ( 4.46 ms per token, 224.22 tokens per second) 1.51.136.078 I slot print_timing: id 2 | task 427 | eval time = 7447.57 ms / 117 tokens ( 64.20 ms per token, 15.58 tokens per second) 1.51.136.079 I slot print_timing: id 2 | task 427 | total time = 7955.99 ms / 231 tokens 1.51.136.079 I slot print_timing: id 2 | task 427 | graphs reused = 239 1.51.136.080 I slot print_timing: id 2 | task 427 | graph reallocs = 0 / 0 (same size) / (changed size) 1.51.136.126 I slot release: id 2 | task 427 | stop processing: n_tokens = 1355, truncated = 0 1.51.193.408 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.846 1.51.193.442 I slot launch_slot_: id 2 | task 551 | processing task, is_child = 0 1.52.999.668 I slot print_timing: id 1 | task 499 | prompt eval time = 528.72 ms / 125 tokens ( 4.23 ms per token, 236.42 tokens per second) 1.52.999.673 I slot print_timing: id 1 | task 499 | eval time = 4532.72 ms / 78 tokens ( 58.87 ms per token, 16.99 tokens per second) 1.52.999.674 I slot print_timing: id 1 | task 499 | total time = 5061.45 ms / 203 tokens 1.52.999.674 I slot print_timing: id 1 | task 499 | graphs reused = 265 1.52.999.675 I slot print_timing: id 1 | task 499 | graph reallocs = 0 / 0 (same size) / (changed size) 1.52.999.721 I slot release: id 1 | task 499 | stop processing: n_tokens = 1327, truncated = 0 1.53.056.731 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.864 1.53.056.771 I slot launch_slot_: id 1 | task 582 | processing task, is_child = 0 1.54.322.174 I slot print_timing: id 0 | task 495 | n_gen = 100, tg = 15.37 t/s, tg_3s = 15.52 t/s 1.55.321.705 I slot print_timing: id 2 | task 551 | prompt eval time = 470.13 ms / 101 tokens ( 4.65 ms per token, 214.83 tokens per second) 1.55.321.713 I slot print_timing: id 2 | task 551 | eval time = 3658.12 ms / 67 tokens ( 55.43 ms per token, 18.04 tokens per second) 1.55.321.714 I slot print_timing: id 2 | task 551 | total time = 4128.25 ms / 168 tokens 1.55.321.715 I slot print_timing: id 2 | task 551 | graphs reused = 300 1.55.321.716 I slot print_timing: id 2 | task 551 | graph reallocs = 0 / 0 (same size) / (changed size) 1.55.321.835 I slot release: id 2 | task 551 | stop processing: n_tokens = 1292, truncated = 0 1.55.322.235 I slot print_timing: id 3 | task 537 | prompt eval time = 444.04 ms / 101 tokens ( 4.40 ms per token, 227.46 tokens per second) 1.55.322.245 I slot print_timing: id 3 | task 537 | eval time = 4682.57 ms / 80 tokens ( 59.27 ms per token, 16.87 tokens per second) 1.55.322.246 I slot print_timing: id 3 | task 537 | total time = 5126.62 ms / 181 tokens 1.55.322.246 I slot print_timing: id 3 | task 537 | graphs reused = 300 1.55.322.247 I slot print_timing: id 3 | task 537 | graph reallocs = 0 / 0 (same size) / (changed size) 1.55.322.320 I slot release: id 3 | task 537 | stop processing: n_tokens = 1305, truncated = 0 1.55.362.134 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.887 1.55.362.174 I slot launch_slot_: id 2 | task 622 | processing task, is_child = 0 1.55.362.286 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.755 MiB) 1.55.362.290 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.188 MiB) 1.55.387.704 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.878 1.55.387.737 I slot launch_slot_: id 3 | task 623 | processing task, is_child = 0 1.57.364.694 I slot print_timing: id 0 | task 495 | n_gen = 146, tg = 15.29 t/s, tg_3s = 15.12 t/s 1.59.196.882 I slot print_timing: id 1 | task 582 | n_gen = 100, tg = 17.47 t/s, tg_3s = 17.65 t/s 1.59.612.320 I slot print_timing: id 2 | task 622 | prompt eval time = 838.48 ms / 120 tokens ( 6.99 ms per token, 143.12 tokens per second) 1.59.612.329 I slot print_timing: id 2 | task 622 | eval time = 3386.09 ms / 69 tokens ( 49.80 ms per token, 20.08 tokens per second) 1.59.612.330 I slot print_timing: id 2 | task 622 | total time = 4224.57 ms / 189 tokens 1.59.612.331 I slot print_timing: id 2 | task 622 | graphs reused = 367 1.59.612.332 I slot print_timing: id 2 | task 622 | graph reallocs = 0 / 0 (same size) / (changed size) 1.59.612.428 I slot release: id 2 | task 622 | stop processing: n_tokens = 1313, truncated = 0 1.59.673.720 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.873 1.59.673.800 I slot launch_slot_: id 2 | task 695 | processing task, is_child = 0 2.00.284.117 I slot print_timing: id 0 | task 495 | prompt eval time = 554.93 ms / 169 tokens ( 3.28 ms per token, 304.54 tokens per second) 2.00.284.122 I slot print_timing: id 0 | task 495 | eval time = 12403.17 ms / 197 tokens ( 63.28 ms per token, 15.80 tokens per second) 2.00.284.123 I slot print_timing: id 0 | task 495 | total time = 12958.10 ms / 366 tokens 2.00.284.123 I slot print_timing: id 0 | task 495 | graphs reused = 369 2.00.284.124 I slot print_timing: id 0 | task 495 | graph reallocs = 0 / 0 (same size) / (changed size) 2.00.284.169 I slot release: id 0 | task 495 | stop processing: n_tokens = 1490, truncated = 0 2.00.284.312 I slot print_timing: id 1 | task 582 | prompt eval time = 473.16 ms / 95 tokens ( 4.98 ms per token, 200.78 tokens per second) 2.00.284.314 I slot print_timing: id 1 | task 582 | eval time = 6754.38 ms / 114 tokens ( 59.77 ms per token, 16.73 tokens per second) 2.00.284.314 I slot print_timing: id 1 | task 582 | total time = 7227.54 ms / 209 tokens 2.00.284.314 I slot print_timing: id 1 | task 582 | graphs reused = 369 2.00.284.315 I slot print_timing: id 1 | task 582 | graph reallocs = 0 / 0 (same size) / (changed size) 2.00.284.343 I slot release: id 1 | task 582 | stop processing: n_tokens = 1333, truncated = 0 2.00.320.526 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.911 (> 0.100 thold), f_keep = 0.769 2.00.320.559 I slot launch_slot_: id 0 | task 702 | processing task, is_child = 0 2.00.320.637 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.010 MiB) 2.00.320.640 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.068 MiB) 2.00.320.642 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.166 MiB) 2.00.340.939 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.860 2.00.340.975 I slot launch_slot_: id 1 | task 703 | processing task, is_child = 0 2.02.211.605 I slot print_timing: id 3 | task 623 | n_gen = 100, tg = 16.54 t/s, tg_3s = 16.71 t/s 2.04.531.249 I slot print_timing: id 1 | task 703 | prompt eval time = 767.80 ms / 97 tokens ( 7.92 ms per token, 126.34 tokens per second) 2.04.531.255 I slot print_timing: id 1 | task 703 | eval time = 3419.15 ms / 69 tokens ( 50.28 ms per token, 19.89 tokens per second) 2.04.531.256 I slot print_timing: id 1 | task 703 | total time = 4186.95 ms / 166 tokens 2.04.531.257 I slot print_timing: id 1 | task 703 | graphs reused = 437 2.04.531.258 I slot print_timing: id 1 | task 703 | graph reallocs = 0 / 0 (same size) / (changed size) 2.04.531.356 I slot release: id 1 | task 703 | stop processing: n_tokens = 1290, truncated = 0 2.04.593.024 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.948 (> 0.100 thold), f_keep = 0.888 2.04.593.100 I slot launch_slot_: id 1 | task 775 | processing task, is_child = 0 2.05.259.492 I slot print_timing: id 3 | task 623 | prompt eval time = 834.72 ms / 148 tokens ( 5.64 ms per token, 177.30 tokens per second) 2.05.259.504 I slot print_timing: id 3 | task 623 | eval time = 9033.06 ms / 153 tokens ( 59.43 ms per token, 16.83 tokens per second) 2.05.259.505 I slot print_timing: id 3 | task 623 | total time = 9867.78 ms / 301 tokens 2.05.259.507 I slot print_timing: id 3 | task 623 | graphs reused = 440 2.05.259.508 I slot print_timing: id 3 | task 623 | graph reallocs = 0 / 0 (same size) / (changed size) 2.05.259.622 I slot release: id 3 | task 623 | stop processing: n_tokens = 1425, truncated = 0 2.05.313.660 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.804 2.05.313.725 I slot launch_slot_: id 3 | task 783 | processing task, is_child = 0 2.06.259.652 I slot print_timing: id 0 | task 702 | prompt eval time = 770.90 ms / 133 tokens ( 5.80 ms per token, 172.52 tokens per second) 2.06.259.654 I slot print_timing: id 0 | task 702 | eval time = 5147.76 ms / 89 tokens ( 58.50 ms per token, 17.09 tokens per second) 2.06.259.654 I slot print_timing: id 0 | task 702 | total time = 5918.66 ms / 222 tokens 2.06.259.655 I slot print_timing: id 0 | task 702 | graphs reused = 449 2.06.259.655 I slot print_timing: id 0 | task 702 | graph reallocs = 0 / 0 (same size) / (changed size) 2.06.259.704 I slot release: id 0 | task 702 | stop processing: n_tokens = 1346, truncated = 0 2.06.304.592 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.851 2.06.304.628 I slot launch_slot_: id 0 | task 797 | processing task, is_child = 0 2.06.836.494 I slot print_timing: id 2 | task 695 | n_gen = 100, tg = 14.77 t/s, tg_3s = 14.92 t/s 2.06.984.741 I slot print_timing: id 2 | task 695 | prompt eval time = 460.09 ms / 86 tokens ( 5.35 ms per token, 186.92 tokens per second) 2.06.984.746 I slot print_timing: id 2 | task 695 | eval time = 6850.84 ms / 103 tokens ( 67.17 ms per token, 14.89 tokens per second) 2.06.984.747 I slot print_timing: id 2 | task 695 | total time = 7310.93 ms / 189 tokens 2.06.984.747 I slot print_timing: id 2 | task 695 | graphs reused = 454 2.06.984.747 I slot print_timing: id 2 | task 695 | graph reallocs = 0 / 0 (same size) / (changed size) 2.06.984.794 I slot release: id 2 | task 695 | stop processing: n_tokens = 1313, truncated = 0 2.07.042.102 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.873 2.07.042.140 I slot launch_slot_: id 2 | task 806 | processing task, is_child = 0 2.09.434.328 I slot print_timing: id 3 | task 783 | prompt eval time = 450.28 ms / 101 tokens ( 4.46 ms per token, 224.30 tokens per second) 2.09.434.335 I slot print_timing: id 3 | task 783 | eval time = 3670.30 ms / 59 tokens ( 63.28 ms per token, 15.80 tokens per second) 2.09.434.336 I slot print_timing: id 3 | task 783 | total time = 4120.59 ms / 160 tokens 2.09.434.337 I slot print_timing: id 3 | task 783 | graphs reused = 489 2.09.434.338 I slot print_timing: id 3 | task 783 | graph reallocs = 0 / 0 (same size) / (changed size) 2.09.434.453 I slot release: id 3 | task 783 | stop processing: n_tokens = 1284, truncated = 0 2.09.481.647 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.943 (> 0.100 thold), f_keep = 0.893 2.09.481.713 I slot launch_slot_: id 3 | task 847 | processing task, is_child = 0 2.10.015.735 I slot print_timing: id 1 | task 775 | prompt eval time = 464.34 ms / 84 tokens ( 5.53 ms per token, 180.90 tokens per second) 2.10.015.737 I slot print_timing: id 1 | task 775 | eval time = 4958.28 ms / 71 tokens ( 70.83 ms per token, 14.12 tokens per second) 2.10.015.738 I slot print_timing: id 1 | task 775 | total time = 5422.62 ms / 155 tokens 2.10.015.738 I slot print_timing: id 1 | task 775 | graphs reused = 490 2.10.015.738 I slot print_timing: id 1 | task 775 | graph reallocs = 0 / 0 (same size) / (changed size) 2.10.015.780 I slot release: id 1 | task 775 | stop processing: n_tokens = 1279, truncated = 0 2.10.072.495 I slot print_timing: id 0 | task 797 | prompt eval time = 431.40 ms / 95 tokens ( 4.54 ms per token, 220.21 tokens per second) 2.10.072.497 I slot print_timing: id 0 | task 797 | eval time = 3336.45 ms / 52 tokens ( 65.42 ms per token, 15.29 tokens per second) 2.10.072.497 I slot print_timing: id 0 | task 797 | total time = 3767.86 ms / 147 tokens 2.10.072.498 I slot print_timing: id 0 | task 797 | graphs reused = 490 2.10.072.498 I slot print_timing: id 0 | task 797 | graph reallocs = 0 / 0 (same size) / (changed size) 2.10.072.544 I slot release: id 0 | task 797 | stop processing: n_tokens = 1271, truncated = 0 2.10.072.860 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.902 2.10.072.896 I slot launch_slot_: id 0 | task 853 | processing task, is_child = 0 2.10.072.972 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.051 MiB) 2.10.072.977 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.051 MiB) 2.10.072.978 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.149 MiB) 2.10.092.337 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.896 2.10.092.370 I slot launch_slot_: id 1 | task 854 | processing task, is_child = 0 2.13.432.919 I slot print_timing: id 2 | task 806 | n_gen = 100, tg = 16.87 t/s, tg_3s = 17.04 t/s 2.14.238.736 I slot print_timing: id 0 | task 853 | prompt eval time = 619.19 ms / 96 tokens ( 6.45 ms per token, 155.04 tokens per second) 2.14.238.741 I slot print_timing: id 0 | task 853 | eval time = 3527.17 ms / 71 tokens ( 50.39 ms per token, 19.85 tokens per second) 2.14.238.742 I slot print_timing: id 0 | task 853 | total time = 4146.36 ms / 167 tokens 2.14.238.743 I slot print_timing: id 0 | task 853 | graphs reused = 560 2.14.238.744 I slot print_timing: id 0 | task 853 | graph reallocs = 0 / 0 (same size) / (changed size) 2.14.238.839 I slot release: id 0 | task 853 | stop processing: n_tokens = 1291, truncated = 0 2.14.287.219 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.888 2.14.287.291 I slot launch_slot_: id 0 | task 928 | processing task, is_child = 0 2.15.536.144 I slot print_timing: id 3 | task 847 | prompt eval time = 433.27 ms / 90 tokens ( 4.81 ms per token, 207.72 tokens per second) 2.15.536.150 I slot print_timing: id 3 | task 847 | eval time = 5621.15 ms / 94 tokens ( 60.44 ms per token, 16.54 tokens per second) 2.15.536.151 I slot print_timing: id 3 | task 847 | total time = 6054.42 ms / 184 tokens 2.15.536.152 I slot print_timing: id 3 | task 847 | graphs reused = 575 2.15.536.153 I slot print_timing: id 3 | task 847 | graph reallocs = 0 / 0 (same size) / (changed size) 2.15.536.242 I slot release: id 3 | task 847 | stop processing: n_tokens = 1308, truncated = 0 2.15.583.680 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.876 2.15.583.748 I slot launch_slot_: id 3 | task 947 | processing task, is_child = 0 2.16.309.963 I slot print_timing: id 1 | task 854 | prompt eval time = 616.15 ms / 87 tokens ( 7.08 ms per token, 141.20 tokens per second) 2.16.309.966 I slot print_timing: id 1 | task 854 | eval time = 5598.19 ms / 96 tokens ( 58.93 ms per token, 16.97 tokens per second) 2.16.309.966 I slot print_timing: id 1 | task 854 | total time = 6214.34 ms / 183 tokens 2.16.309.967 I slot print_timing: id 1 | task 854 | graphs reused = 578 2.16.309.967 I slot print_timing: id 1 | task 854 | graph reallocs = 0 / 0 (same size) / (changed size) 2.16.310.021 I slot release: id 1 | task 854 | stop processing: n_tokens = 1307, truncated = 0 2.16.310.173 I slot print_timing: id 2 | task 806 | prompt eval time = 520.79 ms / 130 tokens ( 4.01 ms per token, 249.62 tokens per second) 2.16.310.178 I slot print_timing: id 2 | task 806 | eval time = 8747.24 ms / 141 tokens ( 62.48 ms per token, 16.01 tokens per second) 2.16.310.178 I slot print_timing: id 2 | task 806 | total time = 9268.03 ms / 271 tokens 2.16.310.178 I slot print_timing: id 2 | task 806 | graphs reused = 578 2.16.310.179 I slot print_timing: id 2 | task 806 | graph reallocs = 0 / 0 (same size) / (changed size) 2.16.310.209 I slot release: id 2 | task 806 | stop processing: n_tokens = 1395, truncated = 0 2.16.354.046 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.877 2.16.354.086 I slot launch_slot_: id 1 | task 955 | processing task, is_child = 0 2.16.354.178 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.130 MiB) 2.16.354.184 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.188 MiB) 2.16.376.755 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.941 (> 0.100 thold), f_keep = 0.822 2.16.376.797 I slot launch_slot_: id 2 | task 956 | processing task, is_child = 0 2.19.669.668 I slot print_timing: id 2 | task 956 | prompt eval time = 847.74 ms / 93 tokens ( 9.12 ms per token, 109.70 tokens per second) 2.19.669.678 I slot print_timing: id 2 | task 956 | eval time = 2441.26 ms / 50 tokens ( 49.82 ms per token, 20.07 tokens per second) 2.19.669.679 I slot print_timing: id 2 | task 956 | total time = 3289.01 ms / 143 tokens 2.19.669.680 I slot print_timing: id 2 | task 956 | graphs reused = 626 2.19.669.681 I slot print_timing: id 2 | task 956 | graph reallocs = 0 / 0 (same size) / (changed size) 2.19.669.785 I slot release: id 2 | task 956 | stop processing: n_tokens = 1267, truncated = 0 2.19.730.880 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.904 2.19.730.940 I slot launch_slot_: id 2 | task 1009 | processing task, is_child = 0 2.21.275.918 I slot print_timing: id 0 | task 928 | n_gen = 100, tg = 15.23 t/s, tg_3s = 15.38 t/s 2.22.068.253 I slot print_timing: id 3 | task 947 | prompt eval time = 526.85 ms / 137 tokens ( 3.85 ms per token, 260.04 tokens per second) 2.22.068.256 I slot print_timing: id 3 | task 947 | eval time = 5957.65 ms / 98 tokens ( 61.42 ms per token, 16.28 tokens per second) 2.22.068.256 I slot print_timing: id 3 | task 947 | total time = 6484.49 ms / 235 tokens 2.22.068.257 I slot print_timing: id 3 | task 947 | graphs reused = 663 2.22.068.257 I slot print_timing: id 3 | task 947 | graph reallocs = 0 / 0 (same size) / (changed size) 2.22.068.306 I slot release: id 3 | task 947 | stop processing: n_tokens = 1359, truncated = 0 2.22.112.429 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.843 2.22.112.462 I slot launch_slot_: id 3 | task 1051 | processing task, is_child = 0 2.22.859.002 I slot print_timing: id 1 | task 955 | n_gen = 100, tg = 17.58 t/s, tg_3s = 17.76 t/s 2.23.304.119 I slot print_timing: id 2 | task 1009 | prompt eval time = 455.43 ms / 87 tokens ( 5.23 ms per token, 191.03 tokens per second) 2.23.304.122 I slot print_timing: id 2 | task 1009 | eval time = 3117.74 ms / 57 tokens ( 55.67 ms per token, 17.96 tokens per second) 2.23.304.122 I slot print_timing: id 2 | task 1009 | total time = 3573.17 ms / 144 tokens 2.23.304.123 I slot print_timing: id 2 | task 1009 | graphs reused = 677 2.23.304.123 I slot print_timing: id 2 | task 1009 | graph reallocs = 0 / 0 (same size) / (changed size) 2.23.304.170 I slot release: id 2 | task 1009 | stop processing: n_tokens = 1268, truncated = 0 2.23.361.995 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.904 2.23.362.067 I slot launch_slot_: id 2 | task 1070 | processing task, is_child = 0 2.23.758.943 I slot print_timing: id 0 | task 928 | prompt eval time = 487.93 ms / 131 tokens ( 3.72 ms per token, 268.48 tokens per second) 2.23.758.945 I slot print_timing: id 0 | task 928 | eval time = 8983.71 ms / 136 tokens ( 66.55 ms per token, 15.03 tokens per second) 2.23.758.946 I slot print_timing: id 0 | task 928 | total time = 9471.64 ms / 267 tokens 2.23.758.946 I slot print_timing: id 0 | task 928 | graphs reused = 677 2.23.758.947 I slot print_timing: id 0 | task 928 | graph reallocs = 0 / 0 (same size) / (changed size) 2.23.758.993 I slot release: id 0 | task 928 | stop processing: n_tokens = 1391, truncated = 0 2.23.853.490 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.824 2.23.853.528 I slot launch_slot_: id 0 | task 1073 | processing task, is_child = 0 2.25.873.064 I slot print_timing: id 1 | task 955 | n_gen = 145, tg = 16.66 t/s, tg_3s = 14.93 t/s 2.26.580.002 I slot print_timing: id 3 | task 1051 | prompt eval time = 449.17 ms / 98 tokens ( 4.58 ms per token, 218.18 tokens per second) 2.26.580.008 I slot print_timing: id 3 | task 1051 | eval time = 4018.36 ms / 66 tokens ( 61.82 ms per token, 16.18 tokens per second) 2.26.580.009 I slot print_timing: id 3 | task 1051 | total time = 4467.53 ms / 164 tokens 2.26.580.010 I slot print_timing: id 3 | task 1051 | graphs reused = 721 2.26.580.011 I slot print_timing: id 3 | task 1051 | graph reallocs = 0 / 0 (same size) / (changed size) 2.26.580.122 I slot release: id 3 | task 1051 | stop processing: n_tokens = 1288, truncated = 0 2.26.627.482 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.890 2.26.627.537 I slot launch_slot_: id 3 | task 1122 | processing task, is_child = 0 2.28.923.039 I slot print_timing: id 1 | task 955 | n_gen = 198, tg = 16.85 t/s, tg_3s = 17.38 t/s 2.29.579.701 I slot print_timing: id 2 | task 1070 | n_gen = 100, tg = 17.29 t/s, tg_3s = 17.46 t/s 2.29.680.350 I slot print_timing: id 0 | task 1073 | n_gen = 100, tg = 18.47 t/s, tg_3s = 18.66 t/s 2.29.880.097 I slot print_timing: id 1 | task 955 | prompt eval time = 851.37 ms / 153 tokens ( 5.56 ms per token, 179.71 tokens per second) 2.29.880.104 I slot print_timing: id 1 | task 955 | eval time = 12651.92 ms / 217 tokens ( 58.57 ms per token, 17.07 tokens per second) 2.29.880.105 I slot print_timing: id 1 | task 955 | total time = 13503.29 ms / 370 tokens 2.29.880.106 I slot print_timing: id 1 | task 955 | graphs reused = 775 2.29.880.107 I slot print_timing: id 1 | task 955 | graph reallocs = 0 / 0 (same size) / (changed size) 2.29.880.201 I slot release: id 1 | task 955 | stop processing: n_tokens = 1494, truncated = 0 2.29.941.338 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.767 2.29.941.407 I slot launch_slot_: id 1 | task 1181 | processing task, is_child = 0 2.30.913.695 I slot print_timing: id 0 | task 1073 | prompt eval time = 468.06 ms / 113 tokens ( 4.14 ms per token, 241.42 tokens per second) 2.30.913.699 I slot print_timing: id 0 | task 1073 | eval time = 6592.10 ms / 117 tokens ( 56.83 ms per token, 17.60 tokens per second) 2.30.913.699 I slot print_timing: id 0 | task 1073 | total time = 7060.16 ms / 230 tokens 2.30.913.700 I slot print_timing: id 0 | task 1073 | graphs reused = 784 2.30.913.700 I slot print_timing: id 0 | task 1073 | graph reallocs = 0 / 0 (same size) / (changed size) 2.30.913.748 I slot release: id 0 | task 1073 | stop processing: n_tokens = 1354, truncated = 0 2.30.958.610 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.846 2.30.958.646 I slot launch_slot_: id 0 | task 1195 | processing task, is_child = 0 2.31.534.403 I slot print_timing: id 2 | task 1070 | prompt eval time = 491.25 ms / 105 tokens ( 4.68 ms per token, 213.74 tokens per second) 2.31.534.405 I slot print_timing: id 2 | task 1070 | eval time = 7681.07 ms / 124 tokens ( 62.45 ms per token, 16.01 tokens per second) 2.31.534.405 I slot print_timing: id 2 | task 1070 | total time = 8172.32 ms / 229 tokens 2.31.534.406 I slot print_timing: id 2 | task 1070 | graphs reused = 786 2.31.534.406 I slot print_timing: id 2 | task 1070 | graph reallocs = 0 / 0 (same size) / (changed size) 2.31.534.457 I slot release: id 2 | task 1070 | stop processing: n_tokens = 1353, truncated = 0 2.31.591.268 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.847 2.31.591.305 I slot launch_slot_: id 2 | task 1201 | processing task, is_child = 0 2.33.278.906 I slot print_timing: id 3 | task 1122 | n_gen = 100, tg = 16.06 t/s, tg_3s = 16.22 t/s 2.33.539.088 I slot print_timing: id 3 | task 1122 | prompt eval time = 486.34 ms / 122 tokens ( 3.99 ms per token, 250.85 tokens per second) 2.33.539.093 I slot print_timing: id 3 | task 1122 | eval time = 6425.20 ms / 105 tokens ( 61.78 ms per token, 16.19 tokens per second) 2.33.539.094 I slot print_timing: id 3 | task 1122 | total time = 6911.54 ms / 227 tokens 2.33.539.095 I slot print_timing: id 3 | task 1122 | graphs reused = 813 2.33.539.096 I slot print_timing: id 3 | task 1122 | graph reallocs = 0 / 0 (same size) / (changed size) 2.33.539.192 I slot release: id 3 | task 1122 | stop processing: n_tokens = 1351, truncated = 0 2.33.586.096 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.848 2.33.586.157 I slot launch_slot_: id 3 | task 1233 | processing task, is_child = 0 2.36.594.777 I slot print_timing: id 1 | task 1181 | n_gen = 100, tg = 16.03 t/s, tg_3s = 16.19 t/s 2.37.248.039 I slot print_timing: id 0 | task 1195 | n_gen = 100, tg = 17.03 t/s, tg_3s = 17.20 t/s 2.37.298.149 I slot print_timing: id 0 | task 1195 | prompt eval time = 474.42 ms / 113 tokens ( 4.20 ms per token, 238.18 tokens per second) 2.37.298.154 I slot print_timing: id 0 | task 1195 | eval time = 5865.07 ms / 101 tokens ( 58.65 ms per token, 17.05 tokens per second) 2.37.298.156 I slot print_timing: id 0 | task 1195 | total time = 6339.49 ms / 214 tokens 2.37.298.157 I slot print_timing: id 0 | task 1195 | graphs reused = 876 2.37.298.158 I slot print_timing: id 0 | task 1195 | graph reallocs = 0 / 0 (same size) / (changed size) 2.37.298.252 I slot release: id 0 | task 1195 | stop processing: n_tokens = 1338, truncated = 0 2.37.298.611 I slot print_timing: id 1 | task 1181 | prompt eval time = 476.28 ms / 96 tokens ( 4.96 ms per token, 201.56 tokens per second) 2.37.298.615 I slot print_timing: id 1 | task 1181 | eval time = 6880.91 ms / 114 tokens ( 60.89 ms per token, 16.42 tokens per second) 2.37.298.617 I slot print_timing: id 1 | task 1181 | total time = 7357.20 ms / 210 tokens 2.37.298.617 I slot print_timing: id 1 | task 1181 | graphs reused = 876 2.37.298.619 I slot print_timing: id 1 | task 1181 | graph reallocs = 0 / 0 (same size) / (changed size) 2.37.298.713 I slot release: id 1 | task 1181 | stop processing: n_tokens = 1334, truncated = 0 2.37.338.553 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.857 2.37.338.614 I slot launch_slot_: id 0 | task 1301 | processing task, is_child = 0 2.37.338.736 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.403 MiB) 2.37.338.743 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.169 MiB) 2.37.338.744 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.051 MiB) 2.37.364.781 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.859 2.37.364.825 I slot launch_slot_: id 1 | task 1302 | processing task, is_child = 0 2.38.146.387 I slot print_timing: id 2 | task 1201 | n_gen = 100, tg = 16.48 t/s, tg_3s = 16.65 t/s 2.39.531.151 I slot print_timing: id 3 | task 1233 | prompt eval time = 500.68 ms / 131 tokens ( 3.82 ms per token, 261.64 tokens per second) 2.39.531.154 I slot print_timing: id 3 | task 1233 | eval time = 5444.30 ms / 97 tokens ( 56.71 ms per token, 17.63 tokens per second) 2.39.531.154 I slot print_timing: id 3 | task 1233 | total time = 5944.98 ms / 228 tokens 2.39.531.155 I slot print_timing: id 3 | task 1233 | graphs reused = 905 2.39.531.155 I slot print_timing: id 3 | task 1233 | graph reallocs = 0 / 0 (same size) / (changed size) 2.39.531.207 I slot release: id 3 | task 1233 | stop processing: n_tokens = 1352, truncated = 0 2.39.575.757 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.848 2.39.575.794 I slot launch_slot_: id 3 | task 1335 | processing task, is_child = 0 2.41.185.512 I slot print_timing: id 2 | task 1201 | prompt eval time = 549.47 ms / 149 tokens ( 3.69 ms per token, 271.17 tokens per second) 2.41.185.517 I slot print_timing: id 2 | task 1201 | eval time = 9044.73 ms / 153 tokens ( 59.50 ms per token, 16.81 tokens per second) 2.41.185.517 I slot print_timing: id 2 | task 1201 | total time = 9594.20 ms / 302 tokens 2.41.185.518 I slot print_timing: id 2 | task 1201 | graphs reused = 926 2.41.185.518 I slot print_timing: id 2 | task 1201 | graph reallocs = 0 / 0 (same size) / (changed size) 2.41.185.564 I slot release: id 2 | task 1201 | stop processing: n_tokens = 1426, truncated = 0 2.41.242.541 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.804 2.41.242.577 I slot launch_slot_: id 2 | task 1361 | processing task, is_child = 0 2.42.795.748 I slot print_timing: id 0 | task 1301 | prompt eval time = 729.78 ms / 117 tokens ( 6.24 ms per token, 160.32 tokens per second) 2.42.795.753 I slot print_timing: id 0 | task 1301 | eval time = 4701.13 ms / 80 tokens ( 59.51 ms per token, 16.80 tokens per second) 2.42.795.754 I slot print_timing: id 0 | task 1301 | total time = 5430.91 ms / 197 tokens 2.42.795.754 I slot print_timing: id 0 | task 1301 | graphs reused = 947 2.42.795.755 I slot print_timing: id 0 | task 1301 | graph reallocs = 0 / 0 (same size) / (changed size) 2.42.795.812 I slot release: id 0 | task 1301 | stop processing: n_tokens = 1321, truncated = 0 2.42.839.968 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.868 2.42.840.003 I slot launch_slot_: id 0 | task 1387 | processing task, is_child = 0 2.44.141.825 I slot print_timing: id 1 | task 1302 | n_gen = 100, tg = 16.37 t/s, tg_3s = 16.54 t/s 2.45.738.706 I slot print_timing: id 3 | task 1335 | n_gen = 100, tg = 17.54 t/s, tg_3s = 17.72 t/s 2.46.494.085 I slot print_timing: id 2 | task 1361 | prompt eval time = 465.14 ms / 96 tokens ( 4.85 ms per token, 206.39 tokens per second) 2.46.494.091 I slot print_timing: id 2 | task 1361 | eval time = 4786.35 ms / 90 tokens ( 53.78 ms per token, 18.59 tokens per second) 2.46.494.094 I slot print_timing: id 2 | task 1361 | total time = 5251.49 ms / 186 tokens 2.46.494.095 I slot print_timing: id 2 | task 1361 | graphs reused = 1011 2.46.494.096 I slot print_timing: id 2 | task 1361 | graph reallocs = 0 / 0 (same size) / (changed size) 2.46.494.217 I slot release: id 2 | task 1361 | stop processing: n_tokens = 1310, truncated = 0 2.46.556.395 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.875 2.46.556.478 I slot launch_slot_: id 2 | task 1455 | processing task, is_child = 0 2.47.079.587 I slot print_timing: id 0 | task 1387 | prompt eval time = 460.04 ms / 104 tokens ( 4.42 ms per token, 226.07 tokens per second) 2.47.079.592 I slot print_timing: id 0 | task 1387 | eval time = 3779.53 ms / 69 tokens ( 55.58 ms per token, 17.99 tokens per second) 2.47.079.593 I slot print_timing: id 0 | task 1387 | total time = 4239.57 ms / 173 tokens 2.47.079.593 I slot print_timing: id 0 | task 1387 | graphs reused = 1011 2.47.079.594 I slot print_timing: id 0 | task 1387 | graph reallocs = 0 / 0 (same size) / (changed size) 2.47.079.641 I slot release: id 0 | task 1387 | stop processing: n_tokens = 1297, truncated = 0 2.47.123.918 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.884 2.47.123.955 I slot launch_slot_: id 0 | task 1460 | processing task, is_child = 0 2.47.492.928 I slot print_timing: id 1 | task 1302 | n_gen = 153, tg = 16.17 t/s, tg_3s = 15.82 t/s 2.48.743.382 I slot print_timing: id 3 | task 1335 | n_gen = 145, tg = 16.65 t/s, tg_3s = 14.98 t/s 2.49.498.583 I slot print_timing: id 3 | task 1335 | prompt eval time = 519.96 ms / 137 tokens ( 3.80 ms per token, 263.48 tokens per second) 2.49.498.591 I slot print_timing: id 3 | task 1335 | eval time = 9402.82 ms / 160 tokens ( 59.14 ms per token, 16.91 tokens per second) 2.49.498.592 I slot print_timing: id 3 | task 1335 | total time = 9922.78 ms / 297 tokens 2.49.498.593 I slot print_timing: id 3 | task 1335 | graphs reused = 1049 2.49.498.594 I slot print_timing: id 3 | task 1335 | graph reallocs = 0 / 0 (same size) / (changed size) 2.49.498.693 I slot release: id 3 | task 1335 | stop processing: n_tokens = 1421, truncated = 0 2.49.546.038 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.806 2.49.546.102 I slot launch_slot_: id 3 | task 1502 | processing task, is_child = 0 2.50.520.358 I slot print_timing: id 1 | task 1302 | n_gen = 205, tg = 16.42 t/s, tg_3s = 17.18 t/s 2.51.311.506 I slot print_timing: id 0 | task 1460 | prompt eval time = 455.99 ms / 102 tokens ( 4.47 ms per token, 223.69 tokens per second) 2.51.311.511 I slot print_timing: id 0 | task 1460 | eval time = 3731.56 ms / 68 tokens ( 55.69 ms per token, 17.95 tokens per second) 2.51.311.513 I slot print_timing: id 0 | task 1460 | total time = 4187.55 ms / 170 tokens 2.51.311.513 I slot print_timing: id 0 | task 1460 | graphs reused = 1074 2.51.311.514 I slot print_timing: id 0 | task 1460 | graph reallocs = 0 / 0 (same size) / (changed size) 2.51.311.558 I slot release: id 0 | task 1460 | stop processing: n_tokens = 1294, truncated = 0 2.51.356.076 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.886 2.51.356.117 I slot launch_slot_: id 0 | task 1532 | processing task, is_child = 0 2.51.981.892 I slot print_timing: id 2 | task 1455 | prompt eval time = 472.00 ms / 98 tokens ( 4.82 ms per token, 207.63 tokens per second) 2.51.981.897 I slot print_timing: id 2 | task 1455 | eval time = 4953.40 ms / 78 tokens ( 64.33 ms per token, 15.54 tokens per second) 2.51.981.898 I slot print_timing: id 2 | task 1455 | total time = 5425.40 ms / 176 tokens 2.51.981.898 I slot print_timing: id 2 | task 1455 | graphs reused = 1077 2.51.981.899 I slot print_timing: id 2 | task 1455 | graph reallocs = 0 / 0 (same size) / (changed size) 2.51.981.945 I slot release: id 2 | task 1455 | stop processing: n_tokens = 1300, truncated = 0 2.52.038.705 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.918 (> 0.100 thold), f_keep = 0.882 2.52.038.740 I slot launch_slot_: id 2 | task 1539 | processing task, is_child = 0 2.53.547.299 I slot print_timing: id 1 | task 1302 | n_gen = 250, tg = 16.11 t/s, tg_3s = 14.87 t/s 2.55.747.389 I slot print_timing: id 3 | task 1502 | n_gen = 100, tg = 17.30 t/s, tg_3s = 17.47 t/s 2.55.999.848 I slot print_timing: id 3 | task 1502 | prompt eval time = 478.31 ms / 108 tokens ( 4.43 ms per token, 225.79 tokens per second) 2.55.999.854 I slot print_timing: id 3 | task 1502 | eval time = 5975.42 ms / 105 tokens ( 57.46 ms per token, 17.40 tokens per second) 2.55.999.855 I slot print_timing: id 3 | task 1502 | total time = 6453.73 ms / 213 tokens 2.55.999.856 I slot print_timing: id 3 | task 1502 | graphs reused = 1144 2.55.999.857 I slot print_timing: id 3 | task 1502 | graph reallocs = 0 / 0 (same size) / (changed size) 2.55.999.975 I slot release: id 3 | task 1502 | stop processing: n_tokens = 1337, truncated = 0 2.56.047.267 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.857 2.56.047.331 I slot launch_slot_: id 3 | task 1612 | processing task, is_child = 0 2.56.580.208 I slot print_timing: id 1 | task 1302 | n_gen = 303, tg = 16.34 t/s, tg_3s = 17.47 t/s 2.57.075.064 I slot print_timing: id 2 | task 1539 | prompt eval time = 518.57 ms / 124 tokens ( 4.18 ms per token, 239.12 tokens per second) 2.57.075.067 I slot print_timing: id 2 | task 1539 | eval time = 4517.75 ms / 84 tokens ( 54.43 ms per token, 18.37 tokens per second) 2.57.075.067 I slot print_timing: id 2 | task 1539 | total time = 5036.32 ms / 208 tokens 2.57.075.068 I slot print_timing: id 2 | task 1539 | graphs reused = 1154 2.57.075.068 I slot print_timing: id 2 | task 1539 | graph reallocs = 0 / 0 (same size) / (changed size) 2.57.075.113 I slot release: id 2 | task 1539 | stop processing: n_tokens = 1332, truncated = 0 2.57.131.805 I slot print_timing: id 0 | task 1532 | prompt eval time = 475.20 ms / 122 tokens ( 3.90 ms per token, 256.73 tokens per second) 2.57.131.810 I slot print_timing: id 0 | task 1532 | eval time = 5300.48 ms / 91 tokens ( 58.89 ms per token, 16.98 tokens per second) 2.57.131.810 I slot print_timing: id 0 | task 1532 | total time = 5775.68 ms / 213 tokens 2.57.131.810 I slot print_timing: id 0 | task 1532 | graphs reused = 1154 2.57.131.811 I slot print_timing: id 0 | task 1532 | graph reallocs = 0 / 0 (same size) / (changed size) 2.57.131.863 I slot release: id 0 | task 1532 | stop processing: n_tokens = 1337, truncated = 0 2.57.132.173 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.857 2.57.132.206 I slot launch_slot_: id 0 | task 1627 | processing task, is_child = 0 2.57.132.277 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.794 MiB) 2.57.132.281 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.403 MiB) 2.57.132.282 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.658 MiB) 2.57.149.557 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.931 (> 0.100 thold), f_keep = 0.860 2.57.149.589 I slot launch_slot_: id 2 | task 1628 | processing task, is_child = 0 2.59.585.348 I slot print_timing: id 1 | task 1302 | n_gen = 348, tg = 16.15 t/s, tg_3s = 14.97 t/s 3.00.747.555 I slot print_timing: id 0 | task 1627 | prompt eval time = 811.97 ms / 86 tokens ( 9.44 ms per token, 105.92 tokens per second) 3.00.747.560 I slot print_timing: id 0 | task 1627 | eval time = 2785.99 ms / 56 tokens ( 50.65 ms per token, 19.74 tokens per second) 3.00.747.562 I slot print_timing: id 0 | task 1627 | total time = 3597.95 ms / 142 tokens 3.00.747.563 I slot print_timing: id 0 | task 1627 | graphs reused = 1208 3.00.747.564 I slot print_timing: id 0 | task 1627 | graph reallocs = 0 / 0 (same size) / (changed size) 3.00.747.649 I slot release: id 0 | task 1627 | stop processing: n_tokens = 1266, truncated = 0 3.00.796.181 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.905 3.00.796.246 I slot launch_slot_: id 0 | task 1687 | processing task, is_child = 0 3.02.566.588 I slot print_timing: id 3 | task 1612 | n_gen = 100, tg = 16.40 t/s, tg_3s = 16.56 t/s 3.02.615.860 I slot print_timing: id 1 | task 1302 | n_gen = 402, tg = 16.35 t/s, tg_3s = 17.82 t/s 3.03.259.033 I slot print_timing: id 2 | task 1628 | n_gen = 100, tg = 18.69 t/s, tg_3s = 18.88 t/s 3.03.754.325 I slot print_timing: id 2 | task 1628 | prompt eval time = 809.28 ms / 106 tokens ( 7.63 ms per token, 130.98 tokens per second) 3.03.754.329 I slot print_timing: id 2 | task 1628 | eval time = 5792.21 ms / 110 tokens ( 53.14 ms per token, 18.82 tokens per second) 3.03.754.330 I slot print_timing: id 2 | task 1628 | total time = 6601.49 ms / 216 tokens 3.03.754.330 I slot print_timing: id 2 | task 1628 | graphs reused = 1259 3.03.754.331 I slot print_timing: id 2 | task 1628 | graph reallocs = 0 / 0 (same size) / (changed size) 3.03.754.378 I slot release: id 2 | task 1628 | stop processing: n_tokens = 1340, truncated = 0 3.03.810.845 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.942 (> 0.100 thold), f_keep = 0.855 3.03.810.885 I slot launch_slot_: id 2 | task 1742 | processing task, is_child = 0 3.04.963.401 I slot print_timing: id 3 | task 1612 | prompt eval time = 481.55 ms / 111 tokens ( 4.34 ms per token, 230.51 tokens per second) 3.04.963.407 I slot print_timing: id 3 | task 1612 | eval time = 8434.51 ms / 141 tokens ( 60.25 ms per token, 16.60 tokens per second) 3.04.963.407 I slot print_timing: id 3 | task 1612 | total time = 8916.06 ms / 252 tokens 3.04.963.408 I slot print_timing: id 3 | task 1612 | graphs reused = 1272 3.04.963.408 I slot print_timing: id 3 | task 1612 | graph reallocs = 0 / 0 (same size) / (changed size) 3.04.963.456 I slot release: id 3 | task 1612 | stop processing: n_tokens = 1376, truncated = 0 3.05.007.876 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.833 3.05.007.908 I slot launch_slot_: id 3 | task 1760 | processing task, is_child = 0 3.05.652.623 I slot print_timing: id 1 | task 1302 | n_gen = 448, tg = 16.22 t/s, tg_3s = 15.15 t/s 3.06.147.465 I slot print_timing: id 0 | task 1687 | prompt eval time = 431.85 ms / 98 tokens ( 4.41 ms per token, 226.93 tokens per second) 3.06.147.467 I slot print_timing: id 0 | task 1687 | eval time = 4919.36 ms / 85 tokens ( 58.56 ms per token, 17.08 tokens per second) 3.06.147.468 I slot print_timing: id 0 | task 1687 | total time = 5351.21 ms / 183 tokens 3.06.147.468 I slot print_timing: id 0 | task 1687 | graphs reused = 1284 3.06.147.468 I slot print_timing: id 0 | task 1687 | graph reallocs = 0 / 0 (same size) / (changed size) 3.06.147.522 I slot release: id 0 | task 1687 | stop processing: n_tokens = 1307, truncated = 0 3.06.192.039 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.877 3.06.192.074 I slot launch_slot_: id 0 | task 1777 | processing task, is_child = 0 3.08.615.490 I slot print_timing: id 3 | task 1760 | prompt eval time = 494.25 ms / 121 tokens ( 4.08 ms per token, 244.81 tokens per second) 3.08.615.498 I slot print_timing: id 3 | task 1760 | eval time = 3113.32 ms / 56 tokens ( 56.61 ms per token, 17.67 tokens per second) 3.08.615.499 I slot print_timing: id 3 | task 1760 | total time = 3607.57 ms / 177 tokens 3.08.615.500 I slot print_timing: id 3 | task 1760 | graphs reused = 1323 3.08.615.501 I slot print_timing: id 3 | task 1760 | graph reallocs = 0 / 0 (same size) / (changed size) 3.08.615.607 I slot release: id 3 | task 1760 | stop processing: n_tokens = 1301, truncated = 0 3.08.662.623 I slot print_timing: id 1 | task 1302 | n_gen = 501, tg = 16.36 t/s, tg_3s = 17.61 t/s 3.08.662.931 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.881 3.08.662.999 I slot launch_slot_: id 3 | task 1820 | processing task, is_child = 0 3.10.065.871 I slot print_timing: id 2 | task 1742 | prompt eval time = 457.66 ms / 91 tokens ( 5.03 ms per token, 198.84 tokens per second) 3.10.065.877 I slot print_timing: id 2 | task 1742 | eval time = 5797.32 ms / 95 tokens ( 61.67 ms per token, 16.21 tokens per second) 3.10.065.878 I slot print_timing: id 2 | task 1742 | total time = 6254.97 ms / 186 tokens 3.10.065.879 I slot print_timing: id 2 | task 1742 | graphs reused = 1341 3.10.065.880 I slot print_timing: id 2 | task 1742 | graph reallocs = 0 / 0 (same size) / (changed size) 3.10.065.968 I slot release: id 2 | task 1742 | stop processing: n_tokens = 1310, truncated = 0 3.10.127.341 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.875 3.10.127.403 I slot launch_slot_: id 2 | task 1843 | processing task, is_child = 0 3.10.933.666 I slot print_timing: id 0 | task 1777 | prompt eval time = 463.73 ms / 105 tokens ( 4.42 ms per token, 226.43 tokens per second) 3.10.933.669 I slot print_timing: id 0 | task 1777 | eval time = 4277.86 ms / 70 tokens ( 62.00 ms per token, 16.13 tokens per second) 3.10.933.670 I slot print_timing: id 0 | task 1777 | total time = 4741.58 ms / 175 tokens 3.10.933.670 I slot print_timing: id 0 | task 1777 | graphs reused = 1345 3.10.933.671 I slot print_timing: id 0 | task 1777 | graph reallocs = 0 / 0 (same size) / (changed size) 3.10.933.721 I slot release: id 0 | task 1777 | stop processing: n_tokens = 1299, truncated = 0 3.10.979.436 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.882 3.10.979.507 I slot launch_slot_: id 0 | task 1852 | processing task, is_child = 0 3.11.696.064 I slot print_timing: id 1 | task 1302 | n_gen = 538, tg = 15.98 t/s, tg_3s = 12.20 t/s 3.13.842.048 I slot print_timing: id 3 | task 1820 | prompt eval time = 440.19 ms / 95 tokens ( 4.63 ms per token, 215.81 tokens per second) 3.13.842.055 I slot print_timing: id 3 | task 1820 | eval time = 4738.84 ms / 79 tokens ( 60.75 ms per token, 16.46 tokens per second) 3.13.842.056 I slot print_timing: id 3 | task 1820 | total time = 5179.03 ms / 174 tokens 3.13.842.058 I slot print_timing: id 3 | task 1820 | graphs reused = 1392 3.13.842.059 I slot print_timing: id 3 | task 1820 | graph reallocs = 0 / 0 (same size) / (changed size) 3.13.842.178 I slot release: id 3 | task 1820 | stop processing: n_tokens = 1298, truncated = 0 3.13.889.970 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.893 (> 0.100 thold), f_keep = 0.883 3.13.890.035 I slot launch_slot_: id 3 | task 1904 | processing task, is_child = 0 3.14.729.514 I slot print_timing: id 1 | task 1302 | n_gen = 590, tg = 16.08 t/s, tg_3s = 17.14 t/s 3.15.331.290 I slot print_timing: id 0 | task 1852 | prompt eval time = 466.46 ms / 110 tokens ( 4.24 ms per token, 235.82 tokens per second) 3.15.331.300 I slot print_timing: id 0 | task 1852 | eval time = 3885.30 ms / 70 tokens ( 56.31 ms per token, 17.76 tokens per second) 3.15.331.301 I slot print_timing: id 0 | task 1852 | total time = 4351.77 ms / 180 tokens 3.15.331.302 I slot print_timing: id 0 | task 1852 | graphs reused = 1409 3.15.331.303 I slot print_timing: id 0 | task 1852 | graph reallocs = 0 / 0 (same size) / (changed size) 3.15.331.406 I slot release: id 0 | task 1852 | stop processing: n_tokens = 1304, truncated = 0 3.15.380.034 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.924 (> 0.100 thold), f_keep = 0.879 3.15.380.099 I slot launch_slot_: id 0 | task 1926 | processing task, is_child = 0 3.16.595.949 I slot print_timing: id 1 | task 1302 | prompt eval time = 725.63 ms / 127 tokens ( 5.71 ms per token, 175.02 tokens per second) 3.16.595.952 I slot print_timing: id 1 | task 1302 | eval time = 38501.13 ms / 620 tokens ( 62.20 ms per token, 16.08 tokens per second) 3.16.595.952 I slot print_timing: id 1 | task 1302 | total time = 39226.76 ms / 747 tokens 3.16.595.953 I slot print_timing: id 1 | task 1302 | graphs reused = 1424 3.16.595.953 I slot print_timing: id 1 | task 1302 | graph reallocs = 0 / 0 (same size) / (changed size) 3.16.596.003 I slot release: id 1 | task 1302 | stop processing: n_tokens = 1871, truncated = 0 3.16.653.499 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.613 3.16.653.532 I slot launch_slot_: id 1 | task 1945 | processing task, is_child = 0 3.17.237.725 I slot print_timing: id 2 | task 1843 | n_gen = 100, tg = 15.10 t/s, tg_3s = 15.25 t/s 3.19.956.143 I slot print_timing: id 0 | task 1926 | prompt eval time = 470.11 ms / 115 tokens ( 4.09 ms per token, 244.62 tokens per second) 3.19.956.147 I slot print_timing: id 0 | task 1926 | eval time = 4105.92 ms / 75 tokens ( 55.49 ms per token, 18.02 tokens per second) 3.19.956.147 I slot print_timing: id 0 | task 1926 | total time = 4576.03 ms / 190 tokens 3.19.956.147 I slot print_timing: id 0 | task 1926 | graphs reused = 1479 3.19.956.148 I slot print_timing: id 0 | task 1926 | graph reallocs = 0 / 0 (same size) / (changed size) 3.19.956.191 I slot release: id 0 | task 1926 | stop processing: n_tokens = 1314, truncated = 0 3.19.956.479 I slot print_timing: id 2 | task 1843 | prompt eval time = 552.24 ms / 144 tokens ( 3.84 ms per token, 260.76 tokens per second) 3.19.956.481 I slot print_timing: id 2 | task 1843 | eval time = 9276.83 ms / 155 tokens ( 60.24 ms per token, 16.60 tokens per second) 3.19.956.482 I slot print_timing: id 2 | task 1843 | total time = 9829.07 ms / 299 tokens 3.19.956.482 I slot print_timing: id 2 | task 1843 | graphs reused = 1479 3.19.956.483 I slot print_timing: id 2 | task 1843 | graph reallocs = 0 / 0 (same size) / (changed size) 3.19.956.522 I slot release: id 2 | task 1843 | stop processing: n_tokens = 1423, truncated = 0 3.20.000.849 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 3.20.000.882 I slot launch_slot_: id 0 | task 2005 | processing task, is_child = 0 3.20.000.967 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.853 MiB) 3.20.000.970 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.325 MiB) 3.20.021.188 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.805 3.20.021.228 I slot launch_slot_: id 2 | task 2006 | processing task, is_child = 0 3.20.871.971 I slot print_timing: id 3 | task 1904 | n_gen = 100, tg = 15.37 t/s, tg_3s = 15.53 t/s 3.22.842.482 I slot print_timing: id 1 | task 1945 | n_gen = 100, tg = 17.50 t/s, tg_3s = 17.68 t/s 3.23.095.776 I slot print_timing: id 3 | task 1904 | prompt eval time = 540.78 ms / 158 tokens ( 3.42 ms per token, 292.17 tokens per second) 3.23.095.782 I slot print_timing: id 3 | task 1904 | eval time = 8664.95 ms / 144 tokens ( 60.59 ms per token, 16.50 tokens per second) 3.23.095.783 I slot print_timing: id 3 | task 1904 | total time = 9205.73 ms / 302 tokens 3.23.095.784 I slot print_timing: id 3 | task 1904 | graphs reused = 1523 3.23.095.785 I slot print_timing: id 3 | task 1904 | graph reallocs = 0 / 0 (same size) / (changed size) 3.23.095.894 I slot release: id 3 | task 1904 | stop processing: n_tokens = 1426, truncated = 0 3.23.142.919 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.804 3.23.142.988 I slot launch_slot_: id 3 | task 2055 | processing task, is_child = 0 3.23.987.034 I slot print_timing: id 2 | task 2006 | prompt eval time = 794.05 ms / 104 tokens ( 7.64 ms per token, 130.97 tokens per second) 3.23.987.038 I slot print_timing: id 2 | task 2006 | eval time = 3168.48 ms / 56 tokens ( 57.61 ms per token, 17.36 tokens per second) 3.23.987.038 I slot print_timing: id 2 | task 2006 | total time = 3962.54 ms / 160 tokens 3.23.987.039 I slot print_timing: id 2 | task 2006 | graphs reused = 1529 3.23.987.039 I slot print_timing: id 2 | task 2006 | graph reallocs = 0 / 0 (same size) / (changed size) 3.23.987.084 I slot release: id 2 | task 2006 | stop processing: n_tokens = 1284, truncated = 0 3.24.043.625 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.893 3.24.043.660 I slot launch_slot_: id 2 | task 2066 | processing task, is_child = 0 3.24.535.683 I slot print_timing: id 0 | task 2005 | prompt eval time = 796.79 ms / 81 tokens ( 9.84 ms per token, 101.66 tokens per second) 3.24.535.688 I slot print_timing: id 0 | task 2005 | eval time = 3717.65 ms / 59 tokens ( 64.10 ms per token, 15.60 tokens per second) 3.24.535.689 I slot print_timing: id 0 | task 2005 | total time = 4514.44 ms / 140 tokens 3.24.535.689 I slot print_timing: id 0 | task 2005 | graphs reused = 1529 3.24.535.690 I slot print_timing: id 0 | task 2005 | graph reallocs = 0 / 0 (same size) / (changed size) 3.24.535.732 I slot release: id 0 | task 2005 | stop processing: n_tokens = 1264, truncated = 0 3.24.580.145 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.916 (> 0.100 thold), f_keep = 0.907 3.24.580.180 I slot launch_slot_: id 0 | task 2070 | processing task, is_child = 0 3.25.855.634 I slot print_timing: id 1 | task 1945 | n_gen = 137, tg = 15.69 t/s, tg_3s = 12.28 t/s 3.27.290.139 I slot print_timing: id 3 | task 2055 | prompt eval time = 497.14 ms / 125 tokens ( 3.98 ms per token, 251.44 tokens per second) 3.27.290.142 I slot print_timing: id 3 | task 2055 | eval time = 3650.00 ms / 59 tokens ( 62.93 ms per token, 15.89 tokens per second) 3.27.290.142 I slot print_timing: id 3 | task 2055 | total time = 4147.14 ms / 184 tokens 3.27.290.143 I slot print_timing: id 3 | task 2055 | graphs reused = 1574 3.27.290.143 I slot print_timing: id 3 | task 2055 | graph reallocs = 0 / 0 (same size) / (changed size) 3.27.290.204 I slot release: id 3 | task 2055 | stop processing: n_tokens = 1308, truncated = 0 3.27.334.337 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.876 3.27.334.372 I slot launch_slot_: id 3 | task 2119 | processing task, is_child = 0 3.28.888.303 I slot print_timing: id 1 | task 1945 | n_gen = 190, tg = 16.15 t/s, tg_3s = 17.48 t/s 3.29.341.701 I slot print_timing: id 1 | task 1945 | prompt eval time = 532.52 ms / 128 tokens ( 4.16 ms per token, 240.37 tokens per second) 3.29.341.707 I slot print_timing: id 1 | task 1945 | eval time = 12155.64 ms / 199 tokens ( 61.39 ms per token, 16.29 tokens per second) 3.29.341.708 I slot print_timing: id 1 | task 1945 | total time = 12688.16 ms / 327 tokens 3.29.341.709 I slot print_timing: id 1 | task 1945 | graphs reused = 1603 3.29.341.710 I slot print_timing: id 1 | task 1945 | graph reallocs = 0 / 0 (same size) / (changed size) 3.29.341.799 I slot release: id 1 | task 1945 | stop processing: n_tokens = 1451, truncated = 0 3.29.402.886 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.792 3.29.402.945 I slot launch_slot_: id 1 | task 2153 | processing task, is_child = 0 3.30.160.523 I slot print_timing: id 0 | task 2070 | prompt eval time = 483.99 ms / 126 tokens ( 3.84 ms per token, 260.34 tokens per second) 3.30.160.526 I slot print_timing: id 0 | task 2070 | eval time = 5096.35 ms / 87 tokens ( 59.26 ms per token, 16.87 tokens per second) 3.30.160.526 I slot print_timing: id 0 | task 2070 | total time = 5580.34 ms / 213 tokens 3.30.160.527 I slot print_timing: id 0 | task 2070 | graphs reused = 1607 3.30.160.527 I slot print_timing: id 0 | task 2070 | graph reallocs = 0 / 0 (same size) / (changed size) 3.30.160.577 I slot release: id 0 | task 2070 | stop processing: n_tokens = 1337, truncated = 0 3.30.205.027 I slot print_timing: id 2 | task 2066 | prompt eval time = 492.51 ms / 103 tokens ( 4.78 ms per token, 209.13 tokens per second) 3.30.205.032 I slot print_timing: id 2 | task 2066 | eval time = 5668.85 ms / 91 tokens ( 62.99 ms per token, 15.88 tokens per second) 3.30.205.033 I slot print_timing: id 2 | task 2066 | total time = 6161.36 ms / 194 tokens 3.30.205.033 I slot print_timing: id 2 | task 2066 | graphs reused = 1607 3.30.205.033 I slot print_timing: id 2 | task 2066 | graph reallocs = 0 / 0 (same size) / (changed size) 3.30.205.076 I slot release: id 2 | task 2066 | stop processing: n_tokens = 1318, truncated = 0 3.30.205.243 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 3.30.205.275 I slot launch_slot_: id 0 | task 2162 | processing task, is_child = 0 3.30.205.344 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.797 MiB) 3.30.205.347 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.540 MiB) 3.30.205.348 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.188 MiB) 3.30.224.124 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.869 3.30.224.165 I slot launch_slot_: id 2 | task 2163 | processing task, is_child = 0 3.34.082.891 I slot print_timing: id 3 | task 2119 | n_gen = 100, tg = 15.82 t/s, tg_3s = 15.98 t/s 3.34.435.316 I slot print_timing: id 2 | task 2163 | prompt eval time = 917.76 ms / 171 tokens ( 5.37 ms per token, 186.32 tokens per second) 3.34.435.324 I slot print_timing: id 2 | task 2163 | eval time = 3289.89 ms / 66 tokens ( 50.61 ms per token, 19.76 tokens per second) 3.34.435.325 I slot print_timing: id 2 | task 2163 | total time = 4207.65 ms / 237 tokens 3.34.435.326 I slot print_timing: id 2 | task 2163 | graphs reused = 1671 3.34.435.328 I slot print_timing: id 2 | task 2163 | graph reallocs = 0 / 0 (same size) / (changed size) 3.34.435.419 I slot release: id 2 | task 2163 | stop processing: n_tokens = 1361, truncated = 0 3.34.497.747 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.944 (> 0.100 thold), f_keep = 0.842 3.34.497.802 I slot launch_slot_: id 2 | task 2232 | processing task, is_child = 0 3.35.415.139 I slot print_timing: id 1 | task 2153 | prompt eval time = 508.72 ms / 108 tokens ( 4.71 ms per token, 212.30 tokens per second) 3.35.415.146 I slot print_timing: id 1 | task 2153 | eval time = 5503.47 ms / 86 tokens ( 64.75 ms per token, 15.44 tokens per second) 3.35.415.147 I slot print_timing: id 1 | task 2153 | total time = 6012.18 ms / 194 tokens 3.35.415.148 I slot print_timing: id 1 | task 2153 | graphs reused = 1679 3.35.415.149 I slot print_timing: id 1 | task 2153 | graph reallocs = 0 / 0 (same size) / (changed size) 3.35.415.240 I slot release: id 1 | task 2153 | stop processing: n_tokens = 1318, truncated = 0 3.35.476.627 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.949 (> 0.100 thold), f_keep = 0.869 3.35.476.709 I slot launch_slot_: id 1 | task 2245 | processing task, is_child = 0 3.35.988.240 I slot print_timing: id 0 | task 2162 | prompt eval time = 920.76 ms / 100 tokens ( 9.21 ms per token, 108.61 tokens per second) 3.35.988.242 I slot print_timing: id 0 | task 2162 | eval time = 4843.30 ms / 82 tokens ( 59.79 ms per token, 16.72 tokens per second) 3.35.988.243 I slot print_timing: id 0 | task 2162 | total time = 5764.07 ms / 182 tokens 3.35.988.244 I slot print_timing: id 0 | task 2162 | graphs reused = 1679 3.35.988.244 I slot print_timing: id 0 | task 2162 | graph reallocs = 0 / 0 (same size) / (changed size) 3.35.988.294 I slot release: id 0 | task 2162 | stop processing: n_tokens = 1306, truncated = 0 3.36.032.773 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.877 3.36.032.803 I slot launch_slot_: id 0 | task 2250 | processing task, is_child = 0 3.37.095.469 I slot print_timing: id 3 | task 2119 | n_gen = 138, tg = 14.78 t/s, tg_3s = 12.61 t/s 3.38.305.685 I slot print_timing: id 3 | task 2119 | prompt eval time = 491.55 ms / 125 tokens ( 3.93 ms per token, 254.30 tokens per second) 3.38.305.693 I slot print_timing: id 3 | task 2119 | eval time = 10479.75 ms / 162 tokens ( 65.09 ms per token, 15.36 tokens per second) 3.38.305.695 I slot print_timing: id 3 | task 2119 | total time = 10971.30 ms / 287 tokens 3.38.305.696 I slot print_timing: id 3 | task 2119 | graphs reused = 1715 3.38.305.697 I slot print_timing: id 3 | task 2119 | graph reallocs = 0 / 0 (same size) / (changed size) 3.38.305.816 I slot release: id 3 | task 2119 | stop processing: n_tokens = 1411, truncated = 0 3.38.353.463 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.812 3.38.353.523 I slot launch_slot_: id 3 | task 2290 | processing task, is_child = 0 3.39.246.763 I slot print_timing: id 0 | task 2250 | prompt eval time = 467.79 ms / 114 tokens ( 4.10 ms per token, 243.70 tokens per second) 3.39.246.768 I slot print_timing: id 0 | task 2250 | eval time = 2746.16 ms / 49 tokens ( 57.21 ms per token, 17.48 tokens per second) 3.39.246.769 I slot print_timing: id 0 | task 2250 | total time = 3213.95 ms / 163 tokens 3.39.246.769 I slot print_timing: id 0 | task 2250 | graphs reused = 1722 3.39.246.769 I slot print_timing: id 0 | task 2250 | graph reallocs = 0 / 0 (same size) / (changed size) 3.39.246.818 I slot release: id 0 | task 2250 | stop processing: n_tokens = 1287, truncated = 0 3.39.291.694 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.890 3.39.291.726 I slot launch_slot_: id 0 | task 2303 | processing task, is_child = 0 3.39.666.376 I slot print_timing: id 2 | task 2232 | prompt eval time = 458.85 ms / 89 tokens ( 5.16 ms per token, 193.96 tokens per second) 3.39.666.379 I slot print_timing: id 2 | task 2232 | eval time = 4709.72 ms / 67 tokens ( 71.36 ms per token, 14.01 tokens per second) 3.39.666.380 I slot print_timing: id 2 | task 2232 | total time = 5168.57 ms / 156 tokens 3.39.666.380 I slot print_timing: id 2 | task 2232 | graphs reused = 1723 3.39.666.381 I slot print_timing: id 2 | task 2232 | graph reallocs = 0 / 0 (same size) / (changed size) 3.39.666.425 I slot release: id 2 | task 2232 | stop processing: n_tokens = 1280, truncated = 0 3.39.752.786 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.895 3.39.752.820 I slot launch_slot_: id 2 | task 2306 | processing task, is_child = 0 3.40.116.919 I slot print_timing: id 1 | task 2245 | prompt eval time = 460.30 ms / 82 tokens ( 5.61 ms per token, 178.15 tokens per second) 3.40.116.925 I slot print_timing: id 1 | task 2245 | eval time = 4179.90 ms / 57 tokens ( 74.64 ms per token, 13.40 tokens per second) 3.40.116.925 I slot print_timing: id 1 | task 2245 | total time = 4640.20 ms / 139 tokens 3.40.116.926 I slot print_timing: id 1 | task 2245 | graphs reused = 1723 3.40.116.926 I slot print_timing: id 1 | task 2245 | graph reallocs = 0 / 0 (same size) / (changed size) 3.40.116.976 I slot release: id 1 | task 2245 | stop processing: n_tokens = 1263, truncated = 0 3.40.203.407 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.907 3.40.203.439 I slot launch_slot_: id 1 | task 2309 | processing task, is_child = 0 3.43.138.373 I slot print_timing: id 3 | task 2290 | prompt eval time = 444.89 ms / 98 tokens ( 4.54 ms per token, 220.28 tokens per second) 3.43.138.375 I slot print_timing: id 3 | task 2290 | eval time = 4339.95 ms / 66 tokens ( 66.77 ms per token, 14.98 tokens per second) 3.43.138.376 I slot print_timing: id 3 | task 2290 | total time = 4784.84 ms / 164 tokens 3.43.138.376 I slot print_timing: id 3 | task 2290 | graphs reused = 1770 3.43.138.377 I slot print_timing: id 3 | task 2290 | graph reallocs = 0 / 0 (same size) / (changed size) 3.43.138.421 I slot release: id 3 | task 2290 | stop processing: n_tokens = 1288, truncated = 0 3.43.182.570 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 3.43.182.602 I slot launch_slot_: id 3 | task 2362 | processing task, is_child = 0 3.44.556.701 I slot print_timing: id 2 | task 2306 | prompt eval time = 450.43 ms / 97 tokens ( 4.64 ms per token, 215.35 tokens per second) 3.44.556.706 I slot print_timing: id 2 | task 2306 | eval time = 4353.44 ms / 73 tokens ( 60.46 ms per token, 16.54 tokens per second) 3.44.556.707 I slot print_timing: id 2 | task 2306 | total time = 4803.87 ms / 170 tokens 3.44.556.707 I slot print_timing: id 2 | task 2306 | graphs reused = 1787 3.44.556.708 I slot print_timing: id 2 | task 2306 | graph reallocs = 0 / 0 (same size) / (changed size) 3.44.556.755 I slot release: id 2 | task 2306 | stop processing: n_tokens = 1294, truncated = 0 3.44.613.654 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.886 3.44.613.692 I slot launch_slot_: id 2 | task 2384 | processing task, is_child = 0 3.45.755.991 I slot print_timing: id 1 | task 2309 | prompt eval time = 510.01 ms / 113 tokens ( 4.51 ms per token, 221.56 tokens per second) 3.45.755.994 I slot print_timing: id 1 | task 2309 | eval time = 5042.53 ms / 86 tokens ( 59.32 ms per token, 16.86 tokens per second) 3.45.755.995 I slot print_timing: id 1 | task 2309 | total time = 5552.55 ms / 199 tokens 3.45.755.995 I slot print_timing: id 1 | task 2309 | graphs reused = 1798 3.45.755.996 I slot print_timing: id 1 | task 2309 | graph reallocs = 0 / 0 (same size) / (changed size) 3.45.756.053 I slot release: id 1 | task 2309 | stop processing: n_tokens = 1323, truncated = 0 3.45.813.343 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.866 3.45.813.380 I slot launch_slot_: id 1 | task 2400 | processing task, is_child = 0 3.46.673.390 I slot print_timing: id 0 | task 2303 | n_gen = 100, tg = 14.30 t/s, tg_3s = 14.45 t/s 3.48.821.203 I slot print_timing: id 0 | task 2303 | prompt eval time = 460.73 ms / 109 tokens ( 4.23 ms per token, 236.58 tokens per second) 3.48.821.209 I slot print_timing: id 0 | task 2303 | eval time = 9068.74 ms / 143 tokens ( 63.86 ms per token, 15.66 tokens per second) 3.48.821.210 I slot print_timing: id 0 | task 2303 | total time = 9529.46 ms / 252 tokens 3.48.821.211 I slot print_timing: id 0 | task 2303 | graphs reused = 1847 3.48.821.212 I slot print_timing: id 0 | task 2303 | graph reallocs = 0 / 0 (same size) / (changed size) 3.48.821.310 I slot release: id 0 | task 2303 | stop processing: n_tokens = 1376, truncated = 0 3.48.869.434 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.833 3.48.869.485 I slot launch_slot_: id 0 | task 2454 | processing task, is_child = 0 3.49.848.064 I slot print_timing: id 3 | task 2362 | n_gen = 100, tg = 16.01 t/s, tg_3s = 16.18 t/s 3.50.048.643 I slot print_timing: id 3 | task 2362 | prompt eval time = 483.64 ms / 119 tokens ( 4.06 ms per token, 246.05 tokens per second) 3.50.048.650 I slot print_timing: id 3 | task 2362 | eval time = 6382.40 ms / 104 tokens ( 61.97 ms per token, 16.14 tokens per second) 3.50.048.651 I slot print_timing: id 3 | task 2362 | total time = 6866.03 ms / 223 tokens 3.50.048.652 I slot print_timing: id 3 | task 2362 | graphs reused = 1861 3.50.048.653 I slot print_timing: id 3 | task 2362 | graph reallocs = 0 / 0 (same size) / (changed size) 3.50.048.734 I slot release: id 3 | task 2362 | stop processing: n_tokens = 1347, truncated = 0 3.50.095.526 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.851 3.50.095.577 I slot launch_slot_: id 3 | task 2472 | processing task, is_child = 0 3.51.231.460 I slot print_timing: id 2 | task 2384 | n_gen = 100, tg = 16.31 t/s, tg_3s = 16.47 t/s 3.51.973.562 I slot print_timing: id 1 | task 2400 | n_gen = 100, tg = 17.53 t/s, tg_3s = 17.70 t/s 3.53.260.347 I slot print_timing: id 2 | task 2384 | prompt eval time = 546.52 ms / 134 tokens ( 4.08 ms per token, 245.19 tokens per second) 3.53.260.352 I slot print_timing: id 2 | task 2384 | eval time = 8100.13 ms / 141 tokens ( 57.86 ms per token, 17.28 tokens per second) 3.53.260.353 I slot print_timing: id 2 | task 2384 | total time = 8646.65 ms / 275 tokens 3.53.260.353 I slot print_timing: id 2 | task 2384 | graphs reused = 1915 3.53.260.354 I slot print_timing: id 2 | task 2384 | graph reallocs = 0 / 0 (same size) / (changed size) 3.53.260.402 I slot release: id 2 | task 2384 | stop processing: n_tokens = 1399, truncated = 0 3.53.317.714 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.819 3.53.317.762 I slot launch_slot_: id 2 | task 2531 | processing task, is_child = 0 3.54.530.431 I slot print_timing: id 3 | task 2472 | prompt eval time = 442.88 ms / 95 tokens ( 4.66 ms per token, 214.51 tokens per second) 3.54.530.436 I slot print_timing: id 3 | task 2472 | eval time = 3991.97 ms / 74 tokens ( 54.68 ms per token, 18.29 tokens per second) 3.54.530.436 I slot print_timing: id 3 | task 2472 | total time = 4434.84 ms / 169 tokens 3.54.530.436 I slot print_timing: id 3 | task 2472 | graphs reused = 1929 3.54.530.437 I slot print_timing: id 3 | task 2472 | graph reallocs = 0 / 0 (same size) / (changed size) 3.54.530.481 I slot release: id 3 | task 2472 | stop processing: n_tokens = 1293, truncated = 0 3.54.574.620 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.886 3.54.574.648 I slot launch_slot_: id 3 | task 2550 | processing task, is_child = 0 3.54.975.605 I slot print_timing: id 1 | task 2400 | n_gen = 146, tg = 16.76 t/s, tg_3s = 15.32 t/s 3.55.363.948 I slot print_timing: id 0 | task 2454 | n_gen = 100, tg = 16.43 t/s, tg_3s = 16.59 t/s 3.55.809.311 I slot print_timing: id 0 | task 2454 | prompt eval time = 467.88 ms / 109 tokens ( 4.29 ms per token, 232.96 tokens per second) 3.55.809.316 I slot print_timing: id 0 | task 2454 | eval time = 6471.93 ms / 109 tokens ( 59.93 ms per token, 16.69 tokens per second) 3.55.809.317 I slot print_timing: id 0 | task 2454 | total time = 6939.81 ms / 218 tokens 3.55.809.318 I slot print_timing: id 0 | task 2454 | graphs reused = 1943 3.55.809.319 I slot print_timing: id 0 | task 2454 | graph reallocs = 0 / 0 (same size) / (changed size) 3.55.809.393 I slot release: id 0 | task 2454 | stop processing: n_tokens = 1342, truncated = 0 3.55.856.660 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.854 3.55.856.773 I slot launch_slot_: id 0 | task 2569 | processing task, is_child = 0 3.57.901.984 I slot print_timing: id 1 | task 2400 | prompt eval time = 511.97 ms / 112 tokens ( 4.57 ms per token, 218.76 tokens per second) 3.57.901.992 I slot print_timing: id 1 | task 2400 | eval time = 11576.62 ms / 194 tokens ( 59.98 ms per token, 16.67 tokens per second) 3.57.901.994 I slot print_timing: id 1 | task 2400 | total time = 12088.59 ms / 306 tokens 3.57.901.995 I slot print_timing: id 1 | task 2400 | graphs reused = 1972 3.57.901.996 I slot print_timing: id 1 | task 2400 | graph reallocs = 0 / 0 (same size) / (changed size) 3.57.902.087 I slot release: id 1 | task 2400 | stop processing: n_tokens = 1430, truncated = 0 3.57.963.243 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.801 3.57.963.316 I slot launch_slot_: id 1 | task 2602 | processing task, is_child = 0 3.59.922.148 I slot print_timing: id 2 | task 2531 | prompt eval time = 468.16 ms / 96 tokens ( 4.88 ms per token, 205.06 tokens per second) 3.59.922.150 I slot print_timing: id 2 | task 2531 | eval time = 6136.21 ms / 98 tokens ( 63.26 ms per token, 15.81 tokens per second) 3.59.922.151 I slot print_timing: id 2 | task 2531 | total time = 6604.37 ms / 194 tokens 3.59.922.151 I slot print_timing: id 2 | task 2531 | graphs reused = 2000 3.59.922.151 I slot print_timing: id 2 | task 2531 | graph reallocs = 0 / 0 (same size) / (changed size) 3.59.922.201 I slot release: id 2 | task 2531 | stop processing: n_tokens = 1318, truncated = 0 3.59.979.436 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.869 3.59.979.490 I slot launch_slot_: id 2 | task 2635 | processing task, is_child = 0 4.01.318.753 I slot print_timing: id 3 | task 2550 | n_gen = 100, tg = 15.83 t/s, tg_3s = 15.99 t/s 4.02.209.573 I slot print_timing: id 0 | task 2569 | n_gen = 100, tg = 17.13 t/s, tg_3s = 17.30 t/s 4.02.408.315 I slot print_timing: id 3 | task 2550 | prompt eval time = 491.05 ms / 122 tokens ( 4.03 ms per token, 248.45 tokens per second) 4.02.408.318 I slot print_timing: id 3 | task 2550 | eval time = 7342.61 ms / 122 tokens ( 60.68 ms per token, 16.48 tokens per second) 4.02.408.318 I slot print_timing: id 3 | task 2550 | total time = 7833.66 ms / 244 tokens 4.02.408.319 I slot print_timing: id 3 | task 2550 | graphs reused = 2038 4.02.408.319 I slot print_timing: id 3 | task 2550 | graph reallocs = 0 / 0 (same size) / (changed size) 4.02.408.370 I slot release: id 3 | task 2550 | stop processing: n_tokens = 1368, truncated = 0 4.02.453.018 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.838 4.02.453.050 I slot launch_slot_: id 3 | task 2678 | processing task, is_child = 0 4.02.925.981 I slot print_timing: id 0 | task 2569 | prompt eval time = 573.84 ms / 166 tokens ( 3.46 ms per token, 289.28 tokens per second) 4.02.925.985 I slot print_timing: id 0 | task 2569 | eval time = 6495.33 ms / 107 tokens ( 61.28 ms per token, 16.32 tokens per second) 4.02.925.986 I slot print_timing: id 0 | task 2569 | total time = 7069.18 ms / 273 tokens 4.02.925.987 I slot print_timing: id 0 | task 2569 | graphs reused = 2038 4.02.925.987 I slot print_timing: id 0 | task 2569 | graph reallocs = 0 / 0 (same size) / (changed size) 4.02.926.035 I slot release: id 0 | task 2569 | stop processing: n_tokens = 1397, truncated = 0 4.02.970.420 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.911 (> 0.100 thold), f_keep = 0.820 4.02.970.460 I slot launch_slot_: id 0 | task 2682 | processing task, is_child = 0 4.04.566.932 I slot print_timing: id 1 | task 2602 | n_gen = 100, tg = 16.28 t/s, tg_3s = 16.45 t/s 4.06.098.614 I slot print_timing: id 2 | task 2635 | prompt eval time = 497.26 ms / 104 tokens ( 4.78 ms per token, 209.15 tokens per second) 4.06.098.619 I slot print_timing: id 2 | task 2635 | eval time = 5621.85 ms / 99 tokens ( 57.37 ms per token, 17.43 tokens per second) 4.06.098.620 I slot print_timing: id 2 | task 2635 | total time = 6119.11 ms / 203 tokens 4.06.098.621 I slot print_timing: id 2 | task 2635 | graphs reused = 2091 4.06.098.621 I slot print_timing: id 2 | task 2635 | graph reallocs = 0 / 0 (same size) / (changed size) 4.06.098.666 I slot release: id 2 | task 2635 | stop processing: n_tokens = 1327, truncated = 0 4.06.156.011 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.864 4.06.156.060 I slot launch_slot_: id 2 | task 2739 | processing task, is_child = 0 4.07.055.495 I slot print_timing: id 1 | task 2602 | prompt eval time = 523.29 ms / 117 tokens ( 4.47 ms per token, 223.58 tokens per second) 4.07.055.498 I slot print_timing: id 1 | task 2602 | eval time = 8568.88 ms / 142 tokens ( 60.77 ms per token, 16.45 tokens per second) 4.07.055.498 I slot print_timing: id 1 | task 2602 | total time = 9092.17 ms / 259 tokens 4.07.055.499 I slot print_timing: id 1 | task 2602 | graphs reused = 2098 4.07.055.499 I slot print_timing: id 1 | task 2602 | graph reallocs = 0 / 0 (same size) / (changed size) 4.07.055.544 I slot release: id 1 | task 2602 | stop processing: n_tokens = 1383, truncated = 0 4.07.112.662 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.829 4.07.112.701 I slot launch_slot_: id 1 | task 2751 | processing task, is_child = 0 4.09.096.946 I slot print_timing: id 3 | task 2678 | n_gen = 100, tg = 16.04 t/s, tg_3s = 16.21 t/s 4.09.247.108 I slot print_timing: id 0 | task 2682 | n_gen = 100, tg = 17.16 t/s, tg_3s = 17.33 t/s 4.10.659.810 I slot print_timing: id 3 | task 2678 | prompt eval time = 473.51 ms / 108 tokens ( 4.38 ms per token, 228.08 tokens per second) 4.10.659.818 I slot print_timing: id 3 | task 2678 | eval time = 7733.24 ms / 131 tokens ( 59.49 ms per token, 16.81 tokens per second) 4.10.659.819 I slot print_timing: id 3 | task 2678 | total time = 8206.75 ms / 239 tokens 4.10.659.820 I slot print_timing: id 3 | task 2678 | graphs reused = 2157 4.10.659.827 I slot print_timing: id 3 | task 2678 | graph reallocs = 0 / 0 (same size) / (changed size) 4.10.659.937 I slot release: id 3 | task 2678 | stop processing: n_tokens = 1363, truncated = 0 4.10.706.984 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.841 4.10.707.041 I slot launch_slot_: id 3 | task 2815 | processing task, is_child = 0 4.11.247.347 I slot print_timing: id 2 | task 2739 | prompt eval time = 502.42 ms / 112 tokens ( 4.49 ms per token, 222.92 tokens per second) 4.11.247.352 I slot print_timing: id 2 | task 2739 | eval time = 4588.86 ms / 76 tokens ( 61.18 ms per token, 16.34 tokens per second) 4.11.247.352 I slot print_timing: id 2 | task 2739 | total time = 5091.28 ms / 188 tokens 4.11.247.353 I slot print_timing: id 2 | task 2739 | graphs reused = 2157 4.11.247.353 I slot print_timing: id 2 | task 2739 | graph reallocs = 0 / 0 (same size) / (changed size) 4.11.247.397 I slot release: id 2 | task 2739 | stop processing: n_tokens = 1312, truncated = 0 4.11.304.146 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.873 4.11.304.180 I slot launch_slot_: id 2 | task 2820 | processing task, is_child = 0 4.12.261.499 I slot print_timing: id 0 | task 2682 | n_gen = 144, tg = 16.28 t/s, tg_3s = 14.60 t/s 4.12.558.118 I slot print_timing: id 1 | task 2751 | prompt eval time = 516.65 ms / 116 tokens ( 4.45 ms per token, 224.53 tokens per second) 4.12.558.123 I slot print_timing: id 1 | task 2751 | eval time = 4928.76 ms / 83 tokens ( 60.11 ms per token, 16.64 tokens per second) 4.12.558.123 I slot print_timing: id 1 | task 2751 | total time = 5445.41 ms / 199 tokens 4.12.558.124 I slot print_timing: id 1 | task 2751 | graphs reused = 2171 4.12.558.124 I slot print_timing: id 1 | task 2751 | graph reallocs = 0 / 0 (same size) / (changed size) 4.12.558.169 I slot release: id 1 | task 2751 | stop processing: n_tokens = 1323, truncated = 0 4.12.615.074 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.866 4.12.615.109 I slot launch_slot_: id 1 | task 2839 | processing task, is_child = 0 4.13.518.482 I slot print_timing: id 0 | task 2682 | prompt eval time = 506.25 ms / 133 tokens ( 3.81 ms per token, 262.72 tokens per second) 4.13.518.485 I slot print_timing: id 0 | task 2682 | eval time = 10041.76 ms / 161 tokens ( 62.76 ms per token, 15.93 tokens per second) 4.13.518.486 I slot print_timing: id 0 | task 2682 | total time = 10548.01 ms / 294 tokens 4.13.518.486 I slot print_timing: id 0 | task 2682 | graphs reused = 2178 4.13.518.487 I slot print_timing: id 0 | task 2682 | graph reallocs = 0 / 0 (same size) / (changed size) 4.13.518.531 I slot release: id 0 | task 2682 | stop processing: n_tokens = 1418, truncated = 0 4.13.563.384 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.808 4.13.563.419 I slot launch_slot_: id 0 | task 2851 | processing task, is_child = 0 4.17.256.412 I slot print_timing: id 0 | task 2851 | prompt eval time = 477.75 ms / 120 tokens ( 3.98 ms per token, 251.18 tokens per second) 4.17.256.417 I slot print_timing: id 0 | task 2851 | eval time = 3215.23 ms / 65 tokens ( 50.24 ms per token, 19.91 tokens per second) 4.17.256.419 I slot print_timing: id 0 | task 2851 | total time = 3692.98 ms / 185 tokens 4.17.256.420 I slot print_timing: id 0 | task 2851 | graphs reused = 2241 4.17.256.421 I slot print_timing: id 0 | task 2851 | graph reallocs = 0 / 0 (same size) / (changed size) 4.17.256.509 I slot release: id 0 | task 2851 | stop processing: n_tokens = 1309, truncated = 0 4.17.304.639 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.875 4.17.304.705 I slot launch_slot_: id 0 | task 2919 | processing task, is_child = 0 4.17.688.126 I slot print_timing: id 2 | task 2820 | prompt eval time = 510.98 ms / 119 tokens ( 4.29 ms per token, 232.89 tokens per second) 4.17.688.134 I slot print_timing: id 2 | task 2820 | eval time = 5872.97 ms / 96 tokens ( 61.82 ms per token, 16.18 tokens per second) 4.17.688.134 I slot print_timing: id 2 | task 2820 | total time = 6383.94 ms / 215 tokens 4.17.688.135 I slot print_timing: id 2 | task 2820 | graphs reused = 2242 4.17.688.135 I slot print_timing: id 2 | task 2820 | graph reallocs = 0 / 0 (same size) / (changed size) 4.17.688.181 I slot release: id 2 | task 2820 | stop processing: n_tokens = 1339, truncated = 0 4.17.688.392 I slot print_timing: id 3 | task 2815 | n_gen = 100, tg = 15.25 t/s, tg_3s = 15.40 t/s 4.17.774.664 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.856 4.17.774.711 I slot launch_slot_: id 2 | task 2922 | processing task, is_child = 0 4.18.392.497 I slot print_timing: id 1 | task 2839 | prompt eval time = 505.80 ms / 103 tokens ( 4.91 ms per token, 203.64 tokens per second) 4.18.392.502 I slot print_timing: id 1 | task 2839 | eval time = 5271.58 ms / 84 tokens ( 63.51 ms per token, 15.74 tokens per second) 4.18.392.502 I slot print_timing: id 1 | task 2839 | total time = 5777.38 ms / 187 tokens 4.18.392.503 I slot print_timing: id 1 | task 2839 | graphs reused = 2244 4.18.392.503 I slot print_timing: id 1 | task 2839 | graph reallocs = 0 / 0 (same size) / (changed size) 4.18.392.554 I slot release: id 1 | task 2839 | stop processing: n_tokens = 1311, truncated = 0 4.18.449.419 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.874 4.18.449.451 I slot launch_slot_: id 1 | task 2929 | processing task, is_child = 0 4.20.710.993 I slot print_timing: id 3 | task 2815 | n_gen = 145, tg = 15.13 t/s, tg_3s = 14.89 t/s 4.21.600.076 I slot print_timing: id 0 | task 2919 | prompt eval time = 469.53 ms / 108 tokens ( 4.35 ms per token, 230.02 tokens per second) 4.21.600.079 I slot print_timing: id 0 | task 2919 | eval time = 3825.84 ms / 63 tokens ( 61.71 ms per token, 16.21 tokens per second) 4.21.600.079 I slot print_timing: id 0 | task 2919 | total time = 4295.36 ms / 171 tokens 4.21.600.080 I slot print_timing: id 0 | task 2919 | graphs reused = 2297 4.21.600.080 I slot print_timing: id 0 | task 2919 | graph reallocs = 0 / 0 (same size) / (changed size) 4.21.600.128 I slot release: id 0 | task 2919 | stop processing: n_tokens = 1295, truncated = 0 4.21.644.694 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.885 4.21.644.735 I slot launch_slot_: id 0 | task 2987 | processing task, is_child = 0 4.22.451.128 I slot print_timing: id 2 | task 2922 | prompt eval time = 467.52 ms / 97 tokens ( 4.82 ms per token, 207.48 tokens per second) 4.22.451.134 I slot print_timing: id 2 | task 2922 | eval time = 4208.89 ms / 69 tokens ( 61.90 ms per token, 16.16 tokens per second) 4.22.451.134 I slot print_timing: id 2 | task 2922 | total time = 4676.41 ms / 166 tokens 4.22.451.135 I slot print_timing: id 2 | task 2922 | graphs reused = 2302 4.22.451.135 I slot print_timing: id 2 | task 2922 | graph reallocs = 0 / 0 (same size) / (changed size) 4.22.451.180 I slot release: id 2 | task 2922 | stop processing: n_tokens = 1290, truncated = 0 4.22.508.548 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.888 4.22.508.603 I slot launch_slot_: id 2 | task 2996 | processing task, is_child = 0 4.23.417.540 I slot print_timing: id 1 | task 2929 | prompt eval time = 479.26 ms / 100 tokens ( 4.79 ms per token, 208.65 tokens per second) 4.23.417.542 I slot print_timing: id 1 | task 2929 | eval time = 4488.81 ms / 74 tokens ( 61.49 ms per token, 16.26 tokens per second) 4.23.417.543 I slot print_timing: id 1 | task 2929 | total time = 4968.08 ms / 174 tokens 4.23.417.543 I slot print_timing: id 1 | task 2929 | graphs reused = 2309 4.23.417.544 I slot print_timing: id 1 | task 2929 | graph reallocs = 0 / 0 (same size) / (changed size) 4.23.417.598 I slot release: id 1 | task 2929 | stop processing: n_tokens = 1298, truncated = 0 4.23.475.006 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.883 4.23.475.054 I slot launch_slot_: id 1 | task 3008 | processing task, is_child = 0 4.23.887.713 I slot print_timing: id 3 | task 2815 | n_gen = 184, tg = 14.42 t/s, tg_3s = 12.28 t/s 4.25.014.613 I slot print_timing: id 3 | task 2815 | prompt eval time = 488.96 ms / 119 tokens ( 4.11 ms per token, 243.37 tokens per second) 4.25.014.621 I slot print_timing: id 3 | task 2815 | eval time = 13818.59 ms / 205 tokens ( 67.74 ms per token, 14.76 tokens per second) 4.25.014.623 I slot print_timing: id 3 | task 2815 | total time = 14307.55 ms / 324 tokens 4.25.014.623 I slot print_timing: id 3 | task 2815 | graphs reused = 2328 4.25.014.624 I slot print_timing: id 3 | task 2815 | graph reallocs = 0 / 0 (same size) / (changed size) 4.25.014.745 I slot release: id 3 | task 2815 | stop processing: n_tokens = 1448, truncated = 0 4.25.063.007 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.791 4.25.063.074 I slot launch_slot_: id 3 | task 3032 | processing task, is_child = 0 4.27.675.667 I slot print_timing: id 1 | task 3008 | prompt eval time = 519.09 ms / 114 tokens ( 4.55 ms per token, 219.61 tokens per second) 4.27.675.678 I slot print_timing: id 1 | task 3008 | eval time = 3681.51 ms / 66 tokens ( 56.64 ms per token, 17.66 tokens per second) 4.27.675.680 I slot print_timing: id 1 | task 3008 | total time = 4200.60 ms / 180 tokens 4.27.675.681 I slot print_timing: id 1 | task 3008 | graphs reused = 2369 4.27.675.682 I slot print_timing: id 1 | task 3008 | graph reallocs = 0 / 0 (same size) / (changed size) 4.27.675.773 I slot release: id 1 | task 3008 | stop processing: n_tokens = 1304, truncated = 0 4.27.736.965 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.879 4.27.737.033 I slot launch_slot_: id 1 | task 3078 | processing task, is_child = 0 4.28.800.881 I slot print_timing: id 3 | task 3032 | prompt eval time = 485.21 ms / 104 tokens ( 4.67 ms per token, 214.34 tokens per second) 4.28.800.887 I slot print_timing: id 3 | task 3032 | eval time = 3252.58 ms / 57 tokens ( 58.08 ms per token, 17.22 tokens per second) 4.28.800.887 I slot print_timing: id 3 | task 3032 | total time = 3737.79 ms / 161 tokens 4.28.800.888 I slot print_timing: id 3 | task 3032 | graphs reused = 2379 4.28.800.888 I slot print_timing: id 3 | task 3032 | graph reallocs = 0 / 0 (same size) / (changed size) 4.28.800.933 I slot release: id 3 | task 3032 | stop processing: n_tokens = 1285, truncated = 0 4.28.844.750 I slot print_timing: id 0 | task 2987 | n_gen = 100, tg = 14.90 t/s, tg_3s = 15.05 t/s 4.28.845.063 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.945 (> 0.100 thold), f_keep = 0.892 4.28.845.092 I slot launch_slot_: id 3 | task 3093 | processing task, is_child = 0 4.29.574.852 I slot print_timing: id 2 | task 2996 | n_gen = 100, tg = 15.10 t/s, tg_3s = 15.26 t/s 4.30.266.954 I slot print_timing: id 2 | task 2996 | prompt eval time = 511.15 ms / 119 tokens ( 4.30 ms per token, 232.81 tokens per second) 4.30.266.959 I slot print_timing: id 2 | task 2996 | eval time = 7247.20 ms / 114 tokens ( 64.13 ms per token, 15.59 tokens per second) 4.30.266.960 I slot print_timing: id 2 | task 2996 | total time = 7758.34 ms / 233 tokens 4.30.266.960 I slot print_timing: id 2 | task 2996 | graphs reused = 2398 4.30.266.960 I slot print_timing: id 2 | task 2996 | graph reallocs = 0 / 0 (same size) / (changed size) 4.30.267.005 I slot release: id 2 | task 2996 | stop processing: n_tokens = 1357, truncated = 0 4.30.323.981 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.845 4.30.324.010 I slot launch_slot_: id 2 | task 3117 | processing task, is_child = 0 4.31.888.596 I slot print_timing: id 0 | task 2987 | n_gen = 146, tg = 14.97 t/s, tg_3s = 15.11 t/s 4.32.629.523 I slot print_timing: id 0 | task 2987 | prompt eval time = 556.24 ms / 172 tokens ( 3.23 ms per token, 309.22 tokens per second) 4.32.629.528 I slot print_timing: id 0 | task 2987 | eval time = 10428.54 ms / 161 tokens ( 65.18 ms per token, 15.34 tokens per second) 4.32.629.529 I slot print_timing: id 0 | task 2987 | total time = 10984.78 ms / 333 tokens 4.32.629.529 I slot print_timing: id 0 | task 2987 | graphs reused = 2433 4.32.629.530 I slot print_timing: id 0 | task 2987 | graph reallocs = 0 / 0 (same size) / (changed size) 4.32.629.579 I slot release: id 0 | task 2987 | stop processing: n_tokens = 1457, truncated = 0 4.32.674.033 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.787 4.32.674.069 I slot launch_slot_: id 0 | task 3157 | processing task, is_child = 0 4.33.297.500 I slot print_timing: id 1 | task 3078 | prompt eval time = 517.56 ms / 117 tokens ( 4.42 ms per token, 226.06 tokens per second) 4.33.297.505 I slot print_timing: id 1 | task 3078 | eval time = 5042.90 ms / 81 tokens ( 63.04 ms per token, 15.86 tokens per second) 4.33.297.506 I slot print_timing: id 1 | task 3078 | total time = 5560.46 ms / 198 tokens 4.33.297.506 I slot print_timing: id 1 | task 3078 | graphs reused = 2437 4.33.297.507 I slot print_timing: id 1 | task 3078 | graph reallocs = 0 / 0 (same size) / (changed size) 4.33.297.554 I slot release: id 1 | task 3078 | stop processing: n_tokens = 1322, truncated = 0 4.33.354.506 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.867 4.33.354.550 I slot launch_slot_: id 1 | task 3165 | processing task, is_child = 0 4.34.693.101 I slot print_timing: id 3 | task 3093 | prompt eval time = 431.59 ms / 88 tokens ( 4.90 ms per token, 203.90 tokens per second) 4.34.693.109 I slot print_timing: id 3 | task 3093 | eval time = 5416.40 ms / 85 tokens ( 64.48 ms per token, 15.51 tokens per second) 4.34.693.111 I slot print_timing: id 3 | task 3093 | total time = 5848.00 ms / 173 tokens 4.34.693.112 I slot print_timing: id 3 | task 3093 | graphs reused = 2451 4.34.693.113 I slot print_timing: id 3 | task 3093 | graph reallocs = 0 / 0 (same size) / (changed size) 4.34.693.198 I slot release: id 3 | task 3093 | stop processing: n_tokens = 1297, truncated = 0 4.34.740.008 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.884 4.34.740.075 I slot launch_slot_: id 3 | task 3184 | processing task, is_child = 0 4.36.831.115 I slot print_timing: id 2 | task 3117 | prompt eval time = 524.71 ms / 129 tokens ( 4.07 ms per token, 245.85 tokens per second) 4.36.831.123 I slot print_timing: id 2 | task 3117 | eval time = 5982.39 ms / 97 tokens ( 62.32 ms per token, 16.05 tokens per second) 4.36.831.125 I slot print_timing: id 2 | task 3117 | total time = 6507.09 ms / 226 tokens 4.36.831.126 I slot print_timing: id 2 | task 3117 | graphs reused = 2482 4.36.831.127 I slot print_timing: id 2 | task 3117 | graph reallocs = 0 / 0 (same size) / (changed size) 4.36.831.217 I slot release: id 2 | task 3117 | stop processing: n_tokens = 1350, truncated = 0 4.36.892.473 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.849 4.36.892.553 I slot launch_slot_: id 2 | task 3220 | processing task, is_child = 0 4.37.292.788 I slot print_timing: id 0 | task 3157 | prompt eval time = 423.27 ms / 87 tokens ( 4.87 ms per token, 205.54 tokens per second) 4.37.292.794 I slot print_timing: id 0 | task 3157 | eval time = 4195.44 ms / 60 tokens ( 71.11 ms per token, 14.06 tokens per second) 4.37.292.795 I slot print_timing: id 0 | task 3157 | total time = 4618.72 ms / 147 tokens 4.37.292.795 I slot print_timing: id 0 | task 3157 | graphs reused = 2482 4.37.292.796 I slot print_timing: id 0 | task 3157 | graph reallocs = 0 / 0 (same size) / (changed size) 4.37.292.843 I slot release: id 0 | task 3157 | stop processing: n_tokens = 1271, truncated = 0 4.37.387.015 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.902 4.37.387.045 I slot launch_slot_: id 0 | task 3223 | processing task, is_child = 0 4.40.079.468 I slot print_timing: id 1 | task 3165 | n_gen = 100, tg = 16.11 t/s, tg_3s = 16.27 t/s 4.40.178.729 I slot print_timing: id 3 | task 3184 | prompt eval time = 489.22 ms / 118 tokens ( 4.15 ms per token, 241.20 tokens per second) 4.40.178.735 I slot print_timing: id 3 | task 3184 | eval time = 4949.43 ms / 84 tokens ( 59.63 ms per token, 16.77 tokens per second) 4.40.178.735 I slot print_timing: id 3 | task 3184 | total time = 5438.65 ms / 202 tokens 4.40.178.736 I slot print_timing: id 3 | task 3184 | graphs reused = 2527 4.40.178.736 I slot print_timing: id 3 | task 3184 | graph reallocs = 0 / 0 (same size) / (changed size) 4.40.178.781 I slot release: id 3 | task 3184 | stop processing: n_tokens = 1326, truncated = 0 4.40.223.235 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.942 (> 0.100 thold), f_keep = 0.864 4.40.223.268 I slot launch_slot_: id 3 | task 3273 | processing task, is_child = 0 4.40.956.285 I slot print_timing: id 1 | task 3165 | prompt eval time = 577.94 ms / 152 tokens ( 3.80 ms per token, 263.00 tokens per second) 4.40.956.290 I slot print_timing: id 1 | task 3165 | eval time = 7023.79 ms / 111 tokens ( 63.85 ms per token, 15.66 tokens per second) 4.40.956.291 I slot print_timing: id 1 | task 3165 | total time = 7601.73 ms / 263 tokens 4.40.956.291 I slot print_timing: id 1 | task 3165 | graphs reused = 2532 4.40.956.292 I slot print_timing: id 1 | task 3165 | graph reallocs = 0 / 0 (same size) / (changed size) 4.40.956.335 I slot release: id 1 | task 3165 | stop processing: n_tokens = 1387, truncated = 0 4.41.013.178 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.826 4.41.013.213 I slot launch_slot_: id 1 | task 3283 | processing task, is_child = 0 4.42.819.284 I slot print_timing: id 0 | task 3223 | prompt eval time = 512.24 ms / 135 tokens ( 3.79 ms per token, 263.55 tokens per second) 4.42.819.286 I slot print_timing: id 0 | task 3223 | eval time = 4919.99 ms / 85 tokens ( 58.57 ms per token, 17.07 tokens per second) 4.42.819.287 I slot print_timing: id 0 | task 3223 | total time = 5432.23 ms / 220 tokens 4.42.819.287 I slot print_timing: id 0 | task 3223 | graphs reused = 2557 4.42.819.288 I slot print_timing: id 0 | task 3223 | graph reallocs = 0 / 0 (same size) / (changed size) 4.42.819.337 I slot release: id 0 | task 3223 | stop processing: n_tokens = 1344, truncated = 0 4.42.864.631 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.853 4.42.864.662 I slot launch_slot_: id 0 | task 3313 | processing task, is_child = 0 4.43.846.932 I slot print_timing: id 2 | task 3220 | n_gen = 100, tg = 15.32 t/s, tg_3s = 15.48 t/s 4.45.566.242 I slot print_timing: id 3 | task 3273 | prompt eval time = 434.65 ms / 92 tokens ( 4.72 ms per token, 211.66 tokens per second) 4.45.566.261 I slot print_timing: id 3 | task 3273 | eval time = 4908.31 ms / 83 tokens ( 59.86 ms per token, 16.71 tokens per second) 4.45.566.262 I slot print_timing: id 3 | task 3273 | total time = 5342.96 ms / 175 tokens 4.45.566.265 I slot print_timing: id 3 | task 3273 | graphs reused = 2601 4.45.566.267 I slot print_timing: id 3 | task 3273 | graph reallocs = 0 / 0 (same size) / (changed size) 4.45.566.377 I slot release: id 3 | task 3273 | stop processing: n_tokens = 1299, truncated = 0 4.45.614.050 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.882 4.45.614.118 I slot launch_slot_: id 3 | task 3361 | processing task, is_child = 0 4.46.895.759 I slot print_timing: id 1 | task 3283 | prompt eval time = 520.42 ms / 120 tokens ( 4.34 ms per token, 230.58 tokens per second) 4.46.895.762 I slot print_timing: id 1 | task 3283 | eval time = 5362.11 ms / 94 tokens ( 57.66 ms per token, 17.34 tokens per second) 4.46.895.763 I slot print_timing: id 1 | task 3283 | total time = 5882.54 ms / 214 tokens 4.46.895.763 I slot print_timing: id 1 | task 3283 | graphs reused = 2617 4.46.895.763 I slot print_timing: id 1 | task 3283 | graph reallocs = 0 / 0 (same size) / (changed size) 4.46.895.808 I slot release: id 1 | task 3283 | stop processing: n_tokens = 1338, truncated = 0 4.46.895.953 I slot print_timing: id 2 | task 3220 | n_gen = 154, tg = 16.09 t/s, tg_3s = 17.71 t/s 4.46.953.294 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.857 4.46.953.331 I slot launch_slot_: id 1 | task 3382 | processing task, is_child = 0 4.49.032.306 I slot print_timing: id 0 | task 3313 | n_gen = 100, tg = 17.42 t/s, tg_3s = 17.60 t/s 4.49.939.914 I slot print_timing: id 2 | task 3220 | n_gen = 207, tg = 16.41 t/s, tg_3s = 17.41 t/s 4.50.493.141 I slot print_timing: id 2 | task 3220 | prompt eval time = 494.30 ms / 110 tokens ( 4.49 ms per token, 222.54 tokens per second) 4.50.493.147 I slot print_timing: id 2 | task 3220 | eval time = 13106.27 ms / 218 tokens ( 60.40 ms per token, 16.56 tokens per second) 4.50.493.148 I slot print_timing: id 2 | task 3220 | total time = 13600.57 ms / 328 tokens 4.50.493.149 I slot print_timing: id 2 | task 3220 | graphs reused = 2677 4.50.493.150 I slot print_timing: id 2 | task 3220 | graph reallocs = 0 / 0 (same size) / (changed size) 4.50.493.276 I slot release: id 2 | task 3220 | stop processing: n_tokens = 1452, truncated = 0 4.50.555.258 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.789 4.50.555.333 I slot launch_slot_: id 2 | task 3447 | processing task, is_child = 0 4.51.813.219 I slot print_timing: id 0 | task 3313 | prompt eval time = 485.04 ms / 131 tokens ( 3.70 ms per token, 270.08 tokens per second) 4.51.813.224 I slot print_timing: id 0 | task 3313 | eval time = 8463.51 ms / 147 tokens ( 57.97 ms per token, 17.25 tokens per second) 4.51.813.224 I slot print_timing: id 0 | task 3313 | total time = 8948.55 ms / 278 tokens 4.51.813.224 I slot print_timing: id 0 | task 3313 | graphs reused = 2691 4.51.813.225 I slot print_timing: id 0 | task 3313 | graph reallocs = 0 / 0 (same size) / (changed size) 4.51.813.273 I slot release: id 0 | task 3313 | stop processing: n_tokens = 1402, truncated = 0 4.51.813.734 I slot print_timing: id 3 | task 3361 | n_gen = 100, tg = 17.19 t/s, tg_3s = 17.36 t/s 4.51.858.005 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.817 4.51.858.038 I slot launch_slot_: id 0 | task 3466 | processing task, is_child = 0 4.52.892.883 I slot print_timing: id 3 | task 3361 | prompt eval time = 439.32 ms / 95 tokens ( 4.62 ms per token, 216.24 tokens per second) 4.52.892.887 I slot print_timing: id 3 | task 3361 | eval time = 6839.43 ms / 114 tokens ( 60.53 ms per token, 16.52 tokens per second) 4.52.892.887 I slot print_timing: id 3 | task 3361 | total time = 7278.75 ms / 209 tokens 4.52.892.888 I slot print_timing: id 3 | task 3361 | graphs reused = 2702 4.52.892.888 I slot print_timing: id 3 | task 3361 | graph reallocs = 0 / 0 (same size) / (changed size) 4.52.892.931 I slot release: id 3 | task 3361 | stop processing: n_tokens = 1333, truncated = 0 4.52.937.367 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.860 4.52.937.399 I slot launch_slot_: id 3 | task 3481 | processing task, is_child = 0 4.53.555.133 I slot print_timing: id 1 | task 3382 | prompt eval time = 475.11 ms / 98 tokens ( 4.85 ms per token, 206.27 tokens per second) 4.53.555.135 I slot print_timing: id 1 | task 3382 | eval time = 6126.69 ms / 100 tokens ( 61.89 ms per token, 16.16 tokens per second) 4.53.555.136 I slot print_timing: id 1 | task 3382 | total time = 6601.79 ms / 198 tokens 4.53.555.136 I slot print_timing: id 1 | task 3382 | graphs reused = 2704 4.53.555.137 I slot print_timing: id 1 | task 3382 | graph reallocs = 0 / 0 (same size) / (changed size) 4.53.555.180 I slot release: id 1 | task 3382 | stop processing: n_tokens = 1322, truncated = 0 4.53.612.105 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.867 4.53.612.135 I slot launch_slot_: id 1 | task 3488 | processing task, is_child = 0 4.56.809.436 I slot print_timing: id 2 | task 3447 | prompt eval time = 513.83 ms / 116 tokens ( 4.43 ms per token, 225.76 tokens per second) 4.56.809.443 I slot print_timing: id 2 | task 3447 | eval time = 5740.25 ms / 92 tokens ( 63.08 ms per token, 15.85 tokens per second) 4.56.809.446 I slot print_timing: id 2 | task 3447 | total time = 6254.07 ms / 208 tokens 4.56.809.446 I slot print_timing: id 2 | task 3447 | graphs reused = 2755 4.56.809.448 I slot print_timing: id 2 | task 3447 | graph reallocs = 0 / 0 (same size) / (changed size) 4.56.809.553 I slot release: id 2 | task 3447 | stop processing: n_tokens = 1332, truncated = 0 4.56.870.712 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.911 (> 0.100 thold), f_keep = 0.860 4.56.870.788 I slot launch_slot_: id 2 | task 3545 | processing task, is_child = 0 4.58.534.711 I slot print_timing: id 0 | task 3466 | n_gen = 100, tg = 16.00 t/s, tg_3s = 16.16 t/s 4.58.732.607 I slot print_timing: id 0 | task 3466 | prompt eval time = 487.65 ms / 130 tokens ( 3.75 ms per token, 266.59 tokens per second) 4.58.732.612 I slot print_timing: id 0 | task 3466 | eval time = 6386.92 ms / 104 tokens ( 62.01 ms per token, 16.13 tokens per second) 4.58.732.612 I slot print_timing: id 0 | task 3466 | total time = 6874.56 ms / 234 tokens 4.58.732.613 I slot print_timing: id 0 | task 3466 | graphs reused = 2781 4.58.732.613 I slot print_timing: id 0 | task 3466 | graph reallocs = 0 / 0 (same size) / (changed size) 4.58.732.662 I slot release: id 0 | task 3466 | stop processing: n_tokens = 1358, truncated = 0 4.58.777.168 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.918 (> 0.100 thold), f_keep = 0.844 4.58.777.202 I slot launch_slot_: id 0 | task 3576 | processing task, is_child = 0 4.59.599.680 I slot print_timing: id 3 | task 3481 | n_gen = 100, tg = 15.98 t/s, tg_3s = 16.14 t/s 4.59.896.639 I slot print_timing: id 1 | task 3488 | n_gen = 100, tg = 17.17 t/s, tg_3s = 17.34 t/s 5.00.689.394 I slot print_timing: id 3 | task 3481 | prompt eval time = 467.82 ms / 103 tokens ( 4.54 ms per token, 220.17 tokens per second) 5.00.689.400 I slot print_timing: id 3 | task 3481 | eval time = 7284.16 ms / 122 tokens ( 60.20 ms per token, 16.61 tokens per second) 5.00.689.400 I slot print_timing: id 3 | task 3481 | total time = 7751.99 ms / 225 tokens 5.00.689.401 I slot print_timing: id 3 | task 3481 | graphs reused = 2810 5.00.689.401 I slot print_timing: id 3 | task 3481 | graph reallocs = 0 / 0 (same size) / (changed size) 5.00.689.447 I slot release: id 3 | task 3481 | stop processing: n_tokens = 1349, truncated = 0 5.00.733.468 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.850 5.00.733.500 I slot launch_slot_: id 3 | task 3609 | processing task, is_child = 0 5.02.506.481 I slot print_timing: id 1 | task 3488 | prompt eval time = 518.55 ms / 122 tokens ( 4.25 ms per token, 235.27 tokens per second) 5.02.506.485 I slot print_timing: id 1 | task 3488 | eval time = 8375.79 ms / 145 tokens ( 58.17 ms per token, 17.19 tokens per second) 5.02.506.485 I slot print_timing: id 1 | task 3488 | total time = 8894.34 ms / 267 tokens 5.02.506.486 I slot print_timing: id 1 | task 3488 | graphs reused = 2835 5.02.506.486 I slot print_timing: id 1 | task 3488 | graph reallocs = 0 / 0 (same size) / (changed size) 5.02.506.531 I slot release: id 1 | task 3488 | stop processing: n_tokens = 1391, truncated = 0 5.02.564.337 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.824 5.02.564.375 I slot launch_slot_: id 1 | task 3639 | processing task, is_child = 0 5.03.432.803 I slot print_timing: id 2 | task 3545 | n_gen = 100, tg = 16.40 t/s, tg_3s = 16.57 t/s 5.04.767.916 I slot print_timing: id 0 | task 3576 | prompt eval time = 474.04 ms / 123 tokens ( 3.85 ms per token, 259.47 tokens per second) 5.04.767.920 I slot print_timing: id 0 | task 3576 | eval time = 5516.67 ms / 97 tokens ( 57.47 ms per token, 17.40 tokens per second) 5.04.767.920 I slot print_timing: id 0 | task 3576 | total time = 5990.71 ms / 220 tokens 5.04.767.921 I slot print_timing: id 0 | task 3576 | graphs reused = 2869 5.04.767.921 I slot print_timing: id 0 | task 3576 | graph reallocs = 0 / 0 (same size) / (changed size) 5.04.767.967 I slot release: id 0 | task 3576 | stop processing: n_tokens = 1344, truncated = 0 5.04.812.067 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.853 5.04.812.100 I slot launch_slot_: id 0 | task 3678 | processing task, is_child = 0 5.06.477.806 I slot print_timing: id 2 | task 3545 | n_gen = 155, tg = 16.96 t/s, tg_3s = 18.06 t/s 5.06.825.336 I slot print_timing: id 3 | task 3609 | n_gen = 100, tg = 17.65 t/s, tg_3s = 17.83 t/s 5.08.014.627 I slot print_timing: id 1 | task 3639 | prompt eval time = 470.65 ms / 101 tokens ( 4.66 ms per token, 214.60 tokens per second) 5.08.014.632 I slot print_timing: id 1 | task 3639 | eval time = 4979.59 ms / 95 tokens ( 52.97 ms per token, 18.88 tokens per second) 5.08.014.633 I slot print_timing: id 1 | task 3639 | total time = 5450.24 ms / 196 tokens 5.08.014.634 I slot print_timing: id 1 | task 3639 | graphs reused = 2925 5.08.014.634 I slot print_timing: id 1 | task 3639 | graph reallocs = 0 / 0 (same size) / (changed size) 5.08.014.689 I slot release: id 1 | task 3639 | stop processing: n_tokens = 1320, truncated = 0 5.08.073.024 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.868 5.08.073.103 I slot launch_slot_: id 1 | task 3738 | processing task, is_child = 0 5.08.858.258 I slot print_timing: id 2 | task 3545 | prompt eval time = 525.36 ms / 133 tokens ( 3.95 ms per token, 253.16 tokens per second) 5.08.858.271 I slot print_timing: id 2 | task 3545 | eval time = 11462.10 ms / 193 tokens ( 59.70 ms per token, 16.75 tokens per second) 5.08.858.273 I slot print_timing: id 2 | task 3545 | total time = 11987.45 ms / 326 tokens 5.08.858.278 I slot print_timing: id 2 | task 3545 | graphs reused = 2928 5.08.858.279 I slot print_timing: id 2 | task 3545 | graph reallocs = 0 / 0 (same size) / (changed size) 5.08.858.356 I slot release: id 2 | task 3545 | stop processing: n_tokens = 1450, truncated = 0 5.08.919.344 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.944 (> 0.100 thold), f_keep = 0.790 5.08.919.400 I slot launch_slot_: id 2 | task 3746 | processing task, is_child = 0 5.09.828.005 I slot print_timing: id 0 | task 3678 | prompt eval time = 427.32 ms / 95 tokens ( 4.50 ms per token, 222.31 tokens per second) 5.09.828.010 I slot print_timing: id 0 | task 3678 | eval time = 4588.57 ms / 76 tokens ( 61.18 ms per token, 16.34 tokens per second) 5.09.828.011 I slot print_timing: id 0 | task 3678 | total time = 5015.90 ms / 171 tokens 5.09.828.011 I slot print_timing: id 0 | task 3678 | graphs reused = 2936 5.09.828.012 I slot print_timing: id 0 | task 3678 | graph reallocs = 0 / 0 (same size) / (changed size) 5.09.828.055 I slot release: id 0 | task 3678 | stop processing: n_tokens = 1295, truncated = 0 5.09.828.483 I slot print_timing: id 3 | task 3609 | n_gen = 143, tg = 16.49 t/s, tg_3s = 14.32 t/s 5.09.872.745 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.885 5.09.872.782 I slot launch_slot_: id 0 | task 3759 | processing task, is_child = 0 5.11.722.836 I slot print_timing: id 3 | task 3609 | prompt eval time = 483.58 ms / 118 tokens ( 4.10 ms per token, 244.01 tokens per second) 5.11.722.842 I slot print_timing: id 3 | task 3609 | eval time = 10505.75 ms / 174 tokens ( 60.73 ms per token, 16.47 tokens per second) 5.11.722.843 I slot print_timing: id 3 | task 3609 | total time = 10989.33 ms / 292 tokens 5.11.722.844 I slot print_timing: id 3 | task 3609 | graphs reused = 2964 5.11.722.845 I slot print_timing: id 3 | task 3609 | graph reallocs = 0 / 0 (same size) / (changed size) 5.11.722.937 I slot release: id 3 | task 3609 | stop processing: n_tokens = 1416, truncated = 0 5.11.769.984 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.942 (> 0.100 thold), f_keep = 0.809 5.11.770.043 I slot launch_slot_: id 3 | task 3791 | processing task, is_child = 0 5.13.251.412 I slot print_timing: id 2 | task 3746 | prompt eval time = 461.85 ms / 89 tokens ( 5.19 ms per token, 192.70 tokens per second) 5.13.251.419 I slot print_timing: id 2 | task 3746 | eval time = 3870.16 ms / 65 tokens ( 60.47 ms per token, 16.54 tokens per second) 5.13.251.419 I slot print_timing: id 2 | task 3746 | total time = 4332.00 ms / 154 tokens 5.13.251.420 I slot print_timing: id 2 | task 3746 | graphs reused = 2984 5.13.251.420 I slot print_timing: id 2 | task 3746 | graph reallocs = 0 / 0 (same size) / (changed size) 5.13.251.464 I slot release: id 2 | task 3746 | stop processing: n_tokens = 1278, truncated = 0 5.13.308.510 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.897 5.13.308.541 I slot launch_slot_: id 2 | task 3816 | processing task, is_child = 0 5.15.050.133 I slot print_timing: id 1 | task 3738 | n_gen = 100, tg = 15.48 t/s, tg_3s = 15.63 t/s 5.15.347.598 I slot print_timing: id 3 | task 3791 | prompt eval time = 440.93 ms / 92 tokens ( 4.79 ms per token, 208.65 tokens per second) 5.15.347.602 I slot print_timing: id 3 | task 3791 | eval time = 3136.61 ms / 56 tokens ( 57.03 ms per token, 17.53 tokens per second) 5.15.347.603 I slot print_timing: id 3 | task 3791 | total time = 3577.54 ms / 148 tokens 5.15.347.603 I slot print_timing: id 3 | task 3791 | graphs reused = 3014 5.15.347.604 I slot print_timing: id 3 | task 3791 | graph reallocs = 0 / 0 (same size) / (changed size) 5.15.347.659 I slot release: id 3 | task 3791 | stop processing: n_tokens = 1272, truncated = 0 5.15.393.106 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.901 5.15.393.160 I slot launch_slot_: id 3 | task 3851 | processing task, is_child = 0 5.16.383.999 I slot print_timing: id 0 | task 3759 | n_gen = 100, tg = 16.29 t/s, tg_3s = 16.46 t/s 5.16.433.609 I slot print_timing: id 0 | task 3759 | prompt eval time = 435.24 ms / 99 tokens ( 4.40 ms per token, 227.46 tokens per second) 5.16.433.614 I slot print_timing: id 0 | task 3759 | eval time = 6125.59 ms / 101 tokens ( 61.26 ms per token, 16.32 tokens per second) 5.16.433.614 I slot print_timing: id 0 | task 3759 | total time = 6560.82 ms / 200 tokens 5.16.433.615 I slot print_timing: id 0 | task 3759 | graphs reused = 3024 5.16.433.615 I slot print_timing: id 0 | task 3759 | graph reallocs = 0 / 0 (same size) / (changed size) 5.16.433.669 I slot release: id 0 | task 3759 | stop processing: n_tokens = 1324, truncated = 0 5.16.478.649 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.943 (> 0.100 thold), f_keep = 0.866 5.16.478.679 I slot launch_slot_: id 0 | task 3866 | processing task, is_child = 0 5.18.091.574 I slot print_timing: id 1 | task 3738 | n_gen = 147, tg = 15.47 t/s, tg_3s = 15.45 t/s 5.18.733.967 I slot print_timing: id 2 | task 3816 | prompt eval time = 503.96 ms / 113 tokens ( 4.46 ms per token, 224.22 tokens per second) 5.18.733.972 I slot print_timing: id 2 | task 3816 | eval time = 4921.45 ms / 86 tokens ( 57.90 ms per token, 17.27 tokens per second) 5.18.733.973 I slot print_timing: id 2 | task 3816 | total time = 5425.42 ms / 199 tokens 5.18.733.973 I slot print_timing: id 2 | task 3816 | graphs reused = 3061 5.18.733.974 I slot print_timing: id 2 | task 3816 | graph reallocs = 0 / 0 (same size) / (changed size) 5.18.734.023 I slot release: id 2 | task 3816 | stop processing: n_tokens = 1323, truncated = 0 5.18.791.394 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 5.18.791.430 I slot launch_slot_: id 2 | task 3907 | processing task, is_child = 0 5.20.933.834 I slot print_timing: id 0 | task 3866 | prompt eval time = 424.81 ms / 90 tokens ( 4.72 ms per token, 211.86 tokens per second) 5.20.933.839 I slot print_timing: id 0 | task 3866 | eval time = 4030.33 ms / 72 tokens ( 56.77 ms per token, 17.62 tokens per second) 5.20.933.842 I slot print_timing: id 0 | task 3866 | total time = 4455.14 ms / 162 tokens 5.20.933.842 I slot print_timing: id 0 | task 3866 | graphs reused = 3091 5.20.933.844 I slot print_timing: id 0 | task 3866 | graph reallocs = 0 / 0 (same size) / (changed size) 5.20.933.931 I slot release: id 0 | task 3866 | stop processing: n_tokens = 1286, truncated = 0 5.20.982.751 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.891 5.20.982.813 I slot launch_slot_: id 0 | task 3942 | processing task, is_child = 0 5.21.360.421 I slot print_timing: id 1 | task 3738 | n_gen = 196, tg = 15.35 t/s, tg_3s = 14.99 t/s 5.21.993.440 I slot print_timing: id 1 | task 3738 | prompt eval time = 579.83 ms / 152 tokens ( 3.81 ms per token, 262.15 tokens per second) 5.21.993.445 I slot print_timing: id 1 | task 3738 | eval time = 13340.50 ms / 208 tokens ( 64.45 ms per token, 15.52 tokens per second) 5.21.993.446 I slot print_timing: id 1 | task 3738 | total time = 13920.33 ms / 360 tokens 5.21.993.446 I slot print_timing: id 1 | task 3738 | graphs reused = 3102 5.21.993.446 I slot print_timing: id 1 | task 3738 | graph reallocs = 0 / 0 (same size) / (changed size) 5.21.993.493 I slot release: id 1 | task 3738 | stop processing: n_tokens = 1484, truncated = 0 5.21.993.783 I slot print_timing: id 3 | task 3851 | n_gen = 100, tg = 16.21 t/s, tg_3s = 16.38 t/s 5.22.050.220 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.901 (> 0.100 thold), f_keep = 0.772 5.22.050.255 I slot launch_slot_: id 1 | task 3957 | processing task, is_child = 0 5.25.036.352 I slot print_timing: id 3 | task 3851 | n_gen = 152, tg = 16.51 t/s, tg_3s = 17.09 t/s 5.25.135.109 I slot print_timing: id 2 | task 3907 | n_gen = 100, tg = 17.20 t/s, tg_3s = 17.37 t/s 5.25.135.264 I slot print_timing: id 3 | task 3851 | prompt eval time = 495.11 ms / 118 tokens ( 4.20 ms per token, 238.33 tokens per second) 5.25.135.266 I slot print_timing: id 3 | task 3851 | eval time = 9246.99 ms / 154 tokens ( 60.44 ms per token, 16.55 tokens per second) 5.25.135.266 I slot print_timing: id 3 | task 3851 | total time = 9742.10 ms / 272 tokens 5.25.135.267 I slot print_timing: id 3 | task 3851 | graphs reused = 3152 5.25.135.267 I slot print_timing: id 3 | task 3851 | graph reallocs = 0 / 0 (same size) / (changed size) 5.25.135.318 I slot release: id 3 | task 3851 | stop processing: n_tokens = 1396, truncated = 0 5.25.179.196 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.821 5.25.179.231 I slot launch_slot_: id 3 | task 4012 | processing task, is_child = 0 5.26.003.988 I slot print_timing: id 0 | task 3942 | prompt eval time = 464.72 ms / 107 tokens ( 4.34 ms per token, 230.25 tokens per second) 5.26.003.993 I slot print_timing: id 0 | task 3942 | eval time = 4556.44 ms / 76 tokens ( 60.75 ms per token, 16.46 tokens per second) 5.26.003.994 I slot print_timing: id 0 | task 3942 | total time = 5021.17 ms / 183 tokens 5.26.003.995 I slot print_timing: id 0 | task 3942 | graphs reused = 3158 5.26.003.995 I slot print_timing: id 0 | task 3942 | graph reallocs = 0 / 0 (same size) / (changed size) 5.26.004.041 I slot release: id 0 | task 3942 | stop processing: n_tokens = 1307, truncated = 0 5.26.048.849 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.877 5.26.048.880 I slot launch_slot_: id 0 | task 4023 | processing task, is_child = 0 5.26.961.696 I slot print_timing: id 2 | task 3907 | prompt eval time = 586.27 ms / 170 tokens ( 3.45 ms per token, 289.97 tokens per second) 5.26.961.702 I slot print_timing: id 2 | task 3907 | eval time = 7583.98 ms / 121 tokens ( 63.20 ms per token, 15.82 tokens per second) 5.26.961.702 I slot print_timing: id 2 | task 3907 | total time = 8170.26 ms / 291 tokens 5.26.961.702 I slot print_timing: id 2 | task 3907 | graphs reused = 3166 5.26.961.703 I slot print_timing: id 2 | task 3907 | graph reallocs = 0 / 0 (same size) / (changed size) 5.26.961.748 I slot release: id 2 | task 3907 | stop processing: n_tokens = 1415, truncated = 0 5.27.018.864 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.810 5.27.018.909 I slot launch_slot_: id 2 | task 4035 | processing task, is_child = 0 5.28.731.534 I slot print_timing: id 1 | task 3957 | n_gen = 100, tg = 16.17 t/s, tg_3s = 16.33 t/s 5.30.093.552 I slot print_timing: id 3 | task 4012 | prompt eval time = 477.03 ms / 109 tokens ( 4.38 ms per token, 228.50 tokens per second) 5.30.093.558 I slot print_timing: id 3 | task 4012 | eval time = 4437.28 ms / 73 tokens ( 61.63 ms per token, 16.23 tokens per second) 5.30.093.559 I slot print_timing: id 3 | task 4012 | total time = 4914.31 ms / 182 tokens 5.30.093.560 I slot print_timing: id 3 | task 4012 | graphs reused = 3216 5.30.093.561 I slot print_timing: id 3 | task 4012 | graph reallocs = 0 / 0 (same size) / (changed size) 5.30.093.658 I slot release: id 3 | task 4012 | stop processing: n_tokens = 1306, truncated = 0 5.30.140.521 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.877 5.30.140.583 I slot launch_slot_: id 3 | task 4090 | processing task, is_child = 0 5.31.067.374 I slot print_timing: id 1 | task 3957 | prompt eval time = 558.24 ms / 147 tokens ( 3.80 ms per token, 263.33 tokens per second) 5.31.067.377 I slot print_timing: id 1 | task 3957 | eval time = 8458.87 ms / 138 tokens ( 61.74 ms per token, 16.20 tokens per second) 5.31.067.377 I slot print_timing: id 1 | task 3957 | total time = 9017.11 ms / 285 tokens 5.31.067.378 I slot print_timing: id 1 | task 3957 | graphs reused = 3223 5.31.067.378 I slot print_timing: id 1 | task 3957 | graph reallocs = 0 / 0 (same size) / (changed size) 5.31.067.428 I slot release: id 1 | task 3957 | stop processing: n_tokens = 1409, truncated = 0 5.31.124.638 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.813 5.31.124.671 I slot launch_slot_: id 1 | task 4102 | processing task, is_child = 0 5.32.785.750 I slot print_timing: id 0 | task 4023 | n_gen = 100, tg = 15.91 t/s, tg_3s = 16.07 t/s 5.33.329.300 I slot print_timing: id 2 | task 4035 | n_gen = 100, tg = 17.05 t/s, tg_3s = 17.22 t/s 5.34.443.754 I slot print_timing: id 2 | task 4035 | prompt eval time = 504.21 ms / 110 tokens ( 4.58 ms per token, 218.16 tokens per second) 5.34.443.761 I slot print_timing: id 2 | task 4035 | eval time = 6920.63 ms / 122 tokens ( 57.20 ms per token, 17.48 tokens per second) 5.34.443.762 I slot print_timing: id 2 | task 4035 | total time = 7424.84 ms / 232 tokens 5.34.443.763 I slot print_timing: id 2 | task 4035 | graphs reused = 3278 5.34.443.764 I slot print_timing: id 2 | task 4035 | graph reallocs = 0 / 0 (same size) / (changed size) 5.34.443.849 I slot release: id 2 | task 4035 | stop processing: n_tokens = 1356, truncated = 0 5.34.505.265 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 5.34.505.339 I slot launch_slot_: id 2 | task 4162 | processing task, is_child = 0 5.35.835.590 I slot print_timing: id 0 | task 4023 | n_gen = 153, tg = 16.39 t/s, tg_3s = 17.38 t/s 5.36.037.557 I slot print_timing: id 0 | task 4023 | prompt eval time = 515.13 ms / 139 tokens ( 3.71 ms per token, 269.83 tokens per second) 5.36.037.562 I slot print_timing: id 0 | task 4023 | eval time = 9473.53 ms / 157 tokens ( 60.73 ms per token, 16.47 tokens per second) 5.36.037.563 I slot print_timing: id 0 | task 4023 | total time = 9988.67 ms / 296 tokens 5.36.037.564 I slot print_timing: id 0 | task 4023 | graphs reused = 3298 5.36.037.565 I slot print_timing: id 0 | task 4023 | graph reallocs = 0 / 0 (same size) / (changed size) 5.36.037.657 I slot release: id 0 | task 4023 | stop processing: n_tokens = 1420, truncated = 0 5.36.086.358 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.807 5.36.086.426 I slot launch_slot_: id 0 | task 4187 | processing task, is_child = 0 5.36.829.221 I slot print_timing: id 3 | task 4090 | n_gen = 100, tg = 16.07 t/s, tg_3s = 16.24 t/s 5.36.979.836 I slot print_timing: id 1 | task 4102 | prompt eval time = 521.79 ms / 122 tokens ( 4.28 ms per token, 233.81 tokens per second) 5.36.979.841 I slot print_timing: id 1 | task 4102 | eval time = 5333.37 ms / 92 tokens ( 58.61 ms per token, 17.06 tokens per second) 5.36.979.842 I slot print_timing: id 1 | task 4102 | total time = 5855.16 ms / 214 tokens 5.36.979.843 I slot print_timing: id 1 | task 4102 | graphs reused = 3306 5.36.979.844 I slot print_timing: id 1 | task 4102 | graph reallocs = 0 / 0 (same size) / (changed size) 5.36.979.937 I slot release: id 1 | task 4102 | stop processing: n_tokens = 1338, truncated = 0 5.37.041.094 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.857 5.37.041.172 I slot launch_slot_: id 1 | task 4199 | processing task, is_child = 0 5.38.424.677 I slot print_timing: id 3 | task 4090 | prompt eval time = 529.44 ms / 134 tokens ( 3.95 ms per token, 253.10 tokens per second) 5.38.424.685 I slot print_timing: id 3 | task 4090 | eval time = 7754.64 ms / 124 tokens ( 63.05 ms per token, 15.86 tokens per second) 5.38.424.686 I slot print_timing: id 3 | task 4090 | total time = 8284.08 ms / 258 tokens 5.38.424.687 I slot print_timing: id 3 | task 4090 | graphs reused = 3323 5.38.424.688 I slot print_timing: id 3 | task 4090 | graph reallocs = 0 / 0 (same size) / (changed size) 5.38.424.831 I slot release: id 3 | task 4090 | stop processing: n_tokens = 1382, truncated = 0 5.38.473.071 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.829 5.38.473.137 I slot launch_slot_: id 3 | task 4221 | processing task, is_child = 0 5.40.579.240 I slot print_timing: id 2 | task 4162 | prompt eval time = 473.20 ms / 96 tokens ( 4.93 ms per token, 202.87 tokens per second) 5.40.579.245 I slot print_timing: id 2 | task 4162 | eval time = 5600.69 ms / 90 tokens ( 62.93 ms per token, 15.89 tokens per second) 5.40.579.246 I slot print_timing: id 2 | task 4162 | total time = 6073.89 ms / 186 tokens 5.40.579.247 I slot print_timing: id 2 | task 4162 | graphs reused = 3354 5.40.579.247 I slot print_timing: id 2 | task 4162 | graph reallocs = 0 / 0 (same size) / (changed size) 5.40.579.297 I slot release: id 2 | task 4162 | stop processing: n_tokens = 1310, truncated = 0 5.40.636.333 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.875 5.40.636.369 I slot launch_slot_: id 2 | task 4258 | processing task, is_child = 0 5.42.070.647 I slot print_timing: id 0 | task 4187 | prompt eval time = 481.06 ms / 111 tokens ( 4.33 ms per token, 230.74 tokens per second) 5.42.070.650 I slot print_timing: id 0 | task 4187 | eval time = 5503.15 ms / 86 tokens ( 64.74 ms per token, 15.45 tokens per second) 5.42.070.650 I slot print_timing: id 0 | task 4187 | total time = 5984.21 ms / 197 tokens 5.42.070.651 I slot print_timing: id 0 | task 4187 | graphs reused = 3370 5.42.070.651 I slot print_timing: id 0 | task 4187 | graph reallocs = 0 / 0 (same size) / (changed size) 5.42.070.701 I slot release: id 0 | task 4187 | stop processing: n_tokens = 1321, truncated = 0 5.42.070.846 I slot print_timing: id 1 | task 4199 | prompt eval time = 477.62 ms / 101 tokens ( 4.73 ms per token, 211.47 tokens per second) 5.42.070.848 I slot print_timing: id 1 | task 4199 | eval time = 4552.05 ms / 75 tokens ( 61.51 ms per token, 16.26 tokens per second) 5.42.070.848 I slot print_timing: id 1 | task 4199 | total time = 5029.66 ms / 176 tokens 5.42.070.848 I slot print_timing: id 1 | task 4199 | graphs reused = 3370 5.42.070.849 I slot print_timing: id 1 | task 4199 | graph reallocs = 0 / 0 (same size) / (changed size) 5.42.070.881 I slot release: id 1 | task 4199 | stop processing: n_tokens = 1300, truncated = 0 5.42.107.414 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.868 5.42.107.446 I slot launch_slot_: id 0 | task 4279 | processing task, is_child = 0 5.42.107.528 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.051 MiB) 5.42.107.531 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.618 MiB) 5.42.107.536 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.716 MiB) 5.42.128.246 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.882 5.42.128.285 I slot launch_slot_: id 1 | task 4280 | processing task, is_child = 0 5.44.994.516 I slot print_timing: id 3 | task 4221 | n_gen = 100, tg = 16.37 t/s, tg_3s = 16.53 t/s 5.46.258.140 I slot print_timing: id 0 | task 4279 | prompt eval time = 738.62 ms / 128 tokens ( 5.77 ms per token, 173.30 tokens per second) 5.46.258.144 I slot print_timing: id 0 | task 4279 | eval time = 3391.22 ms / 69 tokens ( 49.87 ms per token, 20.05 tokens per second) 5.46.258.145 I slot print_timing: id 0 | task 4279 | total time = 4129.84 ms / 197 tokens 5.46.258.146 I slot print_timing: id 0 | task 4279 | graphs reused = 3438 5.46.258.147 I slot print_timing: id 0 | task 4279 | graph reallocs = 0 / 0 (same size) / (changed size) 5.46.258.222 I slot release: id 0 | task 4279 | stop processing: n_tokens = 1321, truncated = 0 5.46.306.151 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.868 5.46.306.213 I slot launch_slot_: id 0 | task 4352 | processing task, is_child = 0 5.46.843.588 I slot print_timing: id 3 | task 4221 | prompt eval time = 472.48 ms / 108 tokens ( 4.37 ms per token, 228.58 tokens per second) 5.46.843.594 I slot print_timing: id 3 | task 4221 | eval time = 7897.96 ms / 130 tokens ( 61.22 ms per token, 16.33 tokens per second) 5.46.843.594 I slot print_timing: id 3 | task 4221 | total time = 8370.44 ms / 238 tokens 5.46.843.595 I slot print_timing: id 3 | task 4221 | graphs reused = 3440 5.46.843.595 I slot print_timing: id 3 | task 4221 | graph reallocs = 0 / 0 (same size) / (changed size) 5.46.843.640 I slot release: id 3 | task 4221 | stop processing: n_tokens = 1362, truncated = 0 5.46.887.721 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.904 (> 0.100 thold), f_keep = 0.841 5.46.887.756 I slot launch_slot_: id 3 | task 4358 | processing task, is_child = 0 5.47.560.983 I slot print_timing: id 2 | task 4258 | n_gen = 100, tg = 15.63 t/s, tg_3s = 15.79 t/s 5.48.105.030 I slot print_timing: id 2 | task 4258 | prompt eval time = 592.50 ms / 166 tokens ( 3.57 ms per token, 280.17 tokens per second) 5.48.105.035 I slot print_timing: id 2 | task 4258 | eval time = 6876.15 ms / 111 tokens ( 62.51 ms per token, 16.00 tokens per second) 5.48.105.036 I slot print_timing: id 2 | task 4258 | total time = 7468.65 ms / 277 tokens 5.48.105.036 I slot print_timing: id 2 | task 4258 | graphs reused = 3453 5.48.105.037 I slot print_timing: id 2 | task 4258 | graph reallocs = 0 / 0 (same size) / (changed size) 5.48.105.121 I slot release: id 2 | task 4258 | stop processing: n_tokens = 1401, truncated = 0 5.48.167.169 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.818 5.48.167.310 I slot launch_slot_: id 2 | task 4376 | processing task, is_child = 0 5.48.837.882 I slot print_timing: id 1 | task 4280 | prompt eval time = 735.54 ms / 110 tokens ( 6.69 ms per token, 149.55 tokens per second) 5.48.837.887 I slot print_timing: id 1 | task 4280 | eval time = 5970.76 ms / 98 tokens ( 61.55 ms per token, 16.25 tokens per second) 5.48.837.888 I slot print_timing: id 1 | task 4280 | total time = 6706.30 ms / 208 tokens 5.48.837.888 I slot print_timing: id 1 | task 4280 | graphs reused = 3456 5.48.837.889 I slot print_timing: id 1 | task 4280 | graph reallocs = 0 / 0 (same size) / (changed size) 5.48.837.936 I slot release: id 1 | task 4280 | stop processing: n_tokens = 1332, truncated = 0 5.51.386.879 I slot print_timing: id 0 | task 4352 | prompt eval time = 435.74 ms / 95 tokens ( 4.59 ms per token, 218.02 tokens per second) 5.51.386.884 I slot print_timing: id 0 | task 4352 | eval time = 4644.91 ms / 72 tokens ( 65.42 ms per token, 15.29 tokens per second) 5.51.386.885 I slot print_timing: id 0 | task 4352 | total time = 5080.66 ms / 167 tokens 5.51.386.885 I slot print_timing: id 0 | task 4352 | graphs reused = 3456 5.51.386.886 I slot print_timing: id 0 | task 4352 | graph reallocs = 0 / 0 (same size) / (changed size) 5.51.386.927 I slot release: id 0 | task 4352 | stop processing: n_tokens = 1291, truncated = 0 5.52.382.541 I slot print_timing: id 2 | task 4376 | prompt eval time = 470.89 ms / 96 tokens ( 4.91 ms per token, 203.87 tokens per second) 5.52.382.551 I slot print_timing: id 2 | task 4376 | eval time = 3744.32 ms / 79 tokens ( 48.00 ms per token, 20.83 tokens per second) 5.52.382.552 I slot print_timing: id 2 | task 4376 | total time = 4215.21 ms / 175 tokens 5.52.382.553 I slot print_timing: id 2 | task 4376 | graphs reused = 3485 5.52.382.554 I slot print_timing: id 2 | task 4376 | graph reallocs = 0 / 0 (same size) / (changed size) 5.52.382.615 I slot release: id 2 | task 4376 | stop processing: n_tokens = 1299, truncated = 0 5.52.469.203 I slot print_timing: id 3 | task 4358 | n_gen = 100, tg = 19.57 t/s, tg_3s = 19.77 t/s 5.52.489.656 I slot print_timing: id 3 | task 4358 | prompt eval time = 522.83 ms / 142 tokens ( 3.68 ms per token, 271.60 tokens per second) 5.52.489.661 I slot print_timing: id 3 | task 4358 | eval time = 5079.06 ms / 101 tokens ( 50.79 ms per token, 19.69 tokens per second) 5.52.489.663 I slot print_timing: id 3 | task 4358 | total time = 5601.90 ms / 243 tokens 5.52.489.664 I slot print_timing: id 3 | task 4358 | graphs reused = 3489 5.52.489.664 I slot print_timing: id 3 | task 4358 | graph reallocs = 0 / 0 (same size) / (changed size) 5.52.489.718 I slot release: id 3 | task 4358 | stop processing: n_tokens = 1367, truncated = 0 5.52.509.223 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1332, t_last = 388790258417 5.52.509.326 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.892 MiB) 5.52.509.331 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.875 MiB) 5.52.531.550 I slot launch_slot_: id 1 | task 4462 | processing task, is_child = 0 5.52.531.631 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.149 MiB) 5.52.531.639 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.403 MiB) 5.52.531.640 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.758 MiB) 5.52.552.918 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.638 MiB) 5.52.552.927 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.146 MiB) 5.52.579.010 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.915 MiB) 5.52.579.016 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.266 MiB) 5.52.579.017 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.736 MiB) 5.52.602.639 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1291, t_last = 388792807408 5.52.602.779 I slot launch_slot_: id 0 | task 4463 | processing task, is_child = 0 5.52.602.899 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1299, t_last = 388793803096 5.52.602.986 I slot launch_slot_: id 2 | task 4464 | processing task, is_child = 0 5.52.603.048 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1367, t_last = 388793910199 5.52.603.136 I slot launch_slot_: id 3 | task 4465 | processing task, is_child = 0 5.56.562.233 I slot print_timing: id 0 | task 4463 | prompt processing, n_tokens = 290, progress = 0.36, t = 3.96 s / 73.25 tokens per second 5.56.822.925 I slot print_timing: id 1 | task 4462 | prompt processing, n_tokens = 656, progress = 0.84, t = 3.96 s / 165.70 tokens per second 5.56.826.380 I slot print_timing: id 2 | task 4464 | prompt processing, n_tokens = 471, progress = 0.48, t = 3.96 s / 118.97 tokens per second 5.56.828.340 I slot print_timing: id 3 | task 4465 | prompt processing, n_tokens = 436, progress = 0.46, t = 3.96 s / 110.13 tokens per second 5.59.297.773 I slot print_timing: id 0 | task 4463 | prompt processing, n_tokens = 642, progress = 0.80, t = 6.69 s / 95.90 tokens per second 5.59.347.660 I slot print_timing: id 1 | task 4462 | prompt processing, n_tokens = 775, progress = 0.99, t = 6.69 s / 115.77 tokens per second 5.59.351.271 I slot print_timing: id 2 | task 4464 | prompt processing, n_tokens = 877, progress = 0.89, t = 6.69 s / 131.00 tokens per second 5.59.353.261 I slot print_timing: id 3 | task 4465 | prompt processing, n_tokens = 835, progress = 0.88, t = 6.69 s / 124.73 tokens per second 6.00.374.069 I slot print_timing: id 0 | task 4463 | prompt processing, n_tokens = 802, progress = 1.00, t = 7.77 s / 103.21 tokens per second 6.00.377.115 I slot print_timing: id 2 | task 4464 | prompt processing, n_tokens = 983, progress = 1.00, t = 7.77 s / 126.50 tokens per second 6.00.379.105 I slot print_timing: id 3 | task 4465 | prompt processing, n_tokens = 948, progress = 1.00, t = 7.77 s / 122.00 tokens per second 6.00.514.627 I slot print_timing: id 1 | task 4462 | prompt eval time = 7770.81 ms / 779 tokens ( 9.98 ms per token, 100.25 tokens per second) 6.00.514.630 I slot print_timing: id 1 | task 4462 | eval time = 140.57 ms / 2 tokens ( 140.57 ms per token, 7.11 tokens per second) 6.00.514.630 I slot print_timing: id 1 | task 4462 | total time = 7911.37 ms / 781 tokens 6.00.514.630 I slot print_timing: id 1 | task 4462 | graphs reused = 3489 6.00.514.631 I slot print_timing: id 1 | task 4462 | graph reallocs = 0 / 0 (same size) / (changed size) 6.00.514.669 I slot release: id 1 | task 4462 | stop processing: n_tokens = 780, truncated = 0 6.00.571.373 I slot print_timing: id 0 | task 4463 | prompt eval time = 7911.30 ms / 806 tokens ( 9.82 ms per token, 101.88 tokens per second) 6.00.571.379 I slot print_timing: id 0 | task 4463 | eval time = 56.93 ms / 2 tokens ( 56.93 ms per token, 17.57 tokens per second) 6.00.571.380 I slot print_timing: id 0 | task 4463 | total time = 7968.23 ms / 808 tokens 6.00.571.380 I slot print_timing: id 0 | task 4463 | graphs reused = 3489 6.00.571.380 I slot print_timing: id 0 | task 4463 | graph reallocs = 0 / 0 (same size) / (changed size) 6.00.571.414 I slot release: id 0 | task 4463 | stop processing: n_tokens = 807, truncated = 0 6.00.571.638 I slot print_timing: id 2 | task 4464 | prompt eval time = 7911.57 ms / 987 tokens ( 8.02 ms per token, 124.75 tokens per second) 6.00.571.640 I slot print_timing: id 2 | task 4464 | eval time = 56.73 ms / 2 tokens ( 56.73 ms per token, 17.63 tokens per second) 6.00.571.641 I slot print_timing: id 2 | task 4464 | total time = 7968.31 ms / 989 tokens 6.00.571.641 I slot print_timing: id 2 | task 4464 | graphs reused = 3489 6.00.571.641 I slot print_timing: id 2 | task 4464 | graph reallocs = 0 / 0 (same size) / (changed size) 6.00.571.675 I slot release: id 2 | task 4464 | stop processing: n_tokens = 988, truncated = 0 6.00.571.839 I slot print_timing: id 3 | task 4465 | prompt eval time = 7911.73 ms / 952 tokens ( 8.31 ms per token, 120.33 tokens per second) 6.00.571.841 I slot print_timing: id 3 | task 4465 | eval time = 56.69 ms / 2 tokens ( 56.69 ms per token, 17.64 tokens per second) 6.00.571.841 I slot print_timing: id 3 | task 4465 | total time = 7968.42 ms / 954 tokens 6.00.571.841 I slot print_timing: id 3 | task 4465 | graphs reused = 3489 6.00.571.842 I slot print_timing: id 3 | task 4465 | graph reallocs = 0 / 0 (same size) / (changed size) 6.00.571.870 I slot release: id 3 | task 4465 | stop processing: n_tokens = 953, truncated = 0 6.00.571.874 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 780, t_last = 388801935151 6.00.571.922 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.286 MiB) 6.00.571.929 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.032 MiB) 6.00.571.932 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.560 MiB) 6.00.594.828 I slot launch_slot_: id 1 | task 4473 | processing task, is_child = 0 6.00.594.877 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.716 MiB) 6.00.594.878 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.560 MiB) 6.00.666.274 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.775 MiB) 6.00.666.282 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.677 MiB) 6.00.666.284 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.658 MiB) 6.01.292.247 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.641 MiB) 6.01.292.268 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.875 MiB) 6.01.922.427 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 807, t_last = 388801991895 6.01.922.754 I slot launch_slot_: id 0 | task 4474 | processing task, is_child = 0 6.01.922.846 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 988, t_last = 388801992156 6.01.922.935 I slot launch_slot_: id 2 | task 4475 | processing task, is_child = 0 6.01.922.984 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 953, t_last = 388801992351 6.01.923.068 I slot launch_slot_: id 3 | task 4476 | processing task, is_child = 0 6.07.157.252 I slot print_timing: id 0 | task 4474 | prompt processing, n_tokens = 696, progress = 0.87, t = 5.23 s / 132.97 tokens per second 6.07.219.636 I slot print_timing: id 1 | task 4473 | prompt processing, n_tokens = 696, progress = 0.87, t = 5.23 s / 132.98 tokens per second 6.07.233.030 I slot print_timing: id 2 | task 4475 | prompt processing, n_tokens = 696, progress = 0.81, t = 5.23 s / 132.98 tokens per second 6.07.242.829 I slot print_timing: id 3 | task 4476 | prompt processing, n_tokens = 696, progress = 0.82, t = 5.23 s / 132.98 tokens per second 6.08.324.445 I slot print_timing: id 0 | task 4474 | prompt processing, n_tokens = 800, progress = 1.00, t = 6.40 s / 124.97 tokens per second 6.08.387.218 I slot print_timing: id 1 | task 4473 | prompt processing, n_tokens = 797, progress = 1.00, t = 6.40 s / 124.51 tokens per second 6.08.393.797 I slot print_timing: id 2 | task 4475 | prompt processing, n_tokens = 851, progress = 1.00, t = 6.40 s / 132.94 tokens per second 6.08.399.785 I slot print_timing: id 3 | task 4476 | prompt processing, n_tokens = 842, progress = 1.00, t = 6.40 s / 131.54 tokens per second 6.08.566.958 I slot print_timing: id 0 | task 4474 | prompt eval time = 6592.08 ms / 804 tokens ( 8.20 ms per token, 121.96 tokens per second) 6.08.566.960 I slot print_timing: id 0 | task 4474 | eval time = 51.79 ms / 2 tokens ( 51.79 ms per token, 19.31 tokens per second) 6.08.566.961 I slot print_timing: id 0 | task 4474 | total time = 6643.88 ms / 806 tokens 6.08.566.961 I slot print_timing: id 0 | task 4474 | graphs reused = 3489 6.08.566.962 I slot print_timing: id 0 | task 4474 | graph reallocs = 0 / 0 (same size) / (changed size) 6.08.567.105 I slot release: id 0 | task 4474 | stop processing: n_tokens = 805, truncated = 0 6.08.567.317 I slot print_timing: id 1 | task 4473 | prompt eval time = 6592.34 ms / 801 tokens ( 8.23 ms per token, 121.50 tokens per second) 6.08.567.319 I slot print_timing: id 1 | task 4473 | eval time = 51.79 ms / 2 tokens ( 51.79 ms per token, 19.31 tokens per second) 6.08.567.319 I slot print_timing: id 1 | task 4473 | total time = 6644.13 ms / 803 tokens 6.08.567.320 I slot print_timing: id 1 | task 4473 | graphs reused = 3489 6.08.567.320 I slot print_timing: id 1 | task 4473 | graph reallocs = 0 / 0 (same size) / (changed size) 6.08.567.356 I slot release: id 1 | task 4473 | stop processing: n_tokens = 802, truncated = 0 6.08.567.610 I slot print_timing: id 2 | task 4475 | prompt eval time = 6592.67 ms / 855 tokens ( 7.71 ms per token, 129.69 tokens per second) 6.08.567.616 I slot print_timing: id 2 | task 4475 | eval time = 51.69 ms / 2 tokens ( 51.69 ms per token, 19.35 tokens per second) 6.08.567.616 I slot print_timing: id 2 | task 4475 | total time = 6644.36 ms / 857 tokens 6.08.567.617 I slot print_timing: id 2 | task 4475 | graphs reused = 3489 6.08.567.617 I slot print_timing: id 2 | task 4475 | graph reallocs = 0 / 0 (same size) / (changed size) 6.08.567.645 I slot release: id 2 | task 4475 | stop processing: n_tokens = 856, truncated = 0 6.08.567.814 I slot print_timing: id 3 | task 4476 | prompt eval time = 6593.06 ms / 846 tokens ( 7.79 ms per token, 128.32 tokens per second) 6.08.567.817 I slot print_timing: id 3 | task 4476 | eval time = 51.45 ms / 2 tokens ( 51.45 ms per token, 19.44 tokens per second) 6.08.567.817 I slot print_timing: id 3 | task 4476 | total time = 6644.50 ms / 848 tokens 6.08.567.818 I slot print_timing: id 3 | task 4476 | graphs reused = 3489 6.08.567.818 I slot print_timing: id 3 | task 4476 | graph reallocs = 0 / 0 (same size) / (changed size) 6.08.567.864 I slot release: id 3 | task 4476 | stop processing: n_tokens = 847, truncated = 0 6.08.578.288 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 6.08.578.381 I slot launch_slot_: id 0 | task 4485 | processing task, is_child = 0 6.08.578.430 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.264 MiB) 6.08.578.442 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.797 MiB) 6.08.578.449 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.032 MiB) 6.08.629.365 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.110 MiB) 6.08.629.378 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.853 MiB) 6.08.629.384 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.091 MiB) 6.08.670.106 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.032 MiB) 6.08.670.120 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.325 MiB) 6.08.725.871 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 802, t_last = 388809987837 6.08.725.985 I slot launch_slot_: id 1 | task 4484 | processing task, is_child = 0 6.08.726.078 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 856, t_last = 388809988126 6.08.726.145 I slot launch_slot_: id 2 | task 4486 | processing task, is_child = 0 6.08.726.187 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 847, t_last = 388809988346 6.08.726.254 I slot launch_slot_: id 3 | task 4487 | processing task, is_child = 0 6.11.755.161 I slot print_timing: id 0 | task 4485 | prompt eval time = 2374.84 ms / 129 tokens ( 18.41 ms per token, 54.32 tokens per second) 6.11.755.164 I slot print_timing: id 0 | task 4485 | eval time = 654.06 ms / 2 tokens ( 654.06 ms per token, 1.53 tokens per second) 6.11.755.164 I slot print_timing: id 0 | task 4485 | total time = 3028.90 ms / 131 tokens 6.11.755.165 I slot print_timing: id 0 | task 4485 | graphs reused = 3489 6.11.755.165 I slot print_timing: id 0 | task 4485 | graph reallocs = 0 / 0 (same size) / (changed size) 6.11.755.210 I slot release: id 0 | task 4485 | stop processing: n_tokens = 826, truncated = 0 6.11.755.220 I slot print_timing: id 1 | task 4484 | prompt processing, n_tokens = 447, progress = 0.46, t = 3.03 s / 147.75 tokens per second 6.11.758.737 I slot print_timing: id 2 | task 4486 | prompt processing, n_tokens = 380, progress = 0.42, t = 3.03 s / 125.61 tokens per second 6.11.761.492 I slot print_timing: id 3 | task 4487 | prompt processing, n_tokens = 364, progress = 0.41, t = 3.03 s / 120.32 tokens per second 6.13.901.595 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 826, t_last = 388813175691 6.13.901.666 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.345 MiB) 6.13.901.680 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.993 MiB) 6.13.901.687 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.384 MiB) 6.13.993.631 I slot launch_slot_: id 0 | task 4492 | processing task, is_child = 0 6.13.993.735 I slot print_timing: id 1 | task 4484 | prompt processing, n_tokens = 831, progress = 0.86, t = 5.17 s / 160.67 tokens per second 6.13.995.734 I slot print_timing: id 2 | task 4486 | prompt processing, n_tokens = 754, progress = 0.84, t = 5.17 s / 145.79 tokens per second 6.13.997.702 I slot print_timing: id 3 | task 4487 | prompt processing, n_tokens = 754, progress = 0.86, t = 5.17 s / 145.79 tokens per second 6.15.283.464 I slot print_timing: id 1 | task 4484 | prompt processing, n_tokens = 959, progress = 1.00, t = 6.49 s / 147.84 tokens per second 6.15.296.477 I slot print_timing: id 2 | task 4486 | prompt processing, n_tokens = 892, progress = 1.00, t = 6.49 s / 137.51 tokens per second 6.15.308.416 I slot print_timing: id 3 | task 4487 | prompt processing, n_tokens = 876, progress = 1.00, t = 6.49 s / 135.05 tokens per second 6.16.188.480 I slot print_timing: id 1 | task 4484 | prompt eval time = 7162.45 ms / 963 tokens ( 7.44 ms per token, 134.45 tokens per second) 6.16.188.487 I slot print_timing: id 1 | task 4484 | eval time = 296.49 ms / 2 tokens ( 296.49 ms per token, 3.37 tokens per second) 6.16.188.487 I slot print_timing: id 1 | task 4484 | total time = 7458.93 ms / 965 tokens 6.16.188.488 I slot print_timing: id 1 | task 4484 | graphs reused = 3489 6.16.188.488 I slot print_timing: id 1 | task 4484 | graph reallocs = 0 / 0 (same size) / (changed size) 6.16.188.564 I slot release: id 1 | task 4484 | stop processing: n_tokens = 964, truncated = 0 6.16.188.721 I slot print_timing: id 2 | task 4486 | prompt eval time = 7162.61 ms / 896 tokens ( 7.99 ms per token, 125.09 tokens per second) 6.16.188.726 I slot print_timing: id 2 | task 4486 | eval time = 296.51 ms / 2 tokens ( 296.51 ms per token, 3.37 tokens per second) 6.16.188.726 I slot print_timing: id 2 | task 4486 | total time = 7459.12 ms / 898 tokens 6.16.188.727 I slot print_timing: id 2 | task 4486 | graphs reused = 3489 6.16.188.727 I slot print_timing: id 2 | task 4486 | graph reallocs = 0 / 0 (same size) / (changed size) 6.16.188.814 I slot release: id 2 | task 4486 | stop processing: n_tokens = 897, truncated = 0 6.16.189.098 I slot print_timing: id 3 | task 4487 | prompt eval time = 7162.97 ms / 880 tokens ( 8.14 ms per token, 122.85 tokens per second) 6.16.189.101 I slot print_timing: id 3 | task 4487 | eval time = 296.46 ms / 2 tokens ( 296.46 ms per token, 3.37 tokens per second) 6.16.189.101 I slot print_timing: id 3 | task 4487 | total time = 7459.43 ms / 882 tokens 6.16.189.101 I slot print_timing: id 3 | task 4487 | graphs reused = 3489 6.16.189.102 I slot print_timing: id 3 | task 4487 | graph reallocs = 0 / 0 (same size) / (changed size) 6.16.189.137 I slot release: id 3 | task 4487 | stop processing: n_tokens = 881, truncated = 0 6.16.201.503 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 964, t_last = 388817609047 6.16.201.557 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.736 MiB) 6.16.201.567 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.931 MiB) 6.16.936.809 I slot launch_slot_: id 1 | task 4497 | processing task, is_child = 0 6.16.936.860 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.660 MiB) 6.16.936.876 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.247 MiB) 6.16.936.884 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.205 MiB) 6.16.983.623 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.677 MiB) 6.16.983.643 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.071 MiB) 6.16.983.648 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.462 MiB) 6.17.034.964 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 897, t_last = 388817609296 6.17.035.067 I slot launch_slot_: id 2 | task 4498 | processing task, is_child = 0 6.17.035.111 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 881, t_last = 388817609618 6.17.035.172 I slot launch_slot_: id 3 | task 4499 | processing task, is_child = 0 6.18.063.954 I slot print_timing: id 0 | task 4492 | prompt processing, n_tokens = 983, progress = 1.00, t = 4.07 s / 241.51 tokens per second 6.20.898.661 I slot print_timing: id 0 | task 4492 | prompt eval time = 5453.40 ms / 987 tokens ( 5.53 ms per token, 180.99 tokens per second) 6.20.898.667 I slot print_timing: id 0 | task 4492 | eval time = 1451.61 ms / 2 tokens ( 1451.61 ms per token, 0.69 tokens per second) 6.20.898.667 I slot print_timing: id 0 | task 4492 | total time = 6905.01 ms / 989 tokens 6.20.898.667 I slot print_timing: id 0 | task 4492 | graphs reused = 3489 6.20.898.668 I slot print_timing: id 0 | task 4492 | graph reallocs = 0 / 0 (same size) / (changed size) 6.20.898.733 I slot release: id 0 | task 4492 | stop processing: n_tokens = 988, truncated = 0 6.20.898.745 I slot print_timing: id 1 | task 4497 | prompt processing, n_tokens = 506, progress = 0.50, t = 3.85 s / 131.40 tokens per second 6.20.901.583 I slot print_timing: id 2 | task 4498 | prompt processing, n_tokens = 408, progress = 0.44, t = 3.85 s / 105.96 tokens per second 6.20.903.503 I slot print_timing: id 3 | task 4499 | prompt processing, n_tokens = 753, progress = 0.42, t = 3.85 s / 195.55 tokens per second 6.22.937.338 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 988, t_last = 388822319214 6.22.937.399 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 339.584 MiB) 6.23.350.296 I slot launch_slot_: id 0 | task 4504 | processing task, is_child = 0 6.23.350.378 I slot print_timing: id 1 | task 4497 | prompt processing, n_tokens = 872, progress = 0.85, t = 5.89 s / 148.06 tokens per second 6.23.352.264 I slot print_timing: id 2 | task 4498 | prompt processing, n_tokens = 753, progress = 0.81, t = 5.89 s / 127.85 tokens per second 6.23.354.135 I slot print_timing: id 3 | task 4499 | prompt processing, n_tokens = 1264, progress = 0.71, t = 5.89 s / 214.62 tokens per second 6.25.466.241 I slot print_timing: id 1 | task 4497 | prompt processing, n_tokens = 1018, progress = 1.00, t = 7.74 s / 131.48 tokens per second 6.25.468.495 I slot print_timing: id 2 | task 4498 | prompt processing, n_tokens = 920, progress = 1.00, t = 7.74 s / 118.83 tokens per second 6.25.470.702 I slot print_timing: id 3 | task 4499 | prompt processing, n_tokens = 1776, progress = 1.00, t = 7.74 s / 229.39 tokens per second 6.26.372.342 I slot print_timing: id 1 | task 4497 | prompt eval time = 8917.28 ms / 1022 tokens ( 8.73 ms per token, 114.61 tokens per second) 6.26.372.347 I slot print_timing: id 1 | task 4497 | eval time = 407.36 ms / 2 tokens ( 407.36 ms per token, 2.45 tokens per second) 6.26.372.348 I slot print_timing: id 1 | task 4497 | total time = 9324.64 ms / 1024 tokens 6.26.372.348 I slot print_timing: id 1 | task 4497 | graphs reused = 3489 6.26.372.349 I slot print_timing: id 1 | task 4497 | graph reallocs = 0 / 0 (same size) / (changed size) 6.26.372.394 I slot release: id 1 | task 4497 | stop processing: n_tokens = 1023, truncated = 0 6.26.372.559 I slot print_timing: id 2 | task 4498 | prompt eval time = 8917.39 ms / 924 tokens ( 9.65 ms per token, 103.62 tokens per second) 6.26.372.561 I slot print_timing: id 2 | task 4498 | eval time = 407.41 ms / 2 tokens ( 407.41 ms per token, 2.45 tokens per second) 6.26.372.562 I slot print_timing: id 2 | task 4498 | total time = 9324.79 ms / 926 tokens 6.26.372.562 I slot print_timing: id 2 | task 4498 | graphs reused = 3489 6.26.372.562 I slot print_timing: id 2 | task 4498 | graph reallocs = 0 / 0 (same size) / (changed size) 6.26.372.621 I slot release: id 2 | task 4498 | stop processing: n_tokens = 925, truncated = 0 6.26.372.866 I slot print_timing: id 3 | task 4499 | prompt eval time = 8917.51 ms / 1780 tokens ( 5.01 ms per token, 199.61 tokens per second) 6.26.372.869 I slot print_timing: id 3 | task 4499 | eval time = 407.53 ms / 2 tokens ( 407.53 ms per token, 2.45 tokens per second) 6.26.372.869 I slot print_timing: id 3 | task 4499 | total time = 9325.04 ms / 1782 tokens 6.26.372.869 I slot print_timing: id 3 | task 4499 | graphs reused = 3489 6.26.372.870 I slot print_timing: id 3 | task 4499 | graph reallocs = 0 / 0 (same size) / (changed size) 6.26.372.977 I slot release: id 3 | task 4499 | stop processing: n_tokens = 1781, truncated = 0 6.26.372.986 I slot print_timing: id 0 | task 4504 | prompt processing, n_tokens = 421, progress = 0.45, t = 3.02 s / 139.32 tokens per second 6.26.390.363 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1023, t_last = 388827792875 6.26.390.421 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 340.132 MiB) 6.27.038.205 I slot launch_slot_: id 1 | task 4509 | processing task, is_child = 0 6.27.038.266 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 339.076 MiB) 6.27.092.451 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 341.344 MiB) 6.27.134.941 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 925, t_last = 388827793104 6.27.135.046 I slot launch_slot_: id 2 | task 4510 | processing task, is_child = 0 6.27.135.117 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1781, t_last = 388827793459 6.27.135.207 I slot launch_slot_: id 3 | task 4511 | processing task, is_child = 0 6.27.135.214 I slot print_timing: id 0 | task 4504 | prompt processing, n_tokens = 753, progress = 0.80, t = 3.04 s / 247.69 tokens per second 6.28.214.780 I slot print_timing: id 0 | task 4504 | prompt processing, n_tokens = 933, progress = 1.00, t = 4.86 s / 191.80 tokens per second 6.31.221.265 I slot print_timing: id 0 | task 4504 | prompt eval time = 6012.69 ms / 937 tokens ( 6.42 ms per token, 155.84 tokens per second) 6.31.221.270 I slot print_timing: id 0 | task 4504 | eval time = 1858.26 ms / 2 tokens ( 1858.26 ms per token, 0.54 tokens per second) 6.31.221.271 I slot print_timing: id 0 | task 4504 | total time = 7870.95 ms / 939 tokens 6.31.221.271 I slot print_timing: id 0 | task 4504 | graphs reused = 3489 6.31.221.272 I slot print_timing: id 0 | task 4504 | graph reallocs = 0 / 0 (same size) / (changed size) 6.31.221.321 I slot release: id 0 | task 4504 | stop processing: n_tokens = 938, truncated = 0 6.31.221.332 I slot print_timing: id 1 | task 4509 | prompt processing, n_tokens = 364, progress = 0.41, t = 4.07 s / 89.34 tokens per second 6.31.224.258 I slot print_timing: id 2 | task 4510 | prompt processing, n_tokens = 603, progress = 0.85, t = 4.07 s / 148.01 tokens per second 6.31.226.744 I slot print_timing: id 3 | task 4511 | prompt processing, n_tokens = 603, progress = 0.81, t = 4.07 s / 148.01 tokens per second 6.32.458.001 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 938, t_last = 388832641802 6.32.458.062 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 340.152 MiB) 6.32.615.099 I slot launch_slot_: id 0 | task 4516 | processing task, is_child = 0 6.32.615.266 I slot print_timing: id 1 | task 4509 | prompt processing, n_tokens = 769, progress = 0.87, t = 5.31 s / 144.79 tokens per second 6.32.618.536 I slot print_timing: id 2 | task 4510 | prompt processing, n_tokens = 709, progress = 0.99, t = 5.31 s / 133.49 tokens per second 6.32.622.003 I slot print_timing: id 3 | task 4511 | prompt processing, n_tokens = 737, progress = 0.99, t = 5.31 s / 138.77 tokens per second 6.33.282.230 I slot print_timing: id 1 | task 4509 | prompt processing, n_tokens = 876, progress = 1.00, t = 6.13 s / 142.85 tokens per second 6.33.648.673 I slot print_timing: id 2 | task 4510 | prompt eval time = 6132.32 ms / 713 tokens ( 8.60 ms per token, 116.27 tokens per second) 6.33.648.679 I slot print_timing: id 2 | task 4510 | eval time = 369.43 ms / 2 tokens ( 369.43 ms per token, 2.71 tokens per second) 6.33.648.679 I slot print_timing: id 2 | task 4510 | total time = 6501.75 ms / 715 tokens 6.33.648.679 I slot print_timing: id 2 | task 4510 | graphs reused = 3489 6.33.648.680 I slot print_timing: id 2 | task 4510 | graph reallocs = 0 / 0 (same size) / (changed size) 6.33.648.722 I slot release: id 2 | task 4510 | stop processing: n_tokens = 714, truncated = 0 6.33.648.972 I slot print_timing: id 3 | task 4511 | prompt eval time = 6132.44 ms / 741 tokens ( 8.28 ms per token, 120.83 tokens per second) 6.33.648.979 I slot print_timing: id 3 | task 4511 | eval time = 369.55 ms / 2 tokens ( 369.55 ms per token, 2.71 tokens per second) 6.33.648.980 I slot print_timing: id 3 | task 4511 | total time = 6501.99 ms / 743 tokens 6.33.648.980 I slot print_timing: id 3 | task 4511 | graphs reused = 3489 6.33.648.980 I slot print_timing: id 3 | task 4511 | graph reallocs = 0 / 0 (same size) / (changed size) 6.33.649.008 I slot release: id 3 | task 4511 | stop processing: n_tokens = 742, truncated = 0 6.34.408.801 I slot print_timing: id 1 | task 4509 | prompt eval time = 6501.65 ms / 880 tokens ( 7.39 ms per token, 135.35 tokens per second) 6.34.408.808 I slot print_timing: id 1 | task 4509 | eval time = 760.31 ms / 2 tokens ( 760.31 ms per token, 1.32 tokens per second) 6.34.408.809 I slot print_timing: id 1 | task 4509 | total time = 7261.96 ms / 882 tokens 6.34.408.809 I slot print_timing: id 1 | task 4509 | graphs reused = 3489 6.34.408.809 I slot print_timing: id 1 | task 4509 | graph reallocs = 0 / 0 (same size) / (changed size) 6.34.408.867 I slot release: id 1 | task 4509 | stop processing: n_tokens = 881, truncated = 0 6.34.408.877 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 6.34.408.928 I slot launch_slot_: id 2 | task 4520 | processing task, is_child = 0 6.34.408.984 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 340.112 MiB) 6.34.456.933 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 341.892 MiB) 6.34.505.178 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.878 (> 0.100 thold), f_keep = 0.850 6.34.505.244 I slot launch_slot_: id 3 | task 4521 | processing task, is_child = 0 6.34.505.303 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 881, t_last = 388835829348 6.34.505.372 I slot launch_slot_: id 1 | task 4522 | processing task, is_child = 0 6.36.365.358 I slot print_timing: id 0 | task 4516 | prompt eval time = 3422.28 ms / 716 tokens ( 4.78 ms per token, 209.22 tokens per second) 6.36.365.360 I slot print_timing: id 0 | task 4516 | eval time = 327.96 ms / 2 tokens ( 327.96 ms per token, 3.05 tokens per second) 6.36.365.361 I slot print_timing: id 0 | task 4516 | total time = 3750.23 ms / 718 tokens 6.36.365.362 I slot print_timing: id 0 | task 4516 | graphs reused = 3489 6.36.365.362 I slot print_timing: id 0 | task 4516 | graph reallocs = 0 / 0 (same size) / (changed size) 6.36.365.405 I slot release: id 0 | task 4516 | stop processing: n_tokens = 717, truncated = 0 6.36.365.571 I slot print_timing: id 2 | task 4520 | prompt eval time = 1530.26 ms / 122 tokens ( 12.54 ms per token, 79.72 tokens per second) 6.36.365.573 I slot print_timing: id 2 | task 4520 | eval time = 327.99 ms / 2 tokens ( 327.99 ms per token, 3.05 tokens per second) 6.36.365.574 I slot print_timing: id 2 | task 4520 | total time = 1858.25 ms / 124 tokens 6.36.365.574 I slot print_timing: id 2 | task 4520 | graphs reused = 3489 6.36.365.574 I slot print_timing: id 2 | task 4520 | graph reallocs = 0 / 0 (same size) / (changed size) 6.36.365.600 I slot release: id 2 | task 4520 | stop processing: n_tokens = 726, truncated = 0 6.36.365.841 I slot print_timing: id 3 | task 4521 | prompt eval time = 1527.27 ms / 116 tokens ( 13.17 ms per token, 75.95 tokens per second) 6.36.365.842 I slot print_timing: id 3 | task 4521 | eval time = 328.03 ms / 2 tokens ( 328.03 ms per token, 3.05 tokens per second) 6.36.365.843 I slot print_timing: id 3 | task 4521 | total time = 1855.30 ms / 118 tokens 6.36.365.843 I slot print_timing: id 3 | task 4521 | graphs reused = 3489 6.36.365.845 I slot print_timing: id 3 | task 4521 | graph reallocs = 0 / 0 (same size) / (changed size) 6.36.365.864 I slot release: id 3 | task 4521 | stop processing: n_tokens = 720, truncated = 0 6.37.108.595 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 717, t_last = 388837785886 6.37.108.640 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 339.839 MiB) 6.37.433.319 I slot launch_slot_: id 0 | task 4528 | processing task, is_child = 0 6.37.433.366 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 339.487 MiB) 6.37.484.541 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 340.112 MiB) 6.37.535.032 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 726, t_last = 388837786081 6.37.535.137 I slot launch_slot_: id 2 | task 4529 | processing task, is_child = 0 6.37.535.175 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 720, t_last = 388837786345 6.37.535.238 I slot launch_slot_: id 3 | task 4530 | processing task, is_child = 0 6.39.761.001 I slot print_timing: id 1 | task 4522 | prompt eval time = 4039.36 ms / 876 tokens ( 4.61 ms per token, 216.87 tokens per second) 6.39.761.003 I slot print_timing: id 1 | task 4522 | eval time = 1214.39 ms / 2 tokens ( 1214.39 ms per token, 0.82 tokens per second) 6.39.761.004 I slot print_timing: id 1 | task 4522 | total time = 5253.74 ms / 878 tokens 6.39.761.004 I slot print_timing: id 1 | task 4522 | graphs reused = 3489 6.39.761.005 I slot print_timing: id 1 | task 4522 | graph reallocs = 0 / 0 (same size) / (changed size) 6.39.761.050 I slot release: id 1 | task 4522 | stop processing: n_tokens = 877, truncated = 0 6.40.649.479 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 877, t_last = 388841181531 6.40.649.546 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 339.311 MiB) 6.40.855.164 I slot launch_slot_: id 1 | task 4534 | processing task, is_child = 0 6.40.855.193 I slot print_timing: id 0 | task 4528 | prompt processing, n_tokens = 490, progress = 0.49, t = 3.11 s / 157.34 tokens per second 6.40.859.656 I slot print_timing: id 2 | task 4529 | prompt processing, n_tokens = 476, progress = 0.48, t = 3.11 s / 152.95 tokens per second 6.40.863.767 I slot print_timing: id 3 | task 4530 | prompt processing, n_tokens = 518, progress = 0.50, t = 3.11 s / 166.44 tokens per second 6.43.204.724 I slot print_timing: id 0 | task 4528 | prompt processing, n_tokens = 861, progress = 0.86, t = 5.67 s / 151.87 tokens per second 6.43.406.373 I slot print_timing: id 2 | task 4529 | prompt processing, n_tokens = 861, progress = 0.87, t = 5.67 s / 151.92 tokens per second 6.43.418.254 I slot print_timing: id 3 | task 4530 | prompt processing, n_tokens = 861, progress = 0.83, t = 5.67 s / 151.92 tokens per second 6.44.714.062 I slot print_timing: id 0 | task 4528 | prompt processing, n_tokens = 1002, progress = 1.00, t = 7.18 s / 139.58 tokens per second 6.44.917.833 I slot print_timing: id 1 | task 4534 | prompt processing, n_tokens = 345, progress = 0.35, t = 3.85 s / 89.51 tokens per second 6.44.917.846 I slot print_timing: id 2 | task 4529 | prompt processing, n_tokens = 988, progress = 1.00, t = 7.18 s / 137.67 tokens per second 6.44.920.743 I slot print_timing: id 3 | task 4530 | prompt processing, n_tokens = 1030, progress = 1.00, t = 7.18 s / 143.52 tokens per second 6.45.390.591 I slot print_timing: id 1 | task 4534 | prompt processing, n_tokens = 483, progress = 0.48, t = 4.53 s / 106.61 tokens per second 6.46.153.091 I slot print_timing: id 0 | task 4528 | prompt eval time = 7854.86 ms / 1006 tokens ( 7.81 ms per token, 128.07 tokens per second) 6.46.153.097 I slot print_timing: id 0 | task 4528 | eval time = 762.98 ms / 2 tokens ( 762.98 ms per token, 1.31 tokens per second) 6.46.153.097 I slot print_timing: id 0 | task 4528 | total time = 8617.84 ms / 1008 tokens 6.46.153.098 I slot print_timing: id 0 | task 4528 | graphs reused = 3489 6.46.153.098 I slot print_timing: id 0 | task 4528 | graph reallocs = 0 / 0 (same size) / (changed size) 6.46.153.139 I slot release: id 0 | task 4528 | stop processing: n_tokens = 1007, truncated = 0 6.46.153.326 I slot print_timing: id 2 | task 4529 | prompt eval time = 7853.07 ms / 992 tokens ( 7.92 ms per token, 126.32 tokens per second) 6.46.153.329 I slot print_timing: id 2 | task 4529 | eval time = 762.98 ms / 2 tokens ( 762.98 ms per token, 1.31 tokens per second) 6.46.153.330 I slot print_timing: id 2 | task 4529 | total time = 8616.05 ms / 994 tokens 6.46.153.330 I slot print_timing: id 2 | task 4529 | graphs reused = 3489 6.46.153.330 I slot print_timing: id 2 | task 4529 | graph reallocs = 0 / 0 (same size) / (changed size) 6.46.153.360 I slot release: id 2 | task 4529 | stop processing: n_tokens = 993, truncated = 0 6.46.153.596 I slot print_timing: id 3 | task 4530 | prompt eval time = 7853.26 ms / 1034 tokens ( 7.60 ms per token, 131.67 tokens per second) 6.46.153.598 I slot print_timing: id 3 | task 4530 | eval time = 763.01 ms / 2 tokens ( 763.01 ms per token, 1.31 tokens per second) 6.46.153.599 I slot print_timing: id 3 | task 4530 | total time = 8616.27 ms / 1036 tokens 6.46.153.600 I slot print_timing: id 3 | task 4530 | graphs reused = 3489 6.46.153.601 I slot print_timing: id 3 | task 4530 | graph reallocs = 0 / 0 (same size) / (changed size) 6.46.153.643 I slot release: id 3 | task 4530 | stop processing: n_tokens = 1035, truncated = 0 6.46.153.650 I slot print_timing: id 1 | task 4534 | prompt processing, n_tokens = 861, progress = 0.86, t = 5.29 s / 162.66 tokens per second 6.46.160.594 I slot print_timing: id 1 | task 4534 | prompt processing, n_tokens = 995, progress = 1.00, t = 5.30 s / 187.70 tokens per second 6.46.566.105 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1007, t_last = 388847573620 6.46.566.162 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 339.467 MiB) 6.46.619.045 I slot launch_slot_: id 0 | task 4541 | processing task, is_child = 0 6.46.619.100 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 340.797 MiB) 6.46.678.195 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 329.319 MiB) 6.46.728.647 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.895 (> 0.100 thold), f_keep = 0.895 6.46.728.712 I slot launch_slot_: id 2 | task 4542 | processing task, is_child = 0 6.46.728.765 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1035, t_last = 388847574124 6.46.728.836 I slot launch_slot_: id 3 | task 4543 | processing task, is_child = 0 6.47.832.102 I slot print_timing: id 1 | task 4534 | prompt eval time = 5706.56 ms / 999 tokens ( 5.71 ms per token, 175.06 tokens per second) 6.47.832.105 I slot print_timing: id 1 | task 4534 | eval time = 1266.00 ms / 2 tokens ( 1266.00 ms per token, 0.79 tokens per second) 6.47.832.106 I slot print_timing: id 1 | task 4534 | total time = 6972.56 ms / 1001 tokens 6.47.832.106 I slot print_timing: id 1 | task 4534 | graphs reused = 3489 6.47.832.107 I slot print_timing: id 1 | task 4534 | graph reallocs = 0 / 0 (same size) / (changed size) 6.47.832.154 I slot release: id 1 | task 4534 | stop processing: n_tokens = 1000, truncated = 0 6.48.679.507 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1000, t_last = 388849252635 6.48.679.569 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 329.847 MiB) 6.48.712.964 I slot launch_slot_: id 1 | task 4546 | processing task, is_child = 0 6.49.743.707 I slot print_timing: id 2 | task 4542 | prompt eval time = 1950.57 ms / 132 tokens ( 14.78 ms per token, 67.67 tokens per second) 6.49.743.710 I slot print_timing: id 2 | task 4542 | eval time = 1064.20 ms / 2 tokens ( 1064.20 ms per token, 0.94 tokens per second) 6.49.743.711 I slot print_timing: id 2 | task 4542 | total time = 3014.77 ms / 134 tokens 6.49.743.711 I slot print_timing: id 2 | task 4542 | graphs reused = 3489 6.49.743.712 I slot print_timing: id 2 | task 4542 | graph reallocs = 0 / 0 (same size) / (changed size) 6.49.743.750 I slot release: id 2 | task 4542 | stop processing: n_tokens = 994, truncated = 0 6.49.743.759 I slot print_timing: id 0 | task 4541 | prompt processing, n_tokens = 363, progress = 0.41, t = 3.01 s / 120.41 tokens per second 6.49.750.095 I slot print_timing: id 3 | task 4543 | prompt processing, n_tokens = 502, progress = 0.49, t = 3.01 s / 166.70 tokens per second 6.50.873.555 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 994, t_last = 388851164231 6.50.873.618 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 333.386 MiB) 6.51.426.198 I slot launch_slot_: id 2 | task 4549 | processing task, is_child = 0 6.51.426.216 I slot print_timing: id 0 | task 4541 | prompt processing, n_tokens = 730, progress = 0.83, t = 4.14 s / 176.13 tokens per second 6.51.435.377 I slot print_timing: id 3 | task 4543 | prompt processing, n_tokens = 773, progress = 0.76, t = 4.14 s / 186.65 tokens per second 6.52.571.836 I slot print_timing: id 0 | task 4541 | prompt processing, n_tokens = 875, progress = 1.00, t = 5.84 s / 149.75 tokens per second 6.52.919.640 I slot print_timing: id 1 | task 4546 | prompt processing, n_tokens = 380, progress = 0.42, t = 3.86 s / 98.48 tokens per second 6.52.923.987 I slot print_timing: id 3 | task 4543 | prompt processing, n_tokens = 1014, progress = 1.00, t = 5.84 s / 173.64 tokens per second 6.54.159.095 I slot print_timing: id 1 | task 4546 | prompt processing, n_tokens = 773, progress = 0.86, t = 5.45 s / 141.95 tokens per second 6.55.007.524 I slot print_timing: id 0 | task 4541 | prompt eval time = 7430.00 ms / 879 tokens ( 8.45 ms per token, 118.30 tokens per second) 6.55.007.527 I slot print_timing: id 0 | task 4541 | eval time = 848.67 ms / 2 tokens ( 848.67 ms per token, 1.18 tokens per second) 6.55.007.528 I slot print_timing: id 0 | task 4541 | total time = 8278.67 ms / 881 tokens 6.55.007.528 I slot print_timing: id 0 | task 4541 | graphs reused = 3489 6.55.007.529 I slot print_timing: id 0 | task 4541 | graph reallocs = 0 / 0 (same size) / (changed size) 6.55.007.571 I slot release: id 0 | task 4541 | stop processing: n_tokens = 880, truncated = 0 6.55.007.813 I slot print_timing: id 3 | task 4543 | prompt eval time = 7426.94 ms / 1018 tokens ( 7.30 ms per token, 137.07 tokens per second) 6.55.007.817 I slot print_timing: id 3 | task 4543 | eval time = 848.73 ms / 2 tokens ( 848.73 ms per token, 1.18 tokens per second) 6.55.007.817 I slot print_timing: id 3 | task 4543 | total time = 8275.67 ms / 1020 tokens 6.55.007.818 I slot print_timing: id 3 | task 4543 | graphs reused = 3489 6.55.007.818 I slot print_timing: id 3 | task 4543 | graph reallocs = 0 / 0 (same size) / (changed size) 6.55.007.873 I slot release: id 3 | task 4543 | stop processing: n_tokens = 1019, truncated = 0 6.55.007.882 I slot print_timing: id 1 | task 4546 | prompt processing, n_tokens = 892, progress = 1.00, t = 6.29 s / 141.72 tokens per second 6.55.022.483 I slot print_timing: id 2 | task 4549 | prompt processing, n_tokens = 493, progress = 0.49, t = 3.57 s / 138.02 tokens per second 6.55.651.075 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 6.55.651.146 I slot launch_slot_: id 3 | task 4554 | processing task, is_child = 0 6.55.651.202 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 332.701 MiB) 6.55.672.906 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 880, t_last = 388856428052 6.55.672.989 I slot launch_slot_: id 0 | task 4555 | processing task, is_child = 0 6.55.673.064 I slot print_timing: id 2 | task 4549 | prompt processing, n_tokens = 773, progress = 0.77, t = 4.22 s / 183.37 tokens per second 6.56.891.485 I slot print_timing: id 1 | task 4546 | prompt eval time = 6938.09 ms / 896 tokens ( 7.74 ms per token, 129.14 tokens per second) 6.56.891.487 I slot print_timing: id 1 | task 4546 | eval time = 1240.41 ms / 2 tokens ( 1240.41 ms per token, 0.81 tokens per second) 6.56.891.488 I slot print_timing: id 1 | task 4546 | total time = 8178.50 ms / 898 tokens 6.56.891.488 I slot print_timing: id 1 | task 4546 | graphs reused = 3489 6.56.891.490 I slot print_timing: id 1 | task 4546 | graph reallocs = 0 / 0 (same size) / (changed size) 6.56.891.539 I slot release: id 1 | task 4546 | stop processing: n_tokens = 897, truncated = 0 6.56.895.124 I slot print_timing: id 2 | task 4549 | prompt processing, n_tokens = 1005, progress = 1.00, t = 5.46 s / 184.20 tokens per second 6.57.383.260 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.909 (> 0.100 thold), f_keep = 0.893 6.57.383.323 I slot launch_slot_: id 1 | task 4558 | processing task, is_child = 0 6.58.166.802 I slot print_timing: id 2 | task 4549 | prompt eval time = 5947.79 ms / 1009 tokens ( 5.89 ms per token, 169.64 tokens per second) 6.58.166.804 I slot print_timing: id 2 | task 4549 | eval time = 783.70 ms / 2 tokens ( 783.70 ms per token, 1.28 tokens per second) 6.58.166.805 I slot print_timing: id 2 | task 4549 | total time = 6731.49 ms / 1011 tokens 6.58.166.805 I slot print_timing: id 2 | task 4549 | graphs reused = 3489 6.58.166.806 I slot print_timing: id 2 | task 4549 | graph reallocs = 0 / 0 (same size) / (changed size) 6.58.166.865 I slot release: id 2 | task 4549 | stop processing: n_tokens = 1010, truncated = 0 6.58.167.090 I slot print_timing: id 3 | task 4554 | prompt eval time = 1708.32 ms / 129 tokens ( 13.24 ms per token, 75.51 tokens per second) 6.58.167.094 I slot print_timing: id 3 | task 4554 | eval time = 783.83 ms / 2 tokens ( 783.83 ms per token, 1.28 tokens per second) 6.58.167.094 I slot print_timing: id 3 | task 4554 | total time = 2492.15 ms / 131 tokens 6.58.167.094 I slot print_timing: id 3 | task 4554 | graphs reused = 3489 6.58.167.095 I slot print_timing: id 3 | task 4554 | graph reallocs = 0 / 0 (same size) / (changed size) 6.58.167.126 I slot release: id 3 | task 4554 | stop processing: n_tokens = 903, truncated = 0 6.58.826.999 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1010, t_last = 388859587346 6.58.827.058 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 329.749 MiB) 6.58.847.977 I slot launch_slot_: id 2 | task 4561 | processing task, is_child = 0 6.58.848.030 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 330.805 MiB) 6.58.871.721 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 903, t_last = 388859587607 6.58.871.816 I slot launch_slot_: id 3 | task 4562 | processing task, is_child = 0 6.58.871.830 I slot print_timing: id 0 | task 4555 | prompt processing, n_tokens = 773, progress = 0.78, t = 3.15 s / 245.10 tokens per second 6.59.853.600 I slot print_timing: id 1 | task 4558 | prompt eval time = 1443.65 ms / 108 tokens ( 13.37 ms per token, 74.81 tokens per second) 6.59.853.603 I slot print_timing: id 1 | task 4558 | eval time = 1026.61 ms / 2 tokens ( 1026.61 ms per token, 0.97 tokens per second) 6.59.853.604 I slot print_timing: id 1 | task 4558 | total time = 2470.26 ms / 110 tokens 6.59.853.604 I slot print_timing: id 1 | task 4558 | graphs reused = 3489 6.59.853.605 I slot print_timing: id 1 | task 4558 | graph reallocs = 0 / 0 (same size) / (changed size) 6.59.853.647 I slot release: id 1 | task 4558 | stop processing: n_tokens = 882, truncated = 0 6.59.853.657 I slot print_timing: id 0 | task 4555 | prompt processing, n_tokens = 981, progress = 1.00, t = 4.18 s / 234.67 tokens per second 7.00.378.471 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 882, t_last = 388861274128 7.00.378.527 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 330.629 MiB) 7.00.399.000 I slot launch_slot_: id 1 | task 4565 | processing task, is_child = 0 7.01.505.864 I slot print_timing: id 0 | task 4555 | prompt eval time = 4705.47 ms / 985 tokens ( 4.78 ms per token, 209.33 tokens per second) 7.01.505.866 I slot print_timing: id 0 | task 4555 | eval time = 1127.39 ms / 2 tokens ( 1127.39 ms per token, 0.89 tokens per second) 7.01.505.866 I slot print_timing: id 0 | task 4555 | total time = 5832.86 ms / 987 tokens 7.01.505.867 I slot print_timing: id 0 | task 4555 | graphs reused = 3489 7.01.505.867 I slot print_timing: id 0 | task 4555 | graph reallocs = 0 / 0 (same size) / (changed size) 7.01.505.919 I slot release: id 0 | task 4555 | stop processing: n_tokens = 986, truncated = 0 7.02.951.830 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 986, t_last = 388862926400 7.02.951.900 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 330.218 MiB) 7.03.159.006 I slot launch_slot_: id 0 | task 4568 | processing task, is_child = 0 7.03.159.101 I slot print_timing: id 2 | task 4561 | prompt processing, n_tokens = 774, progress = 0.85, t = 4.08 s / 189.79 tokens per second 7.03.160.999 I slot print_timing: id 3 | task 4562 | prompt processing, n_tokens = 774, progress = 0.81, t = 4.08 s / 189.80 tokens per second 7.04.659.416 I slot print_timing: id 1 | task 4565 | prompt processing, n_tokens = 424, progress = 0.45, t = 4.05 s / 104.71 tokens per second 7.04.662.654 I slot print_timing: id 2 | task 4561 | prompt processing, n_tokens = 902, progress = 1.00, t = 5.57 s / 161.81 tokens per second 7.04.664.630 I slot print_timing: id 3 | task 4562 | prompt processing, n_tokens = 948, progress = 1.00, t = 5.57 s / 170.07 tokens per second 7.05.943.591 I slot print_timing: id 1 | task 4565 | prompt processing, n_tokens = 774, progress = 0.82, t = 5.54 s / 139.61 tokens per second 7.07.161.142 I slot print_timing: id 2 | task 4561 | prompt eval time = 7069.59 ms / 906 tokens ( 7.80 ms per token, 128.15 tokens per second) 7.07.161.144 I slot print_timing: id 2 | task 4561 | eval time = 1217.82 ms / 2 tokens ( 1217.82 ms per token, 0.82 tokens per second) 7.07.161.145 I slot print_timing: id 2 | task 4561 | total time = 8287.41 ms / 908 tokens 7.07.161.145 I slot print_timing: id 2 | task 4561 | graphs reused = 3489 7.07.161.145 I slot print_timing: id 2 | task 4561 | graph reallocs = 0 / 0 (same size) / (changed size) 7.07.161.187 I slot release: id 2 | task 4561 | stop processing: n_tokens = 907, truncated = 0 7.07.161.421 I slot print_timing: id 3 | task 4562 | prompt eval time = 7069.76 ms / 952 tokens ( 7.43 ms per token, 134.66 tokens per second) 7.07.161.424 I slot print_timing: id 3 | task 4562 | eval time = 1217.86 ms / 2 tokens ( 1217.86 ms per token, 0.82 tokens per second) 7.07.161.424 I slot print_timing: id 3 | task 4562 | total time = 8287.62 ms / 954 tokens 7.07.161.425 I slot print_timing: id 3 | task 4562 | graphs reused = 3489 7.07.161.425 I slot print_timing: id 3 | task 4562 | graph reallocs = 0 / 0 (same size) / (changed size) 7.07.161.451 I slot release: id 3 | task 4562 | stop processing: n_tokens = 953, truncated = 0 7.07.161.460 I slot print_timing: id 0 | task 4568 | prompt processing, n_tokens = 840, progress = 0.62, t = 4.00 s / 209.90 tokens per second 7.07.165.499 I slot print_timing: id 1 | task 4565 | prompt processing, n_tokens = 936, progress = 1.00, t = 6.76 s / 138.42 tokens per second 7.07.837.976 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 907, t_last = 388868581668 7.07.838.034 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 332.917 MiB) 7.07.849.593 I slot launch_slot_: id 2 | task 4573 | processing task, is_child = 0 7.07.849.644 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.606 MiB) 7.07.864.075 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 953, t_last = 388868581932 7.07.864.157 I slot launch_slot_: id 3 | task 4574 | processing task, is_child = 0 7.07.864.166 I slot print_timing: id 0 | task 4568 | prompt processing, n_tokens = 1152, progress = 0.85, t = 4.68 s / 246.22 tokens per second 7.09.007.869 I slot print_timing: id 1 | task 4565 | prompt eval time = 7438.96 ms / 940 tokens ( 7.91 ms per token, 126.36 tokens per second) 7.09.007.872 I slot print_timing: id 1 | task 4565 | eval time = 1169.89 ms / 2 tokens ( 1169.89 ms per token, 0.85 tokens per second) 7.09.007.872 I slot print_timing: id 1 | task 4565 | total time = 8608.85 ms / 942 tokens 7.09.007.873 I slot print_timing: id 1 | task 4565 | graphs reused = 3489 7.09.007.873 I slot print_timing: id 1 | task 4565 | graph reallocs = 0 / 0 (same size) / (changed size) 7.09.007.914 I slot release: id 1 | task 4565 | stop processing: n_tokens = 941, truncated = 0 7.09.007.925 I slot print_timing: id 0 | task 4568 | prompt processing, n_tokens = 1352, progress = 1.00, t = 5.85 s / 231.16 tokens per second 7.09.910.074 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 941, t_last = 388870428395 7.09.910.136 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.294 MiB) 7.09.926.091 I slot launch_slot_: id 1 | task 4577 | processing task, is_child = 0 7.11.751.747 I slot print_timing: id 0 | task 4568 | prompt eval time = 6751.05 ms / 1356 tokens ( 4.98 ms per token, 200.86 tokens per second) 7.11.751.750 I slot print_timing: id 0 | task 4568 | eval time = 1841.67 ms / 2 tokens ( 1841.67 ms per token, 0.54 tokens per second) 7.11.751.750 I slot print_timing: id 0 | task 4568 | total time = 8592.72 ms / 1358 tokens 7.11.751.750 I slot print_timing: id 0 | task 4568 | graphs reused = 3489 7.11.751.751 I slot print_timing: id 0 | task 4568 | graph reallocs = 0 / 0 (same size) / (changed size) 7.11.751.819 I slot release: id 0 | task 4568 | stop processing: n_tokens = 1357, truncated = 0 7.11.754.018 I slot print_timing: id 2 | task 4573 | prompt processing, n_tokens = 743, progress = 0.59, t = 3.89 s / 191.23 tokens per second 7.11.756.226 I slot print_timing: id 3 | task 4574 | prompt processing, n_tokens = 826, progress = 0.62, t = 3.89 s / 212.59 tokens per second 7.13.566.390 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1357, t_last = 388873172300 7.13.566.462 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 333.386 MiB) 7.13.854.806 I slot launch_slot_: id 0 | task 4580 | processing task, is_child = 0 7.13.854.930 I slot print_timing: id 1 | task 4577 | prompt processing, n_tokens = 431, progress = 0.33, t = 3.64 s / 118.40 tokens per second 7.13.854.941 I slot print_timing: id 2 | task 4573 | prompt processing, n_tokens = 1152, progress = 0.92, t = 5.70 s / 202.09 tokens per second 7.13.857.089 I slot print_timing: id 3 | task 4574 | prompt processing, n_tokens = 1152, progress = 0.86, t = 5.70 s / 202.10 tokens per second 7.15.640.916 I slot print_timing: id 1 | task 4577 | prompt processing, n_tokens = 784, progress = 0.60, t = 5.43 s / 144.26 tokens per second 7.15.644.990 I slot print_timing: id 2 | task 4573 | prompt processing, n_tokens = 1255, progress = 1.00, t = 7.49 s / 167.45 tokens per second 7.15.646.966 I slot print_timing: id 3 | task 4574 | prompt processing, n_tokens = 1338, progress = 1.00, t = 7.49 s / 178.53 tokens per second 7.16.830.911 I slot print_timing: id 1 | task 4577 | prompt processing, n_tokens = 1152, progress = 0.89, t = 6.90 s / 166.94 tokens per second 7.18.002.290 I slot print_timing: id 2 | task 4573 | prompt eval time = 8961.12 ms / 1259 tokens ( 7.12 ms per token, 140.50 tokens per second) 7.18.002.294 I slot print_timing: id 2 | task 4573 | eval time = 1175.10 ms / 2 tokens ( 1175.10 ms per token, 0.85 tokens per second) 7.18.002.295 I slot print_timing: id 2 | task 4573 | total time = 10136.23 ms / 1261 tokens 7.18.002.295 I slot print_timing: id 2 | task 4573 | graphs reused = 3489 7.18.002.295 I slot print_timing: id 2 | task 4573 | graph reallocs = 0 / 0 (same size) / (changed size) 7.18.002.353 I slot release: id 2 | task 4573 | stop processing: n_tokens = 1260, truncated = 0 7.18.002.576 I slot print_timing: id 3 | task 4574 | prompt eval time = 8961.29 ms / 1342 tokens ( 6.68 ms per token, 149.76 tokens per second) 7.18.002.580 I slot print_timing: id 3 | task 4574 | eval time = 1175.16 ms / 2 tokens ( 1175.16 ms per token, 0.85 tokens per second) 7.18.002.580 I slot print_timing: id 3 | task 4574 | total time = 10136.46 ms / 1344 tokens 7.18.002.580 I slot print_timing: id 3 | task 4574 | graphs reused = 3489 7.18.002.581 I slot print_timing: id 3 | task 4574 | graph reallocs = 0 / 0 (same size) / (changed size) 7.18.002.631 I slot release: id 3 | task 4574 | stop processing: n_tokens = 1343, truncated = 0 7.18.002.640 I slot print_timing: id 0 | task 4580 | prompt processing, n_tokens = 681, progress = 0.86, t = 4.15 s / 164.20 tokens per second 7.18.004.987 I slot print_timing: id 1 | task 4577 | prompt processing, n_tokens = 1296, progress = 1.00, t = 8.08 s / 160.47 tokens per second 7.18.388.326 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1260, t_last = 388879422834 7.18.388.398 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 334.070 MiB) 7.18.399.460 I slot launch_slot_: id 2 | task 4585 | processing task, is_child = 0 7.18.399.524 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 332.154 MiB) 7.18.423.063 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1343, t_last = 388879423112 7.18.423.199 I slot launch_slot_: id 3 | task 4586 | processing task, is_child = 0 7.18.423.209 I slot print_timing: id 0 | task 4580 | prompt processing, n_tokens = 788, progress = 0.99, t = 4.53 s / 173.83 tokens per second 7.19.126.908 I slot print_timing: id 1 | task 4577 | prompt eval time = 8462.22 ms / 1300 tokens ( 6.51 ms per token, 153.62 tokens per second) 7.19.126.913 I slot print_timing: id 1 | task 4577 | eval time = 738.58 ms / 2 tokens ( 738.58 ms per token, 1.35 tokens per second) 7.19.126.913 I slot print_timing: id 1 | task 4577 | total time = 9200.80 ms / 1302 tokens 7.19.126.914 I slot print_timing: id 1 | task 4577 | graphs reused = 3489 7.19.126.914 I slot print_timing: id 1 | task 4577 | graph reallocs = 0 / 0 (same size) / (changed size) 7.19.126.974 I slot release: id 1 | task 4577 | stop processing: n_tokens = 1301, truncated = 0 7.19.779.574 I slot print_timing: id 0 | task 4580 | prompt eval time = 5271.78 ms / 792 tokens ( 6.66 ms per token, 150.23 tokens per second) 7.19.779.577 I slot print_timing: id 0 | task 4580 | eval time = 652.97 ms / 2 tokens ( 652.97 ms per token, 1.53 tokens per second) 7.19.779.578 I slot print_timing: id 0 | task 4580 | total time = 5924.75 ms / 794 tokens 7.19.779.578 I slot print_timing: id 0 | task 4580 | graphs reused = 3489 7.19.779.579 I slot print_timing: id 0 | task 4580 | graph reallocs = 0 / 0 (same size) / (changed size) 7.19.779.632 I slot release: id 0 | task 4580 | stop processing: n_tokens = 793, truncated = 0 7.19.779.641 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1301, t_last = 388880547455 7.19.779.708 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 348.892 MiB) 7.19.794.411 I slot launch_slot_: id 1 | task 4589 | processing task, is_child = 0 7.19.794.459 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 332.408 MiB) 7.19.804.021 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 793, t_last = 388881200113 7.19.804.108 I slot launch_slot_: id 0 | task 4590 | processing task, is_child = 0 7.22.900.813 I slot print_timing: id 2 | task 4585 | prompt processing, n_tokens = 741, progress = 0.83, t = 4.34 s / 170.69 tokens per second 7.22.904.468 I slot print_timing: id 3 | task 4586 | prompt processing, n_tokens = 681, progress = 0.84, t = 4.34 s / 156.87 tokens per second 7.24.405.662 I slot print_timing: id 0 | task 4590 | prompt processing, n_tokens = 655, progress = 0.83, t = 4.60 s / 142.34 tokens per second 7.24.539.964 I slot print_timing: id 1 | task 4589 | prompt processing, n_tokens = 343, progress = 0.40, t = 4.60 s / 74.54 tokens per second 7.24.543.557 I slot print_timing: id 2 | task 4585 | prompt processing, n_tokens = 887, progress = 1.00, t = 5.98 s / 148.32 tokens per second 7.24.545.648 I slot print_timing: id 3 | task 4586 | prompt processing, n_tokens = 804, progress = 1.00, t = 5.98 s / 134.44 tokens per second 7.25.735.111 I slot print_timing: id 0 | task 4590 | prompt processing, n_tokens = 786, progress = 0.99, t = 5.93 s / 132.53 tokens per second 7.25.738.335 I slot print_timing: id 1 | task 4589 | prompt processing, n_tokens = 741, progress = 0.86, t = 5.93 s / 124.95 tokens per second 7.26.151.217 I slot print_timing: id 2 | task 4585 | prompt eval time = 7309.67 ms / 891 tokens ( 8.20 ms per token, 121.89 tokens per second) 7.26.151.222 I slot print_timing: id 2 | task 4585 | eval time = 416.33 ms / 2 tokens ( 416.33 ms per token, 2.40 tokens per second) 7.26.151.222 I slot print_timing: id 2 | task 4585 | total time = 7726.00 ms / 893 tokens 7.26.151.223 I slot print_timing: id 2 | task 4585 | graphs reused = 3489 7.26.151.223 I slot print_timing: id 2 | task 4585 | graph reallocs = 0 / 0 (same size) / (changed size) 7.26.151.269 I slot release: id 2 | task 4585 | stop processing: n_tokens = 892, truncated = 0 7.26.151.495 I slot print_timing: id 3 | task 4586 | prompt eval time = 7309.80 ms / 808 tokens ( 9.05 ms per token, 110.54 tokens per second) 7.26.151.497 I slot print_timing: id 3 | task 4586 | eval time = 416.39 ms / 2 tokens ( 416.39 ms per token, 2.40 tokens per second) 7.26.151.497 I slot print_timing: id 3 | task 4586 | total time = 7726.19 ms / 810 tokens 7.26.151.497 I slot print_timing: id 3 | task 4586 | graphs reused = 3489 7.26.151.498 I slot print_timing: id 3 | task 4586 | graph reallocs = 0 / 0 (same size) / (changed size) 7.26.151.526 I slot release: id 3 | task 4586 | stop processing: n_tokens = 809, truncated = 0 7.26.151.534 I slot print_timing: id 1 | task 4589 | prompt processing, n_tokens = 855, progress = 1.00, t = 6.35 s / 134.72 tokens per second 7.26.224.009 I slot print_timing: id 0 | task 4590 | prompt eval time = 6346.91 ms / 790 tokens ( 8.03 ms per token, 124.47 tokens per second) 7.26.224.011 I slot print_timing: id 0 | task 4590 | eval time = 72.98 ms / 2 tokens ( 72.98 ms per token, 13.70 tokens per second) 7.26.224.012 I slot print_timing: id 0 | task 4590 | total time = 6419.89 ms / 792 tokens 7.26.224.012 I slot print_timing: id 0 | task 4590 | graphs reused = 3489 7.26.224.013 I slot print_timing: id 0 | task 4590 | graph reallocs = 0 / 0 (same size) / (changed size) 7.26.224.043 I slot release: id 0 | task 4590 | stop processing: n_tokens = 791, truncated = 0 7.26.224.222 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.879 (> 0.100 thold), f_keep = 0.865 7.26.224.273 I slot launch_slot_: id 0 | task 4597 | processing task, is_child = 0 7.26.224.330 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.294 MiB) 7.26.234.095 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.576 MiB) 7.26.245.156 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 892, t_last = 388887571750 7.26.245.257 I slot launch_slot_: id 2 | task 4598 | processing task, is_child = 0 7.26.245.301 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 809, t_last = 388887572007 7.26.245.366 I slot launch_slot_: id 3 | task 4599 | processing task, is_child = 0 7.27.236.321 I slot print_timing: id 1 | task 4589 | prompt eval time = 6420.04 ms / 859 tokens ( 7.47 ms per token, 133.80 tokens per second) 7.27.236.328 I slot print_timing: id 1 | task 4589 | eval time = 1012.10 ms / 2 tokens ( 1012.10 ms per token, 0.99 tokens per second) 7.27.236.328 I slot print_timing: id 1 | task 4589 | total time = 7432.14 ms / 861 tokens 7.27.236.329 I slot print_timing: id 1 | task 4589 | graphs reused = 3489 7.27.236.329 I slot print_timing: id 1 | task 4589 | graph reallocs = 0 / 0 (same size) / (changed size) 7.27.236.371 I slot release: id 1 | task 4589 | stop processing: n_tokens = 860, truncated = 0 7.27.844.293 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 860, t_last = 388888656852 7.27.844.351 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.087 MiB) 7.27.856.246 I slot launch_slot_: id 1 | task 4602 | processing task, is_child = 0 7.29.244.532 I slot print_timing: id 0 | task 4597 | prompt eval time = 1598.91 ms / 123 tokens ( 13.00 ms per token, 76.93 tokens per second) 7.29.244.535 I slot print_timing: id 0 | task 4597 | eval time = 1400.24 ms / 2 tokens ( 1400.24 ms per token, 0.71 tokens per second) 7.29.244.535 I slot print_timing: id 0 | task 4597 | total time = 2999.15 ms / 125 tokens 7.29.244.536 I slot print_timing: id 0 | task 4597 | graphs reused = 3489 7.29.244.536 I slot print_timing: id 0 | task 4597 | graph reallocs = 0 / 0 (same size) / (changed size) 7.29.244.578 I slot release: id 0 | task 4597 | stop processing: n_tokens = 779, truncated = 0 7.30.002.907 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 779, t_last = 388890665059 7.30.002.956 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.263 MiB) 7.30.452.834 I slot launch_slot_: id 0 | task 4605 | processing task, is_child = 0 7.30.454.821 I slot print_timing: id 2 | task 4598 | prompt processing, n_tokens = 655, progress = 0.77, t = 3.75 s / 174.47 tokens per second 7.30.456.705 I slot print_timing: id 3 | task 4599 | prompt processing, n_tokens = 770, progress = 0.99, t = 3.75 s / 205.10 tokens per second 7.32.182.048 I slot print_timing: id 1 | task 4602 | prompt processing, n_tokens = 655, progress = 0.82, t = 4.32 s / 151.54 tokens per second 7.32.184.159 I slot print_timing: id 2 | task 4598 | prompt processing, n_tokens = 851, progress = 1.00, t = 5.93 s / 143.51 tokens per second 7.32.915.680 I slot print_timing: id 3 | task 4599 | prompt eval time = 5930.20 ms / 774 tokens ( 7.66 ms per token, 130.52 tokens per second) 7.32.915.684 I slot print_timing: id 3 | task 4599 | eval time = 736.80 ms / 2 tokens ( 736.80 ms per token, 1.36 tokens per second) 7.32.915.686 I slot print_timing: id 3 | task 4599 | total time = 6667.01 ms / 776 tokens 7.32.915.686 I slot print_timing: id 3 | task 4599 | graphs reused = 3489 7.32.915.687 I slot print_timing: id 3 | task 4599 | graph reallocs = 0 / 0 (same size) / (changed size) 7.32.915.725 I slot release: id 3 | task 4599 | stop processing: n_tokens = 775, truncated = 0 7.32.915.746 I slot print_timing: id 1 | task 4602 | prompt processing, n_tokens = 798, progress = 1.00, t = 5.06 s / 157.74 tokens per second 7.33.327.432 I slot print_timing: id 2 | task 4598 | prompt eval time = 6666.88 ms / 855 tokens ( 7.80 ms per token, 128.25 tokens per second) 7.33.327.435 I slot print_timing: id 2 | task 4598 | eval time = 411.94 ms / 2 tokens ( 411.94 ms per token, 2.43 tokens per second) 7.33.327.436 I slot print_timing: id 2 | task 4598 | total time = 7078.82 ms / 857 tokens 7.33.327.437 I slot print_timing: id 2 | task 4598 | graphs reused = 3489 7.33.327.437 I slot print_timing: id 2 | task 4598 | graph reallocs = 0 / 0 (same size) / (changed size) 7.33.327.474 I slot release: id 2 | task 4598 | stop processing: n_tokens = 856, truncated = 0 7.33.327.481 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 775, t_last = 388894336206 7.33.327.530 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.145 MiB) 7.33.356.491 I slot launch_slot_: id 3 | task 4609 | processing task, is_child = 0 7.33.356.546 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.215 MiB) 7.33.369.963 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 856, t_last = 388894747955 7.33.370.043 I slot launch_slot_: id 2 | task 4610 | processing task, is_child = 0 7.34.767.877 I slot print_timing: id 1 | task 4602 | prompt eval time = 5471.01 ms / 802 tokens ( 6.82 ms per token, 146.59 tokens per second) 7.34.767.880 I slot print_timing: id 1 | task 4602 | eval time = 1440.61 ms / 2 tokens ( 1440.61 ms per token, 0.69 tokens per second) 7.34.767.880 I slot print_timing: id 1 | task 4602 | total time = 6911.62 ms / 804 tokens 7.34.767.881 I slot print_timing: id 1 | task 4602 | graphs reused = 3489 7.34.767.881 I slot print_timing: id 1 | task 4602 | graph reallocs = 0 / 0 (same size) / (changed size) 7.34.767.926 I slot release: id 1 | task 4602 | stop processing: n_tokens = 803, truncated = 0 7.34.767.937 I slot print_timing: id 0 | task 4605 | prompt processing, n_tokens = 836, progress = 0.86, t = 4.31 s / 193.75 tokens per second 7.35.143.283 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 803, t_last = 388896188407 7.35.143.345 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 333.757 MiB) 7.35.708.357 I slot launch_slot_: id 1 | task 4613 | processing task, is_child = 0 7.35.708.367 I slot print_timing: id 0 | task 4605 | prompt processing, n_tokens = 967, progress = 1.00, t = 4.69 s / 206.16 tokens per second 7.36.820.243 I slot print_timing: id 2 | task 4610 | prompt processing, n_tokens = 448, progress = 0.46, t = 3.45 s / 130.02 tokens per second 7.36.822.905 I slot print_timing: id 3 | task 4609 | prompt processing, n_tokens = 428, progress = 0.45, t = 3.45 s / 124.22 tokens per second 7.38.603.886 I slot print_timing: id 0 | task 4605 | prompt eval time = 6364.96 ms / 971 tokens ( 6.56 ms per token, 152.55 tokens per second) 7.38.603.891 I slot print_timing: id 0 | task 4605 | eval time = 1786.07 ms / 2 tokens ( 1786.07 ms per token, 0.56 tokens per second) 7.38.603.891 I slot print_timing: id 0 | task 4605 | total time = 8151.03 ms / 973 tokens 7.38.603.891 I slot print_timing: id 0 | task 4605 | graphs reused = 3489 7.38.603.892 I slot print_timing: id 0 | task 4605 | graph reallocs = 0 / 0 (same size) / (changed size) 7.38.603.928 I slot release: id 0 | task 4605 | stop processing: n_tokens = 972, truncated = 0 7.38.603.948 I slot print_timing: id 2 | task 4610 | prompt processing, n_tokens = 836, progress = 0.87, t = 5.23 s / 159.79 tokens per second 7.38.607.455 I slot print_timing: id 3 | task 4609 | prompt processing, n_tokens = 836, progress = 0.89, t = 5.23 s / 159.79 tokens per second 7.39.294.789 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.892 (> 0.100 thold), f_keep = 0.889 7.39.294.864 I slot launch_slot_: id 0 | task 4617 | processing task, is_child = 0 7.39.420.927 I slot print_timing: id 1 | task 4613 | prompt processing, n_tokens = 431, progress = 0.46, t = 3.58 s / 120.24 tokens per second 7.39.422.806 I slot print_timing: id 2 | task 4610 | prompt processing, n_tokens = 960, progress = 1.00, t = 5.92 s / 162.08 tokens per second 7.39.424.759 I slot print_timing: id 3 | task 4609 | prompt processing, n_tokens = 940, progress = 1.00, t = 5.92 s / 158.71 tokens per second 7.40.624.990 I slot print_timing: id 1 | task 4613 | prompt processing, n_tokens = 836, progress = 0.88, t = 4.91 s / 170.24 tokens per second 7.41.046.014 I slot print_timing: id 2 | task 4610 | prompt eval time = 7249.27 ms / 964 tokens ( 7.52 ms per token, 132.98 tokens per second) 7.41.046.016 I slot print_timing: id 2 | task 4610 | eval time = 424.78 ms / 2 tokens ( 424.78 ms per token, 2.35 tokens per second) 7.41.046.016 I slot print_timing: id 2 | task 4610 | total time = 7674.06 ms / 966 tokens 7.41.046.017 I slot print_timing: id 2 | task 4610 | graphs reused = 3489 7.41.046.017 I slot print_timing: id 2 | task 4610 | graph reallocs = 0 / 0 (same size) / (changed size) 7.41.046.066 I slot release: id 2 | task 4610 | stop processing: n_tokens = 965, truncated = 0 7.41.046.287 I slot print_timing: id 3 | task 4609 | prompt eval time = 7249.37 ms / 944 tokens ( 7.68 ms per token, 130.22 tokens per second) 7.41.046.289 I slot print_timing: id 3 | task 4609 | eval time = 424.90 ms / 2 tokens ( 424.90 ms per token, 2.35 tokens per second) 7.41.046.290 I slot print_timing: id 3 | task 4609 | total time = 7674.27 ms / 946 tokens 7.41.046.290 I slot print_timing: id 3 | task 4609 | graphs reused = 3489 7.41.046.290 I slot print_timing: id 3 | task 4609 | graph reallocs = 0 / 0 (same size) / (changed size) 7.41.046.317 I slot release: id 3 | task 4609 | stop processing: n_tokens = 945, truncated = 0 7.41.046.325 I slot print_timing: id 1 | task 4613 | prompt processing, n_tokens = 943, progress = 1.00, t = 5.34 s / 176.75 tokens per second 7.41.120.159 I slot print_timing: id 0 | task 4617 | prompt eval time = 1751.00 ms / 133 tokens ( 13.17 ms per token, 75.96 tokens per second) 7.41.120.161 I slot print_timing: id 0 | task 4617 | eval time = 74.29 ms / 2 tokens ( 74.29 ms per token, 13.46 tokens per second) 7.41.120.162 I slot print_timing: id 0 | task 4617 | total time = 1825.29 ms / 135 tokens 7.41.120.162 I slot print_timing: id 0 | task 4617 | graphs reused = 3489 7.41.120.163 I slot print_timing: id 0 | task 4617 | graph reallocs = 0 / 0 (same size) / (changed size) 7.41.120.200 I slot release: id 0 | task 4617 | stop processing: n_tokens = 970, truncated = 0 7.41.120.385 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 965, t_last = 388902466547 7.41.120.443 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 333.484 MiB) 7.41.138.610 I slot launch_slot_: id 2 | task 4621 | processing task, is_child = 0 7.41.138.665 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 334.305 MiB) 7.41.156.169 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 333.620 MiB) 7.41.171.851 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 945, t_last = 388902466798 7.41.171.938 I slot launch_slot_: id 3 | task 4622 | processing task, is_child = 0 7.41.171.987 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 970, t_last = 388902540681 7.41.172.062 I slot launch_slot_: id 0 | task 4623 | processing task, is_child = 0 7.42.178.872 I slot print_timing: id 1 | task 4613 | prompt eval time = 5410.02 ms / 947 tokens ( 5.71 ms per token, 175.05 tokens per second) 7.42.178.875 I slot print_timing: id 1 | task 4613 | eval time = 1058.48 ms / 2 tokens ( 1058.48 ms per token, 0.94 tokens per second) 7.42.178.876 I slot print_timing: id 1 | task 4613 | total time = 6468.50 ms / 949 tokens 7.42.178.876 I slot print_timing: id 1 | task 4613 | graphs reused = 3489 7.42.178.876 I slot print_timing: id 1 | task 4613 | graph reallocs = 0 / 0 (same size) / (changed size) 7.42.178.919 I slot release: id 1 | task 4613 | stop processing: n_tokens = 948, truncated = 0 7.43.125.171 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 948, t_last = 388903599400 7.43.125.235 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 333.503 MiB) 7.43.143.580 I slot launch_slot_: id 1 | task 4626 | processing task, is_child = 0 7.45.122.525 I slot print_timing: id 0 | task 4623 | prompt processing, n_tokens = 459, progress = 0.47, t = 3.95 s / 116.19 tokens per second 7.45.143.664 I slot print_timing: id 2 | task 4621 | prompt processing, n_tokens = 679, progress = 0.85, t = 3.95 s / 171.88 tokens per second 7.45.145.556 I slot print_timing: id 3 | task 4622 | prompt processing, n_tokens = 679, progress = 0.85, t = 3.95 s / 171.89 tokens per second 7.46.439.074 I slot print_timing: id 0 | task 4623 | prompt processing, n_tokens = 826, progress = 0.85, t = 5.27 s / 156.83 tokens per second 7.46.856.993 I slot print_timing: id 1 | task 4626 | prompt processing, n_tokens = 335, progress = 0.35, t = 3.30 s / 101.65 tokens per second 7.46.857.009 I slot print_timing: id 2 | task 4621 | prompt processing, n_tokens = 795, progress = 0.99, t = 5.27 s / 150.94 tokens per second 7.46.860.514 I slot print_timing: id 3 | task 4622 | prompt processing, n_tokens = 794, progress = 0.99, t = 5.27 s / 150.75 tokens per second 7.47.635.247 I slot print_timing: id 0 | task 4623 | prompt processing, n_tokens = 971, progress = 1.00, t = 6.46 s / 150.25 tokens per second 7.47.638.753 I slot print_timing: id 1 | task 4626 | prompt processing, n_tokens = 437, progress = 0.46, t = 4.49 s / 97.30 tokens per second 7.48.460.855 I slot print_timing: id 2 | task 4621 | prompt eval time = 6462.86 ms / 799 tokens ( 8.09 ms per token, 123.63 tokens per second) 7.48.460.857 I slot print_timing: id 2 | task 4621 | eval time = 825.85 ms / 2 tokens ( 825.85 ms per token, 1.21 tokens per second) 7.48.460.857 I slot print_timing: id 2 | task 4621 | total time = 7288.71 ms / 801 tokens 7.48.460.858 I slot print_timing: id 2 | task 4621 | graphs reused = 3489 7.48.460.858 I slot print_timing: id 2 | task 4621 | graph reallocs = 0 / 0 (same size) / (changed size) 7.48.460.901 I slot release: id 2 | task 4621 | stop processing: n_tokens = 800, truncated = 0 7.48.461.112 I slot print_timing: id 3 | task 4622 | prompt eval time = 6463.03 ms / 798 tokens ( 8.10 ms per token, 123.47 tokens per second) 7.48.461.117 I slot print_timing: id 3 | task 4622 | eval time = 825.87 ms / 2 tokens ( 825.87 ms per token, 1.21 tokens per second) 7.48.461.117 I slot print_timing: id 3 | task 4622 | total time = 7288.90 ms / 800 tokens 7.48.461.117 I slot print_timing: id 3 | task 4622 | graphs reused = 3489 7.48.461.118 I slot print_timing: id 3 | task 4622 | graph reallocs = 0 / 0 (same size) / (changed size) 7.48.461.147 I slot release: id 3 | task 4622 | stop processing: n_tokens = 799, truncated = 0 7.48.461.155 I slot print_timing: id 1 | task 4626 | prompt processing, n_tokens = 826, progress = 0.87, t = 5.32 s / 155.35 tokens per second 7.48.836.492 I slot print_timing: id 0 | task 4623 | prompt eval time = 7288.65 ms / 975 tokens ( 7.48 ms per token, 133.77 tokens per second) 7.48.836.495 I slot print_timing: id 0 | task 4623 | eval time = 375.77 ms / 2 tokens ( 375.77 ms per token, 2.66 tokens per second) 7.48.836.495 I slot print_timing: id 0 | task 4623 | total time = 7664.42 ms / 977 tokens 7.48.836.496 I slot print_timing: id 0 | task 4623 | graphs reused = 3489 7.48.836.496 I slot print_timing: id 0 | task 4623 | graph reallocs = 0 / 0 (same size) / (changed size) 7.48.836.542 I slot release: id 0 | task 4623 | stop processing: n_tokens = 976, truncated = 0 7.48.836.551 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.889 (> 0.100 thold), f_keep = 0.875 7.48.836.608 I slot launch_slot_: id 0 | task 4632 | processing task, is_child = 0 7.48.836.656 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.274 MiB) 7.48.845.748 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 333.816 MiB) 7.48.855.810 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 800, t_last = 388909881382 7.48.855.914 I slot launch_slot_: id 2 | task 4633 | processing task, is_child = 0 7.48.855.958 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 799, t_last = 388909881628 7.48.856.023 I slot launch_slot_: id 3 | task 4634 | processing task, is_child = 0 7.48.859.297 I slot print_timing: id 1 | task 4626 | prompt processing, n_tokens = 949, progress = 1.00, t = 5.69 s / 166.70 tokens per second 7.50.526.441 I slot print_timing: id 1 | task 4626 | prompt eval time = 6686.49 ms / 953 tokens ( 7.02 ms per token, 142.53 tokens per second) 7.50.526.445 I slot print_timing: id 1 | task 4626 | eval time = 696.35 ms / 2 tokens ( 696.35 ms per token, 1.44 tokens per second) 7.50.526.445 I slot print_timing: id 1 | task 4626 | total time = 7382.84 ms / 955 tokens 7.50.526.446 I slot print_timing: id 1 | task 4626 | graphs reused = 3489 7.50.526.446 I slot print_timing: id 1 | task 4626 | graph reallocs = 0 / 0 (same size) / (changed size) 7.50.526.494 I slot release: id 1 | task 4626 | stop processing: n_tokens = 954, truncated = 0 7.51.044.060 I slot print_timing: id 0 | task 4632 | prompt eval time = 1670.22 ms / 135 tokens ( 12.37 ms per token, 80.83 tokens per second) 7.51.044.063 I slot print_timing: id 0 | task 4632 | eval time = 517.81 ms / 2 tokens ( 517.81 ms per token, 1.93 tokens per second) 7.51.044.064 I slot print_timing: id 0 | task 4632 | total time = 2188.03 ms / 137 tokens 7.51.044.064 I slot print_timing: id 0 | task 4632 | graphs reused = 3489 7.51.044.065 I slot print_timing: id 0 | task 4632 | graph reallocs = 0 / 0 (same size) / (changed size) 7.51.044.106 I slot release: id 0 | task 4632 | stop processing: n_tokens = 962, truncated = 0 7.51.044.115 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 954, t_last = 388911946975 7.51.044.170 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.724 MiB) 7.51.057.121 I slot launch_slot_: id 1 | task 4638 | processing task, is_child = 0 7.51.057.174 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.313 MiB) 7.51.067.230 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 962, t_last = 388912464587 7.51.067.328 I slot launch_slot_: id 0 | task 4639 | processing task, is_child = 0 7.53.113.467 I slot print_timing: id 2 | task 4633 | prompt processing, n_tokens = 779, progress = 0.84, t = 4.09 s / 190.49 tokens per second 7.53.115.625 I slot print_timing: id 3 | task 4634 | prompt processing, n_tokens = 779, progress = 0.87, t = 4.09 s / 190.49 tokens per second 7.54.208.728 I slot print_timing: id 0 | task 4639 | prompt processing, n_tokens = 304, progress = 0.34, t = 3.14 s / 96.77 tokens per second 7.54.208.737 I slot print_timing: id 1 | task 4638 | prompt processing, n_tokens = 304, progress = 0.34, t = 3.14 s / 96.78 tokens per second 7.54.208.742 I slot print_timing: id 2 | task 4633 | prompt processing, n_tokens = 926, progress = 1.00, t = 5.35 s / 173.17 tokens per second 7.54.366.376 I slot print_timing: id 3 | task 4634 | prompt processing, n_tokens = 894, progress = 1.00, t = 5.35 s / 167.18 tokens per second 7.54.856.320 I slot print_timing: id 0 | task 4639 | prompt processing, n_tokens = 383, progress = 0.43, t = 3.79 s / 101.09 tokens per second 7.54.859.783 I slot print_timing: id 1 | task 4638 | prompt processing, n_tokens = 386, progress = 0.43, t = 3.79 s / 101.89 tokens per second 7.56.333.716 I slot print_timing: id 2 | task 4633 | prompt eval time = 5994.83 ms / 930 tokens ( 6.45 ms per token, 155.13 tokens per second) 7.56.333.719 I slot print_timing: id 2 | task 4633 | eval time = 1477.63 ms / 2 tokens ( 1477.63 ms per token, 0.68 tokens per second) 7.56.333.719 I slot print_timing: id 2 | task 4633 | total time = 7472.46 ms / 932 tokens 7.56.333.720 I slot print_timing: id 2 | task 4633 | graphs reused = 3489 7.56.333.720 I slot print_timing: id 2 | task 4633 | graph reallocs = 0 / 0 (same size) / (changed size) 7.56.333.781 I slot release: id 2 | task 4633 | stop processing: n_tokens = 931, truncated = 0 7.56.334.012 I slot print_timing: id 3 | task 4634 | prompt eval time = 5995.00 ms / 898 tokens ( 6.68 ms per token, 149.79 tokens per second) 7.56.334.015 I slot print_timing: id 3 | task 4634 | eval time = 1477.70 ms / 2 tokens ( 1477.70 ms per token, 0.68 tokens per second) 7.56.334.016 I slot print_timing: id 3 | task 4634 | total time = 7472.70 ms / 900 tokens 7.56.334.016 I slot print_timing: id 3 | task 4634 | graphs reused = 3489 7.56.334.016 I slot print_timing: id 3 | task 4634 | graph reallocs = 0 / 0 (same size) / (changed size) 7.56.334.046 I slot release: id 3 | task 4634 | stop processing: n_tokens = 899, truncated = 0 7.56.334.054 I slot print_timing: id 0 | task 4639 | prompt processing, n_tokens = 779, progress = 0.87, t = 5.27 s / 147.92 tokens per second 7.56.337.165 I slot print_timing: id 1 | task 4638 | prompt processing, n_tokens = 779, progress = 0.86, t = 5.27 s / 147.93 tokens per second 7.56.852.522 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 931, t_last = 388917754262 7.56.852.587 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 333.347 MiB) 7.56.885.615 I slot launch_slot_: id 2 | task 4645 | processing task, is_child = 0 7.56.885.677 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.802 MiB) 7.56.893.494 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.898 7.56.893.535 I slot launch_slot_: id 3 | task 4646 | processing task, is_child = 0 7.56.893.542 I slot print_timing: id 0 | task 4639 | prompt processing, n_tokens = 895, progress = 1.00, t = 5.79 s / 154.71 tokens per second 7.56.895.578 I slot print_timing: id 1 | task 4638 | prompt processing, n_tokens = 898, progress = 1.00, t = 5.79 s / 155.23 tokens per second 7.58.322.425 I slot print_timing: id 0 | task 4639 | prompt eval time = 6684.84 ms / 899 tokens ( 7.44 ms per token, 134.48 tokens per second) 7.58.322.427 I slot print_timing: id 0 | task 4639 | eval time = 570.25 ms / 2 tokens ( 570.25 ms per token, 1.75 tokens per second) 7.58.322.427 I slot print_timing: id 0 | task 4639 | total time = 7255.09 ms / 901 tokens 7.58.322.428 I slot print_timing: id 0 | task 4639 | graphs reused = 3489 7.58.322.428 I slot print_timing: id 0 | task 4639 | graph reallocs = 0 / 0 (same size) / (changed size) 7.58.322.472 I slot release: id 0 | task 4639 | stop processing: n_tokens = 900, truncated = 0 7.58.322.632 I slot print_timing: id 1 | task 4638 | prompt eval time = 6684.99 ms / 902 tokens ( 7.41 ms per token, 134.93 tokens per second) 7.58.322.634 I slot print_timing: id 1 | task 4638 | eval time = 570.22 ms / 2 tokens ( 570.22 ms per token, 1.75 tokens per second) 7.58.322.634 I slot print_timing: id 1 | task 4638 | total time = 7255.21 ms / 904 tokens 7.58.322.634 I slot print_timing: id 1 | task 4638 | graphs reused = 3489 7.58.322.635 I slot print_timing: id 1 | task 4638 | graph reallocs = 0 / 0 (same size) / (changed size) 7.58.322.669 I slot release: id 1 | task 4638 | stop processing: n_tokens = 903, truncated = 0 7.58.957.884 I slot print_timing: id 3 | task 4646 | prompt eval time = 1425.25 ms / 111 tokens ( 12.84 ms per token, 77.88 tokens per second) 7.58.957.887 I slot print_timing: id 3 | task 4646 | eval time = 635.01 ms / 2 tokens ( 635.01 ms per token, 1.57 tokens per second) 7.58.957.888 I slot print_timing: id 3 | task 4646 | total time = 2060.26 ms / 113 tokens 7.58.957.888 I slot print_timing: id 3 | task 4646 | graphs reused = 3489 7.58.957.889 I slot print_timing: id 3 | task 4646 | graph reallocs = 0 / 0 (same size) / (changed size) 7.58.957.927 I slot release: id 3 | task 4646 | stop processing: n_tokens = 891, truncated = 0 7.58.957.934 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 900, t_last = 388919742953 7.58.957.989 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 332.701 MiB) 7.58.971.264 I slot launch_slot_: id 0 | task 4650 | processing task, is_child = 0 7.58.971.318 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 332.467 MiB) 7.58.980.794 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 340.601 MiB) 7.58.988.991 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 903, t_last = 388919743150 7.58.989.095 I slot launch_slot_: id 1 | task 4651 | processing task, is_child = 0 7.58.989.155 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 891, t_last = 388920378408 7.58.989.227 I slot launch_slot_: id 3 | task 4652 | processing task, is_child = 0 8.01.261.433 I slot print_timing: id 2 | task 4645 | prompt processing, n_tokens = 1061, progress = 0.87, t = 4.16 s / 255.28 tokens per second 8.02.796.391 I slot print_timing: id 0 | task 4650 | prompt processing, n_tokens = 402, progress = 0.31, t = 3.81 s / 105.59 tokens per second 8.02.796.407 I slot print_timing: id 1 | task 4651 | prompt processing, n_tokens = 402, progress = 0.33, t = 3.81 s / 105.59 tokens per second 8.02.796.418 I slot print_timing: id 2 | task 4645 | prompt processing, n_tokens = 1221, progress = 1.00, t = 5.90 s / 206.99 tokens per second 8.03.530.719 I slot print_timing: id 3 | task 4652 | prompt processing, n_tokens = 961, progress = 0.37, t = 3.81 s / 252.55 tokens per second 8.07.062.348 I slot print_timing: id 0 | task 4650 | prompt processing, n_tokens = 774, progress = 0.60, t = 8.07 s / 95.88 tokens per second 8.07.065.417 I slot print_timing: id 1 | task 4651 | prompt processing, n_tokens = 720, progress = 0.58, t = 8.07 s / 89.19 tokens per second 8.07.069.008 I slot print_timing: id 3 | task 4652 | prompt processing, n_tokens = 2071, progress = 0.80, t = 8.07 s / 256.60 tokens per second 8.08.936.628 I slot print_timing: id 2 | task 4645 | prompt eval time = 10164.78 ms / 1225 tokens ( 8.30 ms per token, 120.51 tokens per second) 8.08.936.631 I slot print_timing: id 2 | task 4645 | eval time = 1874.29 ms / 2 tokens ( 1874.29 ms per token, 0.53 tokens per second) 8.08.936.631 I slot print_timing: id 2 | task 4645 | total time = 12039.07 ms / 1227 tokens 8.08.936.632 I slot print_timing: id 2 | task 4645 | graphs reused = 3489 8.08.936.632 I slot print_timing: id 2 | task 4645 | graph reallocs = 0 / 0 (same size) / (changed size) 8.08.936.683 I slot release: id 2 | task 4645 | stop processing: n_tokens = 1226, truncated = 0 8.08.936.696 I slot print_timing: id 0 | task 4650 | prompt processing, n_tokens = 1061, progress = 0.82, t = 9.95 s / 106.66 tokens per second 8.08.939.520 I slot print_timing: id 1 | task 4651 | prompt processing, n_tokens = 1061, progress = 0.86, t = 9.95 s / 106.66 tokens per second 8.08.941.427 I slot print_timing: id 3 | task 4652 | prompt processing, n_tokens = 2288, progress = 0.88, t = 9.95 s / 230.06 tokens per second 8.09.843.773 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1226, t_last = 388930357164 8.09.843.848 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 338.705 MiB) 8.10.472.150 I slot launch_slot_: id 2 | task 4658 | processing task, is_child = 0 8.10.472.164 I slot print_timing: id 0 | task 4650 | prompt processing, n_tokens = 1286, progress = 1.00, t = 10.85 s / 118.48 tokens per second 8.10.474.180 I slot print_timing: id 1 | task 4651 | prompt processing, n_tokens = 1232, progress = 1.00, t = 10.85 s / 113.50 tokens per second 8.10.476.252 I slot print_timing: id 3 | task 4652 | prompt processing, n_tokens = 2583, progress = 1.00, t = 10.85 s / 238.01 tokens per second 8.12.461.629 I slot print_timing: id 0 | task 4650 | prompt eval time = 12323.08 ms / 1290 tokens ( 9.55 ms per token, 104.68 tokens per second) 8.12.461.631 I slot print_timing: id 0 | task 4650 | eval time = 1149.31 ms / 2 tokens ( 1149.31 ms per token, 0.87 tokens per second) 8.12.461.632 I slot print_timing: id 0 | task 4650 | total time = 13472.39 ms / 1292 tokens 8.12.461.632 I slot print_timing: id 0 | task 4650 | graphs reused = 3489 8.12.461.633 I slot print_timing: id 0 | task 4650 | graph reallocs = 0 / 0 (same size) / (changed size) 8.12.461.690 I slot release: id 0 | task 4650 | stop processing: n_tokens = 1291, truncated = 0 8.12.461.843 I slot print_timing: id 1 | task 4651 | prompt eval time = 12323.17 ms / 1236 tokens ( 9.97 ms per token, 100.30 tokens per second) 8.12.461.846 I slot print_timing: id 1 | task 4651 | eval time = 1149.36 ms / 2 tokens ( 1149.36 ms per token, 0.87 tokens per second) 8.12.461.847 I slot print_timing: id 1 | task 4651 | total time = 13472.53 ms / 1238 tokens 8.12.461.847 I slot print_timing: id 1 | task 4651 | graphs reused = 3489 8.12.461.848 I slot print_timing: id 1 | task 4651 | graph reallocs = 0 / 0 (same size) / (changed size) 8.12.461.886 I slot release: id 1 | task 4651 | stop processing: n_tokens = 1237, truncated = 0 8.12.462.101 I slot print_timing: id 3 | task 4652 | prompt eval time = 12321.42 ms / 2587 tokens ( 4.76 ms per token, 209.96 tokens per second) 8.12.462.103 I slot print_timing: id 3 | task 4652 | eval time = 1149.44 ms / 2 tokens ( 1149.44 ms per token, 0.87 tokens per second) 8.12.462.104 I slot print_timing: id 3 | task 4652 | total time = 13470.86 ms / 2589 tokens 8.12.462.104 I slot print_timing: id 3 | task 4652 | graphs reused = 3489 8.12.462.104 I slot print_timing: id 3 | task 4652 | graph reallocs = 0 / 0 (same size) / (changed size) 8.12.462.229 I slot release: id 3 | task 4652 | stop processing: n_tokens = 2588, truncated = 0 8.13.362.332 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.848 (> 0.100 thold), f_keep = 0.898 8.13.362.387 I slot launch_slot_: id 3 | task 4662 | processing task, is_child = 0 8.13.362.458 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 340.328 MiB) 8.14.273.672 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 339.506 MiB) 8.14.283.219 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1291, t_last = 388933882172 8.14.283.349 I slot launch_slot_: id 0 | task 4663 | processing task, is_child = 0 8.14.283.406 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1237, t_last = 388933882367 8.14.283.490 I slot launch_slot_: id 1 | task 4664 | processing task, is_child = 0 8.17.133.401 I slot print_timing: id 2 | task 4658 | prompt processing, n_tokens = 2288, progress = 0.92, t = 6.26 s / 365.32 tokens per second 8.19.477.207 I slot print_timing: id 0 | task 4663 | prompt processing, n_tokens = 961, progress = 0.36, t = 5.19 s / 185.04 tokens per second 8.19.477.249 I slot print_timing: id 1 | task 4664 | prompt processing, n_tokens = 520, progress = 0.29, t = 5.19 s / 100.13 tokens per second 8.19.477.272 I slot print_timing: id 2 | task 4658 | prompt processing, n_tokens = 2496, progress = 1.00, t = 9.00 s / 277.31 tokens per second 8.23.039.657 I slot print_timing: id 3 | task 4662 | prompt eval time = 5191.62 ms / 454 tokens ( 11.44 ms per token, 87.45 tokens per second) 8.23.039.661 I slot print_timing: id 3 | task 4662 | eval time = 3562.46 ms / 2 tokens ( 3562.46 ms per token, 0.28 tokens per second) 8.23.039.661 I slot print_timing: id 3 | task 4662 | total time = 8754.09 ms / 456 tokens 8.23.039.662 I slot print_timing: id 3 | task 4662 | graphs reused = 3489 8.23.039.662 I slot print_timing: id 3 | task 4662 | graph reallocs = 0 / 0 (same size) / (changed size) 8.23.039.775 I slot release: id 3 | task 4662 | stop processing: n_tokens = 2743, truncated = 0 8.23.039.795 I slot print_timing: id 0 | task 4663 | prompt processing, n_tokens = 2139, progress = 0.81, t = 8.76 s / 244.30 tokens per second 8.23.043.547 I slot print_timing: id 1 | task 4664 | prompt processing, n_tokens = 1263, progress = 0.71, t = 8.76 s / 144.25 tokens per second 8.23.884.002 I slot print_timing: id 2 | task 4658 | prompt eval time = 12563.35 ms / 2500 tokens ( 5.03 ms per token, 198.99 tokens per second) 8.23.884.008 I slot print_timing: id 2 | task 4658 | eval time = 844.49 ms / 2 tokens ( 844.49 ms per token, 1.18 tokens per second) 8.23.884.008 I slot print_timing: id 2 | task 4658 | total time = 13407.84 ms / 2502 tokens 8.23.884.009 I slot print_timing: id 2 | task 4658 | graphs reused = 3489 8.23.884.009 I slot print_timing: id 2 | task 4658 | graph reallocs = 0 / 0 (same size) / (changed size) 8.23.884.120 I slot release: id 2 | task 4658 | stop processing: n_tokens = 2501, truncated = 0 8.23.884.129 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 2743, t_last = 388944460257 8.23.884.237 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 329.573 MiB) 8.23.915.642 I slot launch_slot_: id 3 | task 4669 | processing task, is_child = 0 8.23.915.745 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.509 MiB) 8.23.940.083 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 2501, t_last = 388945304602 8.23.940.249 I slot launch_slot_: id 2 | task 4670 | processing task, is_child = 0 8.23.940.262 I slot print_timing: id 0 | task 4663 | prompt processing, n_tokens = 2288, progress = 0.86, t = 9.60 s / 238.33 tokens per second 8.23.942.214 I slot print_timing: id 1 | task 4664 | prompt processing, n_tokens = 1447, progress = 0.81, t = 9.60 s / 150.73 tokens per second 8.25.983.187 I slot print_timing: id 0 | task 4663 | prompt processing, n_tokens = 2651, progress = 1.00, t = 11.70 s / 226.59 tokens per second 8.26.173.724 I slot print_timing: id 1 | task 4664 | prompt processing, n_tokens = 1775, progress = 1.00, t = 11.70 s / 151.71 tokens per second 8.27.420.334 I slot print_timing: id 2 | task 4670 | prompt processing, n_tokens = 520, progress = 0.25, t = 3.48 s / 149.61 tokens per second 8.27.420.363 I slot print_timing: id 3 | task 4669 | prompt processing, n_tokens = 520, progress = 0.28, t = 3.48 s / 149.62 tokens per second 8.30.649.343 I slot print_timing: id 0 | task 4663 | prompt eval time = 13136.61 ms / 2655 tokens ( 4.95 ms per token, 202.11 tokens per second) 8.30.649.345 I slot print_timing: id 0 | task 4663 | eval time = 3229.23 ms / 2 tokens ( 3229.23 ms per token, 0.31 tokens per second) 8.30.649.345 I slot print_timing: id 0 | task 4663 | total time = 16365.84 ms / 2657 tokens 8.30.649.346 I slot print_timing: id 0 | task 4663 | graphs reused = 3489 8.30.649.346 I slot print_timing: id 0 | task 4663 | graph reallocs = 0 / 0 (same size) / (changed size) 8.30.649.456 I slot release: id 0 | task 4663 | stop processing: n_tokens = 2656, truncated = 0 8.30.649.705 I slot print_timing: id 1 | task 4664 | prompt eval time = 13136.73 ms / 1779 tokens ( 7.38 ms per token, 135.42 tokens per second) 8.30.649.708 I slot print_timing: id 1 | task 4664 | eval time = 3229.38 ms / 2 tokens ( 3229.38 ms per token, 0.31 tokens per second) 8.30.649.709 I slot print_timing: id 1 | task 4664 | total time = 16366.10 ms / 1781 tokens 8.30.649.710 I slot print_timing: id 1 | task 4664 | graphs reused = 3489 8.30.649.710 I slot print_timing: id 1 | task 4664 | graph reallocs = 0 / 0 (same size) / (changed size) 8.30.649.804 I slot release: id 1 | task 4664 | stop processing: n_tokens = 1780, truncated = 0 8.30.649.818 I slot print_timing: id 2 | task 4670 | prompt processing, n_tokens = 1447, progress = 0.71, t = 6.70 s / 215.81 tokens per second 8.30.653.954 I slot print_timing: id 3 | task 4669 | prompt processing, n_tokens = 1325, progress = 0.72, t = 6.70 s / 197.62 tokens per second 8.31.091.498 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 8.31.091.564 I slot launch_slot_: id 1 | task 4675 | processing task, is_child = 0 8.31.091.688 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 329.886 MiB) 8.31.292.025 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 2656, t_last = 388952069937 8.31.292.221 I slot launch_slot_: id 0 | task 4676 | processing task, is_child = 0 8.31.295.654 I slot print_timing: id 2 | task 4670 | prompt processing, n_tokens = 1532, progress = 0.75, t = 7.15 s / 214.35 tokens per second 8.31.297.551 I slot print_timing: id 3 | task 4669 | prompt processing, n_tokens = 1447, progress = 0.79, t = 7.15 s / 202.46 tokens per second 8.34.507.243 I slot print_timing: id 0 | task 4676 | prompt processing, n_tokens = 208, progress = 0.11, t = 3.21 s / 64.70 tokens per second 8.34.526.302 I slot print_timing: id 1 | task 4675 | prompt processing, n_tokens = 511, progress = 1.00, t = 3.21 s / 158.95 tokens per second 8.34.528.773 I slot print_timing: id 2 | task 4670 | prompt processing, n_tokens = 2044, progress = 1.00, t = 10.56 s / 193.50 tokens per second 8.34.530.828 I slot print_timing: id 3 | task 4669 | prompt processing, n_tokens = 1837, progress = 1.00, t = 10.56 s / 173.91 tokens per second 8.35.240.396 I slot print_timing: id 0 | task 4676 | prompt processing, n_tokens = 520, progress = 0.28, t = 3.95 s / 131.73 tokens per second 8.36.778.984 I slot print_timing: id 1 | task 4675 | prompt eval time = 3947.52 ms / 515 tokens ( 7.67 ms per token, 130.46 tokens per second) 8.36.778.986 I slot print_timing: id 1 | task 4675 | eval time = 1539.03 ms / 2 tokens ( 1539.03 ms per token, 0.65 tokens per second) 8.36.778.986 I slot print_timing: id 1 | task 4675 | total time = 5486.55 ms / 517 tokens 8.36.778.987 I slot print_timing: id 1 | task 4675 | graphs reused = 3489 8.36.778.987 I slot print_timing: id 1 | task 4675 | graph reallocs = 0 / 0 (same size) / (changed size) 8.36.779.102 I slot release: id 1 | task 4675 | stop processing: n_tokens = 1963, truncated = 0 8.36.779.337 I slot print_timing: id 2 | task 4670 | prompt eval time = 11296.00 ms / 2048 tokens ( 5.52 ms per token, 181.30 tokens per second) 8.36.779.340 I slot print_timing: id 2 | task 4670 | eval time = 1539.19 ms / 2 tokens ( 1539.19 ms per token, 0.65 tokens per second) 8.36.779.341 I slot print_timing: id 2 | task 4670 | total time = 12835.19 ms / 2050 tokens 8.36.779.341 I slot print_timing: id 2 | task 4670 | graphs reused = 3489 8.36.779.341 I slot print_timing: id 2 | task 4670 | graph reallocs = 0 / 0 (same size) / (changed size) 8.36.779.421 I slot release: id 2 | task 4670 | stop processing: n_tokens = 2049, truncated = 0 8.36.779.658 I slot print_timing: id 3 | task 4669 | prompt eval time = 11296.07 ms / 1841 tokens ( 6.14 ms per token, 162.98 tokens per second) 8.36.779.661 I slot print_timing: id 3 | task 4669 | eval time = 1539.27 ms / 2 tokens ( 1539.27 ms per token, 0.65 tokens per second) 8.36.779.661 I slot print_timing: id 3 | task 4669 | total time = 12835.34 ms / 1843 tokens 8.36.779.661 I slot print_timing: id 3 | task 4669 | graphs reused = 3489 8.36.779.661 I slot print_timing: id 3 | task 4669 | graph reallocs = 0 / 0 (same size) / (changed size) 8.36.779.701 I slot release: id 3 | task 4669 | stop processing: n_tokens = 1842, truncated = 0 8.36.779.710 I slot print_timing: id 0 | task 4676 | prompt processing, n_tokens = 1336, progress = 0.72, t = 5.49 s / 243.50 tokens per second 8.36.788.151 I slot print_timing: id 0 | task 4676 | prompt processing, n_tokens = 1447, progress = 0.78, t = 5.50 s / 263.29 tokens per second 8.37.125.675 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1963, t_last = 388958199584 8.37.125.765 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 330.883 MiB) 8.37.905.472 I slot launch_slot_: id 1 | task 4682 | processing task, is_child = 0 8.37.905.671 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 329.299 MiB) 8.38.019.798 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 329.221 MiB) 8.38.465.783 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 2049, t_last = 388958199904 8.38.466.041 I slot launch_slot_: id 2 | task 4683 | processing task, is_child = 0 8.38.466.127 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.833 (> 0.100 thold), f_keep = 0.806 8.38.466.156 I slot launch_slot_: id 3 | task 4684 | processing task, is_child = 0 8.38.466.172 I slot print_timing: id 0 | task 4676 | prompt processing, n_tokens = 1848, progress = 1.00, t = 5.83 s / 316.79 tokens per second 8.40.407.610 I slot print_timing: id 0 | task 4676 | prompt eval time = 8495.47 ms / 1852 tokens ( 4.59 ms per token, 218.00 tokens per second) 8.40.407.613 I slot print_timing: id 0 | task 4676 | eval time = 619.91 ms / 2 tokens ( 619.91 ms per token, 1.61 tokens per second) 8.40.407.613 I slot print_timing: id 0 | task 4676 | total time = 9115.38 ms / 1854 tokens 8.40.407.614 I slot print_timing: id 0 | task 4676 | graphs reused = 3489 8.40.407.614 I slot print_timing: id 0 | task 4676 | graph reallocs = 0 / 0 (same size) / (changed size) 8.40.407.722 I slot release: id 0 | task 4676 | stop processing: n_tokens = 1853, truncated = 0 8.41.950.152 I slot print_timing: id 3 | task 4684 | prompt eval time = 1920.23 ms / 334 tokens ( 5.75 ms per token, 173.94 tokens per second) 8.41.950.154 I slot print_timing: id 3 | task 4684 | eval time = 1541.83 ms / 2 tokens ( 1541.83 ms per token, 0.65 tokens per second) 8.41.950.155 I slot print_timing: id 3 | task 4684 | total time = 3462.06 ms / 336 tokens 8.41.950.155 I slot print_timing: id 3 | task 4684 | graphs reused = 3489 8.41.950.156 I slot print_timing: id 3 | task 4684 | graph reallocs = 0 / 0 (same size) / (changed size) 8.41.950.239 I slot release: id 3 | task 4684 | stop processing: n_tokens = 1782, truncated = 0 8.41.950.248 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1853, t_last = 388961828203 8.41.950.354 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 330.805 MiB) 8.42.015.368 I slot launch_slot_: id 0 | task 4688 | processing task, is_child = 0 8.42.015.451 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 329.768 MiB) 8.42.067.353 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1782, t_last = 388963370720 8.42.067.492 I slot launch_slot_: id 3 | task 4689 | processing task, is_child = 0 8.42.067.655 I slot print_timing: id 1 | task 4682 | prompt processing, n_tokens = 615, progress = 0.85, t = 3.46 s / 177.63 tokens per second 8.42.072.257 I slot print_timing: id 2 | task 4683 | prompt processing, n_tokens = 615, progress = 0.82, t = 3.46 s / 177.64 tokens per second 8.43.218.856 I slot print_timing: id 1 | task 4682 | prompt processing, n_tokens = 722, progress = 0.99, t = 4.71 s / 153.20 tokens per second 8.43.222.291 I slot print_timing: id 2 | task 4683 | prompt processing, n_tokens = 744, progress = 0.99, t = 4.71 s / 157.88 tokens per second 8.45.401.692 I slot print_timing: id 1 | task 4682 | prompt eval time = 5441.32 ms / 726 tokens ( 7.49 ms per token, 133.42 tokens per second) 8.45.401.694 I slot print_timing: id 1 | task 4682 | eval time = 1472.65 ms / 2 tokens ( 1472.65 ms per token, 0.68 tokens per second) 8.45.401.695 I slot print_timing: id 1 | task 4682 | total time = 6913.97 ms / 728 tokens 8.45.401.695 I slot print_timing: id 1 | task 4682 | graphs reused = 3489 8.45.401.696 I slot print_timing: id 1 | task 4682 | graph reallocs = 0 / 0 (same size) / (changed size) 8.45.401.751 I slot release: id 1 | task 4682 | stop processing: n_tokens = 727, truncated = 0 8.45.401.984 I slot print_timing: id 2 | task 4683 | prompt eval time = 5441.36 ms / 748 tokens ( 7.27 ms per token, 137.47 tokens per second) 8.45.401.986 I slot print_timing: id 2 | task 4683 | eval time = 1472.70 ms / 2 tokens ( 1472.70 ms per token, 0.68 tokens per second) 8.45.401.987 I slot print_timing: id 2 | task 4683 | total time = 6914.06 ms / 750 tokens 8.45.401.987 I slot print_timing: id 2 | task 4683 | graphs reused = 3489 8.45.401.988 I slot print_timing: id 2 | task 4683 | graph reallocs = 0 / 0 (same size) / (changed size) 8.45.402.019 I slot release: id 2 | task 4683 | stop processing: n_tokens = 749, truncated = 0 8.45.402.028 I slot print_timing: id 0 | task 4688 | prompt processing, n_tokens = 615, progress = 0.81, t = 3.33 s / 184.46 tokens per second 8.45.414.623 I slot print_timing: id 3 | task 4689 | prompt processing, n_tokens = 615, progress = 0.85, t = 3.32 s / 185.04 tokens per second 8.45.792.605 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.870 (> 0.100 thold), f_keep = 0.884 8.45.792.668 I slot launch_slot_: id 1 | task 4694 | processing task, is_child = 0 8.45.792.721 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 332.936 MiB) 8.46.114.316 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 749, t_last = 388966822500 8.46.114.434 I slot launch_slot_: id 2 | task 4695 | processing task, is_child = 0 8.46.114.441 I slot print_timing: id 0 | task 4688 | prompt processing, n_tokens = 757, progress = 0.99, t = 3.73 s / 203.22 tokens per second 8.46.129.088 I slot print_timing: id 3 | task 4689 | prompt processing, n_tokens = 721, progress = 0.99, t = 3.71 s / 194.09 tokens per second 8.47.263.958 I slot print_timing: id 0 | task 4688 | prompt eval time = 4710.66 ms / 761 tokens ( 6.19 ms per token, 161.55 tokens per second) 8.47.263.962 I slot print_timing: id 0 | task 4688 | eval time = 485.79 ms / 2 tokens ( 485.79 ms per token, 2.06 tokens per second) 8.47.263.962 I slot print_timing: id 0 | task 4688 | total time = 5196.45 ms / 763 tokens 8.47.263.963 I slot print_timing: id 0 | task 4688 | graphs reused = 3489 8.47.263.963 I slot print_timing: id 0 | task 4688 | graph reallocs = 0 / 0 (same size) / (changed size) 8.47.263.997 I slot release: id 0 | task 4688 | stop processing: n_tokens = 762, truncated = 0 8.47.264.689 I slot print_timing: id 3 | task 4689 | prompt eval time = 4700.57 ms / 725 tokens ( 6.48 ms per token, 154.24 tokens per second) 8.47.264.692 I slot print_timing: id 3 | task 4689 | eval time = 486.29 ms / 2 tokens ( 486.29 ms per token, 2.06 tokens per second) 8.47.264.692 I slot print_timing: id 3 | task 4689 | total time = 5186.86 ms / 727 tokens 8.47.264.693 I slot print_timing: id 3 | task 4689 | graphs reused = 3489 8.47.264.693 I slot print_timing: id 3 | task 4689 | graph reallocs = 0 / 0 (same size) / (changed size) 8.47.264.718 I slot release: id 3 | task 4689 | stop processing: n_tokens = 726, truncated = 0 8.47.436.069 I slot print_timing: id 1 | task 4694 | prompt eval time = 1138.64 ms / 124 tokens ( 9.18 ms per token, 108.90 tokens per second) 8.47.436.072 I slot print_timing: id 1 | task 4694 | eval time = 171.63 ms / 2 tokens ( 171.63 ms per token, 5.83 tokens per second) 8.47.436.073 I slot print_timing: id 1 | task 4694 | total time = 1310.26 ms / 126 tokens 8.47.436.073 I slot print_timing: id 1 | task 4694 | graphs reused = 3489 8.47.436.073 I slot print_timing: id 1 | task 4694 | graph reallocs = 0 / 0 (same size) / (changed size) 8.47.436.105 I slot release: id 1 | task 4694 | stop processing: n_tokens = 740, truncated = 0 8.47.436.111 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 762, t_last = 388968684478 8.47.436.160 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 333.034 MiB) 8.47.480.020 I slot launch_slot_: id 0 | task 4699 | processing task, is_child = 0 8.47.480.072 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 332.545 MiB) 8.47.518.603 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 332.604 MiB) 8.47.547.058 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 726, t_last = 388968685199 8.47.547.151 I slot launch_slot_: id 3 | task 4700 | processing task, is_child = 0 8.47.547.189 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 740, t_last = 388968856586 8.47.547.257 I slot launch_slot_: id 1 | task 4701 | processing task, is_child = 0 8.50.395.768 I slot print_timing: id 2 | task 4695 | prompt processing, n_tokens = 794, progress = 0.99, t = 4.27 s / 186.09 tokens per second 8.51.224.174 I slot print_timing: id 0 | task 4699 | prompt processing, n_tokens = 526, progress = 0.50, t = 3.68 s / 143.06 tokens per second 8.51.226.523 I slot print_timing: id 1 | task 4701 | prompt processing, n_tokens = 283, progress = 0.35, t = 3.68 s / 76.97 tokens per second 8.51.228.693 I slot print_timing: id 3 | task 4700 | prompt processing, n_tokens = 293, progress = 0.36, t = 3.67 s / 79.74 tokens per second 8.53.510.309 I slot print_timing: id 2 | task 4695 | prompt eval time = 5095.14 ms / 798 tokens ( 6.38 ms per token, 156.62 tokens per second) 8.53.510.311 I slot print_timing: id 2 | task 4695 | eval time = 2286.14 ms / 2 tokens ( 2286.14 ms per token, 0.44 tokens per second) 8.53.510.312 I slot print_timing: id 2 | task 4695 | total time = 7381.27 ms / 800 tokens 8.53.510.312 I slot print_timing: id 2 | task 4695 | graphs reused = 3489 8.53.510.313 I slot print_timing: id 2 | task 4695 | graph reallocs = 0 / 0 (same size) / (changed size) 8.53.510.355 I slot release: id 2 | task 4695 | stop processing: n_tokens = 799, truncated = 0 8.53.510.368 I slot print_timing: id 0 | task 4699 | prompt processing, n_tokens = 893, progress = 0.86, t = 5.96 s / 149.76 tokens per second 8.53.513.322 I slot print_timing: id 1 | task 4701 | prompt processing, n_tokens = 679, progress = 0.85, t = 5.96 s / 113.87 tokens per second 8.53.515.563 I slot print_timing: id 3 | task 4700 | prompt processing, n_tokens = 679, progress = 0.84, t = 5.96 s / 113.91 tokens per second 8.54.189.260 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 799, t_last = 388974930836 8.54.189.322 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 329.710 MiB) 8.54.533.177 I slot launch_slot_: id 2 | task 4707 | processing task, is_child = 0 8.54.533.194 I slot print_timing: id 0 | task 4699 | prompt processing, n_tokens = 1038, progress = 1.00, t = 6.64 s / 156.28 tokens per second 8.54.536.768 I slot print_timing: id 1 | task 4701 | prompt processing, n_tokens = 795, progress = 0.99, t = 6.64 s / 119.69 tokens per second 8.54.538.801 I slot print_timing: id 3 | task 4700 | prompt processing, n_tokens = 805, progress = 1.00, t = 6.64 s / 121.24 tokens per second 8.55.489.687 I slot print_timing: id 0 | task 4699 | prompt eval time = 7461.26 ms / 1042 tokens ( 7.16 ms per token, 139.65 tokens per second) 8.55.489.690 I slot print_timing: id 0 | task 4699 | eval time = 481.16 ms / 2 tokens ( 481.16 ms per token, 2.08 tokens per second) 8.55.489.690 I slot print_timing: id 0 | task 4699 | total time = 7942.42 ms / 1044 tokens 8.55.489.691 I slot print_timing: id 0 | task 4699 | graphs reused = 3489 8.55.489.691 I slot print_timing: id 0 | task 4699 | graph reallocs = 0 / 0 (same size) / (changed size) 8.55.489.748 I slot release: id 0 | task 4699 | stop processing: n_tokens = 1043, truncated = 0 8.55.489.948 I slot print_timing: id 1 | task 4701 | prompt eval time = 7461.37 ms / 799 tokens ( 9.34 ms per token, 107.08 tokens per second) 8.55.489.950 I slot print_timing: id 1 | task 4701 | eval time = 481.25 ms / 2 tokens ( 481.25 ms per token, 2.08 tokens per second) 8.55.489.950 I slot print_timing: id 1 | task 4701 | total time = 7942.62 ms / 801 tokens 8.55.489.951 I slot print_timing: id 1 | task 4701 | graphs reused = 3489 8.55.489.951 I slot print_timing: id 1 | task 4701 | graph reallocs = 0 / 0 (same size) / (changed size) 8.55.489.982 I slot release: id 1 | task 4701 | stop processing: n_tokens = 800, truncated = 0 8.55.490.157 I slot print_timing: id 3 | task 4700 | prompt eval time = 7459.57 ms / 809 tokens ( 9.22 ms per token, 108.45 tokens per second) 8.55.490.159 I slot print_timing: id 3 | task 4700 | eval time = 481.29 ms / 2 tokens ( 481.29 ms per token, 2.08 tokens per second) 8.55.490.160 I slot print_timing: id 3 | task 4700 | total time = 7940.85 ms / 811 tokens 8.55.490.161 I slot print_timing: id 3 | task 4700 | graphs reused = 3489 8.55.490.161 I slot print_timing: id 3 | task 4700 | graph reallocs = 0 / 0 (same size) / (changed size) 8.55.490.183 I slot release: id 3 | task 4700 | stop processing: n_tokens = 810, truncated = 0 8.55.565.610 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1043, t_last = 388976910230 8.55.565.669 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 329.690 MiB) 8.56.285.942 I slot launch_slot_: id 0 | task 4712 | processing task, is_child = 0 8.56.285.998 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 332.721 MiB) 8.56.306.520 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 332.877 MiB) 8.56.324.205 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 800, t_last = 388976910464 8.56.324.320 I slot launch_slot_: id 1 | task 4713 | processing task, is_child = 0 8.56.324.362 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 810, t_last = 388976910664 8.56.324.434 I slot launch_slot_: id 3 | task 4714 | processing task, is_child = 0 8.59.170.972 I slot print_timing: id 2 | task 4707 | prompt eval time = 4052.89 ms / 845 tokens ( 4.80 ms per token, 208.49 tokens per second) 8.59.170.975 I slot print_timing: id 2 | task 4707 | eval time = 579.34 ms / 2 tokens ( 579.34 ms per token, 1.73 tokens per second) 8.59.170.976 I slot print_timing: id 2 | task 4707 | total time = 4632.22 ms / 847 tokens 8.59.170.976 I slot print_timing: id 2 | task 4707 | graphs reused = 3489 8.59.170.976 I slot print_timing: id 2 | task 4707 | graph reallocs = 0 / 0 (same size) / (changed size) 8.59.171.026 I slot release: id 2 | task 4707 | stop processing: n_tokens = 846, truncated = 0 9.00.680.753 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.871 (> 0.100 thold), f_keep = 0.888 9.00.680.830 I slot launch_slot_: id 2 | task 4719 | processing task, is_child = 0 9.00.680.837 I slot print_timing: id 0 | task 4712 | prompt processing, n_tokens = 723, progress = 0.86, t = 4.36 s / 165.97 tokens per second 9.01.311.287 I slot print_timing: id 1 | task 4713 | prompt processing, n_tokens = 723, progress = 0.80, t = 4.36 s / 165.97 tokens per second 9.01.316.728 I slot print_timing: id 3 | task 4714 | prompt processing, n_tokens = 723, progress = 0.79, t = 4.35 s / 166.04 tokens per second 9.02.582.463 I slot print_timing: id 0 | task 4712 | prompt processing, n_tokens = 835, progress = 1.00, t = 6.26 s / 133.43 tokens per second 9.02.797.073 I slot print_timing: id 1 | task 4713 | prompt processing, n_tokens = 897, progress = 1.00, t = 6.26 s / 143.34 tokens per second 9.02.801.157 I slot print_timing: id 3 | task 4714 | prompt processing, n_tokens = 906, progress = 1.00, t = 6.26 s / 144.82 tokens per second 9.02.973.647 I slot print_timing: id 0 | task 4712 | prompt eval time = 6597.70 ms / 839 tokens ( 7.86 ms per token, 127.17 tokens per second) 9.02.973.653 I slot print_timing: id 0 | task 4712 | eval time = 51.51 ms / 2 tokens ( 51.51 ms per token, 19.42 tokens per second) 9.02.973.654 I slot print_timing: id 0 | task 4712 | total time = 6649.20 ms / 841 tokens 9.02.973.654 I slot print_timing: id 0 | task 4712 | graphs reused = 3489 9.02.973.655 I slot print_timing: id 0 | task 4712 | graph reallocs = 0 / 0 (same size) / (changed size) 9.02.973.698 I slot release: id 0 | task 4712 | stop processing: n_tokens = 840, truncated = 0 9.02.973.852 I slot print_timing: id 1 | task 4713 | prompt eval time = 6597.81 ms / 901 tokens ( 7.32 ms per token, 136.56 tokens per second) 9.02.973.853 I slot print_timing: id 1 | task 4713 | eval time = 51.52 ms / 2 tokens ( 51.52 ms per token, 19.41 tokens per second) 9.02.973.854 I slot print_timing: id 1 | task 4713 | total time = 6649.33 ms / 903 tokens 9.02.973.854 I slot print_timing: id 1 | task 4713 | graphs reused = 3489 9.02.973.855 I slot print_timing: id 1 | task 4713 | graph reallocs = 0 / 0 (same size) / (changed size) 9.02.973.892 I slot release: id 1 | task 4713 | stop processing: n_tokens = 902, truncated = 0 9.02.974.054 I slot print_timing: id 2 | task 4719 | prompt eval time = 1609.06 ms / 139 tokens ( 11.58 ms per token, 86.39 tokens per second) 9.02.974.056 I slot print_timing: id 2 | task 4719 | eval time = 51.52 ms / 2 tokens ( 51.52 ms per token, 19.41 tokens per second) 9.02.974.056 I slot print_timing: id 2 | task 4719 | total time = 1660.57 ms / 141 tokens 9.02.974.056 I slot print_timing: id 2 | task 4719 | graphs reused = 3489 9.02.974.057 I slot print_timing: id 2 | task 4719 | graph reallocs = 0 / 0 (same size) / (changed size) 9.02.974.090 I slot release: id 2 | task 4719 | stop processing: n_tokens = 863, truncated = 0 9.02.974.245 I slot print_timing: id 3 | task 4714 | prompt eval time = 6596.52 ms / 910 tokens ( 7.25 ms per token, 137.95 tokens per second) 9.02.974.247 I slot print_timing: id 3 | task 4714 | eval time = 51.28 ms / 2 tokens ( 51.28 ms per token, 19.50 tokens per second) 9.02.974.247 I slot print_timing: id 3 | task 4714 | total time = 6647.80 ms / 912 tokens 9.02.974.247 I slot print_timing: id 3 | task 4714 | graphs reused = 3489 9.02.974.248 I slot print_timing: id 3 | task 4714 | graph reallocs = 0 / 0 (same size) / (changed size) 9.02.974.278 I slot release: id 3 | task 4714 | stop processing: n_tokens = 911, truncated = 0 9.02.982.474 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 840, t_last = 388984394179 9.02.982.524 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 332.271 MiB) 9.03.028.892 I slot launch_slot_: id 0 | task 4723 | processing task, is_child = 0 9.03.028.942 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.646 MiB) 9.03.076.427 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.665 MiB) 9.03.117.505 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.724 MiB) 9.03.166.381 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 902, t_last = 388984394373 9.03.166.486 I slot launch_slot_: id 1 | task 4724 | processing task, is_child = 0 9.03.166.571 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 863, t_last = 388984394571 9.03.166.637 I slot launch_slot_: id 2 | task 4725 | processing task, is_child = 0 9.03.166.684 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 911, t_last = 388984394759 9.03.166.752 I slot launch_slot_: id 3 | task 4726 | processing task, is_child = 0 9.07.125.395 I slot print_timing: id 0 | task 4723 | prompt processing, n_tokens = 309, progress = 0.37, t = 3.96 s / 78.06 tokens per second 9.07.289.886 I slot print_timing: id 1 | task 4724 | prompt processing, n_tokens = 583, progress = 0.85, t = 3.96 s / 147.28 tokens per second 9.07.293.570 I slot print_timing: id 2 | task 4725 | prompt processing, n_tokens = 632, progress = 0.82, t = 3.96 s / 159.66 tokens per second 9.07.295.469 I slot print_timing: id 3 | task 4726 | prompt processing, n_tokens = 335, progress = 0.39, t = 3.96 s / 84.63 tokens per second 9.08.889.908 I slot print_timing: id 0 | task 4723 | prompt processing, n_tokens = 708, progress = 0.86, t = 5.72 s / 123.71 tokens per second 9.09.409.346 I slot print_timing: id 1 | task 4724 | prompt processing, n_tokens = 684, progress = 0.99, t = 5.72 s / 119.52 tokens per second 9.09.411.482 I slot print_timing: id 2 | task 4725 | prompt processing, n_tokens = 765, progress = 0.99, t = 5.72 s / 133.67 tokens per second 9.09.413.440 I slot print_timing: id 3 | task 4726 | prompt processing, n_tokens = 708, progress = 0.83, t = 5.72 s / 123.71 tokens per second 9.10.227.673 I slot print_timing: id 0 | task 4723 | prompt processing, n_tokens = 821, progress = 1.00, t = 7.06 s / 116.28 tokens per second 9.10.231.285 I slot print_timing: id 3 | task 4726 | prompt processing, n_tokens = 847, progress = 1.00, t = 7.06 s / 119.97 tokens per second 9.10.351.329 I slot print_timing: id 1 | task 4724 | prompt eval time = 7060.59 ms / 688 tokens ( 10.26 ms per token, 97.44 tokens per second) 9.10.351.332 I slot print_timing: id 1 | task 4724 | eval time = 123.91 ms / 2 tokens ( 123.91 ms per token, 8.07 tokens per second) 9.10.351.333 I slot print_timing: id 1 | task 4724 | total time = 7184.50 ms / 690 tokens 9.10.351.334 I slot print_timing: id 1 | task 4724 | graphs reused = 3489 9.10.351.334 I slot print_timing: id 1 | task 4724 | graph reallocs = 0 / 0 (same size) / (changed size) 9.10.351.384 I slot release: id 1 | task 4724 | stop processing: n_tokens = 689, truncated = 0 9.10.351.541 I slot print_timing: id 2 | task 4725 | prompt eval time = 7060.77 ms / 769 tokens ( 9.18 ms per token, 108.91 tokens per second) 9.10.351.543 I slot print_timing: id 2 | task 4725 | eval time = 123.88 ms / 2 tokens ( 123.88 ms per token, 8.07 tokens per second) 9.10.351.544 I slot print_timing: id 2 | task 4725 | total time = 7184.65 ms / 771 tokens 9.10.351.544 I slot print_timing: id 2 | task 4725 | graphs reused = 3489 9.10.351.545 I slot print_timing: id 2 | task 4725 | graph reallocs = 0 / 0 (same size) / (changed size) 9.10.351.577 I slot release: id 2 | task 4725 | stop processing: n_tokens = 770, truncated = 0 9.10.395.082 I slot print_timing: id 0 | task 4723 | prompt eval time = 7184.43 ms / 825 tokens ( 8.71 ms per token, 114.83 tokens per second) 9.10.395.086 I slot print_timing: id 0 | task 4723 | eval time = 43.89 ms / 2 tokens ( 43.89 ms per token, 22.78 tokens per second) 9.10.395.087 I slot print_timing: id 0 | task 4723 | total time = 7228.32 ms / 827 tokens 9.10.395.087 I slot print_timing: id 0 | task 4723 | graphs reused = 3489 9.10.395.088 I slot print_timing: id 0 | task 4723 | graph reallocs = 0 / 0 (same size) / (changed size) 9.10.395.132 I slot release: id 0 | task 4723 | stop processing: n_tokens = 826, truncated = 0 9.10.395.297 I slot print_timing: id 3 | task 4726 | prompt eval time = 7184.80 ms / 851 tokens ( 8.44 ms per token, 118.44 tokens per second) 9.10.395.300 I slot print_timing: id 3 | task 4726 | eval time = 43.54 ms / 2 tokens ( 43.54 ms per token, 22.97 tokens per second) 9.10.395.301 I slot print_timing: id 3 | task 4726 | total time = 7228.34 ms / 853 tokens 9.10.395.301 I slot print_timing: id 3 | task 4726 | graphs reused = 3489 9.10.395.301 I slot print_timing: id 3 | task 4726 | graph reallocs = 0 / 0 (same size) / (changed size) 9.10.395.331 I slot release: id 3 | task 4726 | stop processing: n_tokens = 852, truncated = 0 9.10.395.337 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.878 (> 0.100 thold), f_keep = 0.857 9.10.395.381 I slot launch_slot_: id 2 | task 4734 | processing task, is_child = 0 9.10.395.445 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.489 MiB) 9.10.451.543 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 338.040 MiB) 9.10.492.695 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 339.311 MiB) 9.10.549.086 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 689, t_last = 388991771865 9.10.549.195 I slot launch_slot_: id 1 | task 4735 | processing task, is_child = 0 9.10.549.279 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 826, t_last = 388991815613 9.10.549.347 I slot launch_slot_: id 0 | task 4736 | processing task, is_child = 0 9.10.549.392 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 852, t_last = 388991815812 9.10.549.451 I slot launch_slot_: id 3 | task 4737 | processing task, is_child = 0 9.14.441.235 I slot print_timing: id 2 | task 4734 | prompt eval time = 1714.67 ms / 120 tokens ( 14.29 ms per token, 69.98 tokens per second) 9.14.441.237 I slot print_timing: id 2 | task 4734 | eval time = 2176.99 ms / 2 tokens ( 2176.99 ms per token, 0.46 tokens per second) 9.14.441.238 I slot print_timing: id 2 | task 4734 | total time = 3891.65 ms / 122 tokens 9.14.441.238 I slot print_timing: id 2 | task 4734 | graphs reused = 3489 9.14.441.239 I slot print_timing: id 2 | task 4734 | graph reallocs = 0 / 0 (same size) / (changed size) 9.14.441.282 I slot release: id 2 | task 4734 | stop processing: n_tokens = 753, truncated = 0 9.14.441.297 I slot print_timing: id 0 | task 4736 | prompt processing, n_tokens = 603, progress = 0.84, t = 3.89 s / 154.95 tokens per second 9.14.443.799 I slot print_timing: id 1 | task 4735 | prompt processing, n_tokens = 603, progress = 0.85, t = 3.89 s / 154.95 tokens per second 9.14.446.788 I slot print_timing: id 3 | task 4737 | prompt processing, n_tokens = 603, progress = 0.82, t = 3.89 s / 155.09 tokens per second 9.14.968.504 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 753, t_last = 388995861764 9.14.968.556 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 338.255 MiB) 9.15.334.372 I slot launch_slot_: id 2 | task 4742 | processing task, is_child = 0 9.15.334.383 I slot print_timing: id 0 | task 4736 | prompt processing, n_tokens = 715, progress = 0.99, t = 4.42 s / 161.80 tokens per second 9.15.336.346 I slot print_timing: id 1 | task 4735 | prompt processing, n_tokens = 709, progress = 0.99, t = 4.42 s / 160.44 tokens per second 9.15.338.357 I slot print_timing: id 3 | task 4737 | prompt processing, n_tokens = 732, progress = 0.99, t = 4.42 s / 165.77 tokens per second 9.16.106.262 I slot print_timing: id 0 | task 4736 | prompt eval time = 5210.82 ms / 719 tokens ( 7.25 ms per token, 137.98 tokens per second) 9.16.106.263 I slot print_timing: id 0 | task 4736 | eval time = 345.98 ms / 2 tokens ( 345.98 ms per token, 2.89 tokens per second) 9.16.106.264 I slot print_timing: id 0 | task 4736 | total time = 5556.80 ms / 721 tokens 9.16.106.264 I slot print_timing: id 0 | task 4736 | graphs reused = 3489 9.16.106.265 I slot print_timing: id 0 | task 4736 | graph reallocs = 0 / 0 (same size) / (changed size) 9.16.106.307 I slot release: id 0 | task 4736 | stop processing: n_tokens = 720, truncated = 0 9.16.106.518 I slot print_timing: id 1 | task 4735 | prompt eval time = 5210.93 ms / 713 tokens ( 7.31 ms per token, 136.83 tokens per second) 9.16.106.520 I slot print_timing: id 1 | task 4735 | eval time = 346.06 ms / 2 tokens ( 346.06 ms per token, 2.89 tokens per second) 9.16.106.521 I slot print_timing: id 1 | task 4735 | total time = 5556.99 ms / 715 tokens 9.16.106.521 I slot print_timing: id 1 | task 4735 | graphs reused = 3489 9.16.106.521 I slot print_timing: id 1 | task 4735 | graph reallocs = 0 / 0 (same size) / (changed size) 9.16.106.548 I slot release: id 1 | task 4735 | stop processing: n_tokens = 714, truncated = 0 9.16.106.713 I slot print_timing: id 3 | task 4737 | prompt eval time = 5207.89 ms / 736 tokens ( 7.08 ms per token, 141.32 tokens per second) 9.16.106.714 I slot print_timing: id 3 | task 4737 | eval time = 345.97 ms / 2 tokens ( 345.97 ms per token, 2.89 tokens per second) 9.16.106.715 I slot print_timing: id 3 | task 4737 | total time = 5553.86 ms / 738 tokens 9.16.106.715 I slot print_timing: id 3 | task 4737 | graphs reused = 3489 9.16.106.716 I slot print_timing: id 3 | task 4737 | graph reallocs = 0 / 0 (same size) / (changed size) 9.16.106.739 I slot release: id 3 | task 4737 | stop processing: n_tokens = 737, truncated = 0 9.16.856.503 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.890 (> 0.100 thold), f_keep = 0.876 9.16.856.560 I slot launch_slot_: id 0 | task 4747 | processing task, is_child = 0 9.16.856.605 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 367.703 MiB) 9.17.179.982 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 362.971 MiB) 9.17.223.537 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.883 (> 0.100 thold), f_keep = 0.884 9.17.223.604 I slot launch_slot_: id 1 | task 4748 | processing task, is_child = 0 9.17.223.649 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 9.17.223.675 I slot launch_slot_: id 3 | task 4749 | processing task, is_child = 0 9.18.281.229 I slot print_timing: id 2 | task 4742 | prompt eval time = 2795.02 ms / 710 tokens ( 3.94 ms per token, 254.02 tokens per second) 9.18.281.232 I slot print_timing: id 2 | task 4742 | eval time = 147.91 ms / 2 tokens ( 147.91 ms per token, 6.76 tokens per second) 9.18.281.232 I slot print_timing: id 2 | task 4742 | total time = 2942.93 ms / 712 tokens 9.18.281.233 I slot print_timing: id 2 | task 4742 | graphs reused = 3489 9.18.281.233 I slot print_timing: id 2 | task 4742 | graph reallocs = 0 / 0 (same size) / (changed size) 9.18.281.280 I slot release: id 2 | task 4742 | stop processing: n_tokens = 711, truncated = 0 9.18.337.391 I slot print_timing: id 0 | task 4747 | prompt eval time = 1057.18 ms / 106 tokens ( 9.97 ms per token, 100.27 tokens per second) 9.18.337.393 I slot print_timing: id 0 | task 4747 | eval time = 56.53 ms / 2 tokens ( 56.53 ms per token, 17.69 tokens per second) 9.18.337.394 I slot print_timing: id 0 | task 4747 | total time = 1113.70 ms / 108 tokens 9.18.337.394 I slot print_timing: id 0 | task 4747 | graphs reused = 3489 9.18.337.394 I slot print_timing: id 0 | task 4747 | graph reallocs = 0 / 0 (same size) / (changed size) 9.18.337.426 I slot release: id 0 | task 4747 | stop processing: n_tokens = 710, truncated = 0 9.18.337.577 I slot print_timing: id 1 | task 4748 | prompt eval time = 1054.14 ms / 112 tokens ( 9.41 ms per token, 106.25 tokens per second) 9.18.337.579 I slot print_timing: id 1 | task 4748 | eval time = 56.50 ms / 2 tokens ( 56.50 ms per token, 17.70 tokens per second) 9.18.337.579 I slot print_timing: id 1 | task 4748 | total time = 1110.64 ms / 114 tokens 9.18.337.579 I slot print_timing: id 1 | task 4748 | graphs reused = 3489 9.18.337.580 I slot print_timing: id 1 | task 4748 | graph reallocs = 0 / 0 (same size) / (changed size) 9.18.337.604 I slot release: id 1 | task 4748 | stop processing: n_tokens = 716, truncated = 0 9.18.337.784 I slot print_timing: id 3 | task 4749 | prompt eval time = 1049.34 ms / 104 tokens ( 10.09 ms per token, 99.11 tokens per second) 9.18.337.786 I slot print_timing: id 3 | task 4749 | eval time = 56.32 ms / 2 tokens ( 56.32 ms per token, 17.75 tokens per second) 9.18.337.786 I slot print_timing: id 3 | task 4749 | total time = 1105.67 ms / 106 tokens 9.18.337.787 I slot print_timing: id 3 | task 4749 | graphs reused = 3489 9.18.337.787 I slot print_timing: id 3 | task 4749 | graph reallocs = 0 / 0 (same size) / (changed size) 9.18.337.811 I slot release: id 3 | task 4749 | stop processing: n_tokens = 708, truncated = 0 9.18.337.818 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.893 9.18.337.865 I slot launch_slot_: id 0 | task 4753 | processing task, is_child = 0 9.18.337.912 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 366.002 MiB) 9.18.377.321 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 352.451 MiB) 9.18.423.889 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 354.133 MiB) 9.18.473.208 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.890 (> 0.100 thold), f_keep = 0.881 9.18.473.281 I slot launch_slot_: id 1 | task 4754 | processing task, is_child = 0 9.18.473.359 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 9.18.473.381 I slot launch_slot_: id 3 | task 4755 | processing task, is_child = 0 9.18.473.419 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.840 (> 0.100 thold), f_keep = 0.887 9.18.473.441 I slot launch_slot_: id 2 | task 4756 | processing task, is_child = 0 9.19.745.752 I slot print_timing: id 0 | task 4753 | prompt eval time = 1221.44 ms / 114 tokens ( 10.71 ms per token, 93.33 tokens per second) 9.19.745.757 I slot print_timing: id 0 | task 4753 | eval time = 50.85 ms / 2 tokens ( 50.85 ms per token, 19.66 tokens per second) 9.19.745.758 I slot print_timing: id 0 | task 4753 | total time = 1272.29 ms / 116 tokens 9.19.745.758 I slot print_timing: id 0 | task 4753 | graphs reused = 3489 9.19.745.758 I slot print_timing: id 0 | task 4753 | graph reallocs = 0 / 0 (same size) / (changed size) 9.19.745.794 I slot release: id 0 | task 4753 | stop processing: n_tokens = 718, truncated = 0 9.19.745.950 I slot print_timing: id 1 | task 4754 | prompt eval time = 1218.31 ms / 106 tokens ( 11.49 ms per token, 87.01 tokens per second) 9.19.745.954 I slot print_timing: id 1 | task 4754 | eval time = 50.89 ms / 2 tokens ( 50.89 ms per token, 19.65 tokens per second) 9.19.745.954 I slot print_timing: id 1 | task 4754 | total time = 1269.20 ms / 108 tokens 9.19.745.955 I slot print_timing: id 1 | task 4754 | graphs reused = 3489 9.19.745.955 I slot print_timing: id 1 | task 4754 | graph reallocs = 0 / 0 (same size) / (changed size) 9.19.745.980 I slot release: id 1 | task 4754 | stop processing: n_tokens = 710, truncated = 0 9.19.746.144 I slot print_timing: id 2 | task 4756 | prompt eval time = 1215.25 ms / 148 tokens ( 8.21 ms per token, 121.79 tokens per second) 9.19.746.145 I slot print_timing: id 2 | task 4756 | eval time = 50.88 ms / 2 tokens ( 50.88 ms per token, 19.65 tokens per second) 9.19.746.146 I slot print_timing: id 2 | task 4756 | total time = 1266.14 ms / 150 tokens 9.19.746.146 I slot print_timing: id 2 | task 4756 | graphs reused = 3489 9.19.746.146 I slot print_timing: id 2 | task 4756 | graph reallocs = 0 / 0 (same size) / (changed size) 9.19.746.172 I slot release: id 2 | task 4756 | stop processing: n_tokens = 752, truncated = 0 9.19.746.337 I slot print_timing: id 3 | task 4755 | prompt eval time = 1212.19 ms / 113 tokens ( 10.73 ms per token, 93.22 tokens per second) 9.19.746.338 I slot print_timing: id 3 | task 4755 | eval time = 50.88 ms / 2 tokens ( 50.88 ms per token, 19.65 tokens per second) 9.19.746.339 I slot print_timing: id 3 | task 4755 | total time = 1263.07 ms / 115 tokens 9.19.746.339 I slot print_timing: id 3 | task 4755 | graphs reused = 3489 9.19.746.339 I slot print_timing: id 3 | task 4755 | graph reallocs = 0 / 0 (same size) / (changed size) 9.19.746.355 I slot release: id 3 | task 4755 | stop processing: n_tokens = 717, truncated = 0 9.19.754.448 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 718, t_last = 389001166275 9.19.754.498 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 350.085 MiB) 9.19.781.315 I slot launch_slot_: id 0 | task 4760 | processing task, is_child = 0 9.19.781.363 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 350.300 MiB) 9.19.790.990 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 348.912 MiB) 9.19.800.739 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.712 MiB) 9.19.810.953 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 710, t_last = 389001166461 9.19.811.041 I slot launch_slot_: id 1 | task 4761 | processing task, is_child = 0 9.19.811.117 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 752, t_last = 389001166653 9.19.811.178 I slot launch_slot_: id 2 | task 4762 | processing task, is_child = 0 9.19.811.220 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 717, t_last = 389001166836 9.19.811.277 I slot launch_slot_: id 3 | task 4763 | processing task, is_child = 0 9.23.492.338 I slot print_timing: id 0 | task 4760 | prompt processing, n_tokens = 364, progress = 0.41, t = 3.68 s / 98.88 tokens per second 9.23.554.848 I slot print_timing: id 1 | task 4761 | prompt processing, n_tokens = 380, progress = 0.42, t = 3.68 s / 103.23 tokens per second 9.23.558.884 I slot print_timing: id 2 | task 4762 | prompt processing, n_tokens = 566, progress = 0.52, t = 3.68 s / 153.77 tokens per second 9.23.560.858 I slot print_timing: id 3 | task 4763 | prompt processing, n_tokens = 575, progress = 0.53, t = 3.68 s / 156.21 tokens per second 9.26.350.659 I slot print_timing: id 0 | task 4760 | prompt processing, n_tokens = 762, progress = 0.87, t = 6.54 s / 116.53 tokens per second 9.26.443.416 I slot print_timing: id 1 | task 4761 | prompt processing, n_tokens = 762, progress = 0.85, t = 6.54 s / 116.53 tokens per second 9.26.445.835 I slot print_timing: id 2 | task 4762 | prompt processing, n_tokens = 905, progress = 0.84, t = 6.54 s / 138.39 tokens per second 9.26.447.716 I slot print_timing: id 3 | task 4763 | prompt processing, n_tokens = 905, progress = 0.83, t = 6.54 s / 138.40 tokens per second 9.27.788.433 I slot print_timing: id 0 | task 4760 | prompt processing, n_tokens = 876, progress = 1.00, t = 7.98 s / 109.81 tokens per second 9.27.851.412 I slot print_timing: id 1 | task 4761 | prompt processing, n_tokens = 892, progress = 1.00, t = 7.98 s / 111.82 tokens per second 9.27.853.651 I slot print_timing: id 2 | task 4762 | prompt processing, n_tokens = 1078, progress = 1.00, t = 7.98 s / 135.14 tokens per second 9.27.855.892 I slot print_timing: id 3 | task 4763 | prompt processing, n_tokens = 1087, progress = 1.00, t = 7.98 s / 136.27 tokens per second 9.28.018.823 I slot print_timing: id 0 | task 4760 | prompt eval time = 8156.11 ms / 880 tokens ( 9.27 ms per token, 107.89 tokens per second) 9.28.018.829 I slot print_timing: id 0 | task 4760 | eval time = 51.42 ms / 2 tokens ( 51.42 ms per token, 19.45 tokens per second) 9.28.018.829 I slot print_timing: id 0 | task 4760 | total time = 8207.54 ms / 882 tokens 9.28.018.830 I slot print_timing: id 0 | task 4760 | graphs reused = 3489 9.28.018.830 I slot print_timing: id 0 | task 4760 | graph reallocs = 0 / 0 (same size) / (changed size) 9.28.018.884 I slot release: id 0 | task 4760 | stop processing: n_tokens = 881, truncated = 0 9.28.019.029 I slot print_timing: id 1 | task 4761 | prompt eval time = 8156.27 ms / 896 tokens ( 9.10 ms per token, 109.85 tokens per second) 9.28.019.035 I slot print_timing: id 1 | task 4761 | eval time = 51.42 ms / 2 tokens ( 51.42 ms per token, 19.45 tokens per second) 9.28.019.035 I slot print_timing: id 1 | task 4761 | total time = 8207.69 ms / 898 tokens 9.28.019.035 I slot print_timing: id 1 | task 4761 | graphs reused = 3489 9.28.019.036 I slot print_timing: id 1 | task 4761 | graph reallocs = 0 / 0 (same size) / (changed size) 9.28.019.061 I slot release: id 1 | task 4761 | stop processing: n_tokens = 897, truncated = 0 9.28.019.236 I slot print_timing: id 2 | task 4762 | prompt eval time = 8156.41 ms / 1082 tokens ( 7.54 ms per token, 132.66 tokens per second) 9.28.019.241 I slot print_timing: id 2 | task 4762 | eval time = 51.43 ms / 2 tokens ( 51.43 ms per token, 19.44 tokens per second) 9.28.019.242 I slot print_timing: id 2 | task 4762 | total time = 8207.85 ms / 1084 tokens 9.28.019.242 I slot print_timing: id 2 | task 4762 | graphs reused = 3489 9.28.019.242 I slot print_timing: id 2 | task 4762 | graph reallocs = 0 / 0 (same size) / (changed size) 9.28.019.284 I slot release: id 2 | task 4762 | stop processing: n_tokens = 1083, truncated = 0 9.28.019.460 I slot print_timing: id 3 | task 4763 | prompt eval time = 8156.60 ms / 1091 tokens ( 7.48 ms per token, 133.76 tokens per second) 9.28.019.461 I slot print_timing: id 3 | task 4763 | eval time = 51.43 ms / 2 tokens ( 51.43 ms per token, 19.44 tokens per second) 9.28.019.461 I slot print_timing: id 3 | task 4763 | total time = 8208.02 ms / 1093 tokens 9.28.019.462 I slot print_timing: id 3 | task 4763 | graphs reused = 3489 9.28.019.462 I slot print_timing: id 3 | task 4763 | graph reallocs = 0 / 0 (same size) / (changed size) 9.28.019.483 I slot release: id 3 | task 4763 | stop processing: n_tokens = 1092, truncated = 0 9.28.028.392 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.895 9.28.028.425 I slot launch_slot_: id 3 | task 4771 | processing task, is_child = 0 9.28.028.475 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.967 MiB) 9.28.038.381 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.536 MiB) 9.28.048.518 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.263 MiB) 9.28.065.259 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.901 9.28.065.316 I slot launch_slot_: id 2 | task 4772 | processing task, is_child = 0 9.28.065.407 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 881, t_last = 389009439365 9.28.067.477 I slot launch_slot_: id 0 | task 4773 | processing task, is_child = 0 9.28.067.526 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 897, t_last = 389009439542 9.28.067.585 I slot launch_slot_: id 1 | task 4774 | processing task, is_child = 0 9.30.694.097 I slot print_timing: id 0 | task 4773 | prompt eval time = 2089.79 ms / 180 tokens ( 11.61 ms per token, 86.13 tokens per second) 9.30.694.100 I slot print_timing: id 0 | task 4773 | eval time = 536.71 ms / 2 tokens ( 536.71 ms per token, 1.86 tokens per second) 9.30.694.101 I slot print_timing: id 0 | task 4773 | total time = 2626.50 ms / 182 tokens 9.30.694.101 I slot print_timing: id 0 | task 4773 | graphs reused = 3489 9.30.694.102 I slot print_timing: id 0 | task 4773 | graph reallocs = 0 / 0 (same size) / (changed size) 9.30.694.146 I slot release: id 0 | task 4773 | stop processing: n_tokens = 1086, truncated = 0 9.30.694.324 I slot print_timing: id 2 | task 4772 | prompt eval time = 2086.76 ms / 174 tokens ( 11.99 ms per token, 83.38 tokens per second) 9.30.694.329 I slot print_timing: id 2 | task 4772 | eval time = 536.69 ms / 2 tokens ( 536.69 ms per token, 1.86 tokens per second) 9.30.694.330 I slot print_timing: id 2 | task 4772 | total time = 2623.44 ms / 176 tokens 9.30.694.330 I slot print_timing: id 2 | task 4772 | graphs reused = 3489 9.30.694.330 I slot print_timing: id 2 | task 4772 | graph reallocs = 0 / 0 (same size) / (changed size) 9.30.694.362 I slot release: id 2 | task 4772 | stop processing: n_tokens = 1080, truncated = 0 9.30.694.600 I slot print_timing: id 3 | task 4771 | prompt eval time = 2083.81 ms / 166 tokens ( 12.55 ms per token, 79.66 tokens per second) 9.30.694.602 I slot print_timing: id 3 | task 4771 | eval time = 536.72 ms / 2 tokens ( 536.72 ms per token, 1.86 tokens per second) 9.30.694.602 I slot print_timing: id 3 | task 4771 | total time = 2620.53 ms / 168 tokens 9.30.694.602 I slot print_timing: id 3 | task 4771 | graphs reused = 3489 9.30.694.603 I slot print_timing: id 3 | task 4771 | graph reallocs = 0 / 0 (same size) / (changed size) 9.30.694.623 I slot release: id 3 | task 4771 | stop processing: n_tokens = 1072, truncated = 0 9.31.361.318 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.898 (> 0.100 thold), f_keep = 0.900 9.31.361.370 I slot launch_slot_: id 0 | task 4780 | processing task, is_child = 0 9.31.796.323 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 329.690 MiB) 9.31.807.427 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.911 (> 0.100 thold), f_keep = 0.905 9.31.807.496 I slot launch_slot_: id 2 | task 4781 | processing task, is_child = 0 9.31.807.555 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.911 9.31.807.579 I slot launch_slot_: id 3 | task 4782 | processing task, is_child = 0 9.31.810.838 I slot print_timing: id 1 | task 4774 | prompt processing, n_tokens = 1076, progress = 1.00, t = 3.29 s / 327.00 tokens per second 9.33.199.138 I slot print_timing: id 1 | task 4774 | prompt eval time = 4985.99 ms / 1080 tokens ( 4.62 ms per token, 216.61 tokens per second) 9.33.199.141 I slot print_timing: id 1 | task 4774 | eval time = 142.32 ms / 2 tokens ( 142.32 ms per token, 7.03 tokens per second) 9.33.199.142 I slot print_timing: id 1 | task 4774 | total time = 5128.31 ms / 1082 tokens 9.33.199.142 I slot print_timing: id 1 | task 4774 | graphs reused = 3489 9.33.199.143 I slot print_timing: id 1 | task 4774 | graph reallocs = 0 / 0 (same size) / (changed size) 9.33.199.189 I slot release: id 1 | task 4774 | stop processing: n_tokens = 1081, truncated = 0 9.33.255.839 I slot print_timing: id 0 | task 4780 | prompt eval time = 1391.35 ms / 183 tokens ( 7.60 ms per token, 131.53 tokens per second) 9.33.255.843 I slot print_timing: id 0 | task 4780 | eval time = 56.90 ms / 2 tokens ( 56.90 ms per token, 17.57 tokens per second) 9.33.255.844 I slot print_timing: id 0 | task 4780 | total time = 1448.25 ms / 185 tokens 9.33.255.844 I slot print_timing: id 0 | task 4780 | graphs reused = 3489 9.33.255.845 I slot print_timing: id 0 | task 4780 | graph reallocs = 0 / 0 (same size) / (changed size) 9.33.255.885 I slot release: id 0 | task 4780 | stop processing: n_tokens = 1089, truncated = 0 9.33.256.102 I slot print_timing: id 2 | task 4781 | prompt eval time = 1386.57 ms / 168 tokens ( 8.25 ms per token, 121.16 tokens per second) 9.33.256.104 I slot print_timing: id 2 | task 4781 | eval time = 56.73 ms / 2 tokens ( 56.73 ms per token, 17.63 tokens per second) 9.33.256.105 I slot print_timing: id 2 | task 4781 | total time = 1443.30 ms / 170 tokens 9.33.256.105 I slot print_timing: id 2 | task 4781 | graphs reused = 3489 9.33.256.105 I slot print_timing: id 2 | task 4781 | graph reallocs = 0 / 0 (same size) / (changed size) 9.33.256.142 I slot release: id 2 | task 4781 | stop processing: n_tokens = 1074, truncated = 0 9.33.256.358 I slot print_timing: id 3 | task 4782 | prompt eval time = 1383.58 ms / 177 tokens ( 7.82 ms per token, 127.93 tokens per second) 9.33.256.362 I slot print_timing: id 3 | task 4782 | eval time = 56.74 ms / 2 tokens ( 56.74 ms per token, 17.62 tokens per second) 9.33.256.362 I slot print_timing: id 3 | task 4782 | total time = 1440.32 ms / 179 tokens 9.33.256.362 I slot print_timing: id 3 | task 4782 | graphs reused = 3489 9.33.256.363 I slot print_timing: id 3 | task 4782 | graph reallocs = 0 / 0 (same size) / (changed size) 9.33.256.389 I slot release: id 3 | task 4782 | stop processing: n_tokens = 1083, truncated = 0 9.33.256.395 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.902 (> 0.100 thold), f_keep = 0.897 9.33.256.438 I slot launch_slot_: id 0 | task 4786 | processing task, is_child = 0 9.33.256.501 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 334.461 MiB) 9.33.270.400 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 329.710 MiB) 9.33.284.049 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 329.905 MiB) 9.33.297.072 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.904 9.33.297.143 I slot launch_slot_: id 1 | task 4787 | processing task, is_child = 0 9.33.297.251 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.909 (> 0.100 thold), f_keep = 0.910 9.33.297.275 I slot launch_slot_: id 2 | task 4788 | processing task, is_child = 0 9.33.297.331 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.902 9.33.297.351 I slot launch_slot_: id 3 | task 4789 | processing task, is_child = 0 9.34.857.114 I slot print_timing: id 0 | task 4786 | prompt eval time = 1508.52 ms / 178 tokens ( 8.47 ms per token, 118.00 tokens per second) 9.34.857.116 I slot print_timing: id 0 | task 4786 | eval time = 51.23 ms / 2 tokens ( 51.23 ms per token, 19.52 tokens per second) 9.34.857.116 I slot print_timing: id 0 | task 4786 | total time = 1559.75 ms / 180 tokens 9.34.857.117 I slot print_timing: id 0 | task 4786 | graphs reused = 3489 9.34.857.117 I slot print_timing: id 0 | task 4786 | graph reallocs = 0 / 0 (same size) / (changed size) 9.34.857.156 I slot release: id 0 | task 4786 | stop processing: n_tokens = 1084, truncated = 0 9.34.857.306 I slot print_timing: id 1 | task 4787 | prompt eval time = 1505.47 ms / 171 tokens ( 8.80 ms per token, 113.59 tokens per second) 9.34.857.309 I slot print_timing: id 1 | task 4787 | eval time = 51.23 ms / 2 tokens ( 51.23 ms per token, 19.52 tokens per second) 9.34.857.309 I slot print_timing: id 1 | task 4787 | total time = 1556.70 ms / 173 tokens 9.34.857.310 I slot print_timing: id 1 | task 4787 | graphs reused = 3489 9.34.857.310 I slot print_timing: id 1 | task 4787 | graph reallocs = 0 / 0 (same size) / (changed size) 9.34.857.341 I slot release: id 1 | task 4787 | stop processing: n_tokens = 1077, truncated = 0 9.34.857.514 I slot print_timing: id 2 | task 4788 | prompt eval time = 1502.47 ms / 170 tokens ( 8.84 ms per token, 113.15 tokens per second) 9.34.857.515 I slot print_timing: id 2 | task 4788 | eval time = 51.23 ms / 2 tokens ( 51.23 ms per token, 19.52 tokens per second) 9.34.857.516 I slot print_timing: id 2 | task 4788 | total time = 1553.71 ms / 172 tokens 9.34.857.516 I slot print_timing: id 2 | task 4788 | graphs reused = 3489 9.34.857.516 I slot print_timing: id 2 | task 4788 | graph reallocs = 0 / 0 (same size) / (changed size) 9.34.857.548 I slot release: id 2 | task 4788 | stop processing: n_tokens = 1076, truncated = 0 9.34.857.716 I slot print_timing: id 3 | task 4789 | prompt eval time = 1499.45 ms / 175 tokens ( 8.57 ms per token, 116.71 tokens per second) 9.34.857.718 I slot print_timing: id 3 | task 4789 | eval time = 51.23 ms / 2 tokens ( 51.23 ms per token, 19.52 tokens per second) 9.34.857.718 I slot print_timing: id 3 | task 4789 | total time = 1550.68 ms / 177 tokens 9.34.857.719 I slot print_timing: id 3 | task 4789 | graphs reused = 3489 9.34.857.719 I slot print_timing: id 3 | task 4789 | graph reallocs = 0 / 0 (same size) / (changed size) 9.34.857.739 I slot release: id 3 | task 4789 | stop processing: n_tokens = 1081, truncated = 0 9.34.865.762 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1084, t_last = 389016277637 9.34.865.825 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 330.492 MiB) 9.34.880.593 I slot launch_slot_: id 0 | task 4793 | processing task, is_child = 0 9.34.880.650 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.704 MiB) 9.34.895.675 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 330.942 MiB) 9.34.910.290 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.880 MiB) 9.34.927.980 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.907 9.34.928.033 I slot launch_slot_: id 1 | task 4794 | processing task, is_child = 0 9.34.928.134 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.908 9.34.928.156 I slot launch_slot_: id 2 | task 4795 | processing task, is_child = 0 9.34.928.210 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1081, t_last = 389016278220 9.34.928.288 I slot launch_slot_: id 3 | task 4796 | processing task, is_child = 0 9.38.328.875 I slot print_timing: id 1 | task 4794 | prompt eval time = 2696.38 ms / 173 tokens ( 15.59 ms per token, 64.16 tokens per second) 9.38.328.877 I slot print_timing: id 1 | task 4794 | eval time = 704.12 ms / 2 tokens ( 704.12 ms per token, 1.42 tokens per second) 9.38.328.879 I slot print_timing: id 1 | task 4794 | total time = 3400.49 ms / 175 tokens 9.38.328.879 I slot print_timing: id 1 | task 4794 | graphs reused = 3489 9.38.328.879 I slot print_timing: id 1 | task 4794 | graph reallocs = 0 / 0 (same size) / (changed size) 9.38.328.923 I slot release: id 1 | task 4794 | stop processing: n_tokens = 1079, truncated = 0 9.38.329.107 I slot print_timing: id 2 | task 4795 | prompt eval time = 2693.37 ms / 174 tokens ( 15.48 ms per token, 64.60 tokens per second) 9.38.329.109 I slot print_timing: id 2 | task 4795 | eval time = 704.14 ms / 2 tokens ( 704.14 ms per token, 1.42 tokens per second) 9.38.329.109 I slot print_timing: id 2 | task 4795 | total time = 3397.51 ms / 176 tokens 9.38.329.110 I slot print_timing: id 2 | task 4795 | graphs reused = 3489 9.38.329.110 I slot print_timing: id 2 | task 4795 | graph reallocs = 0 / 0 (same size) / (changed size) 9.38.329.145 I slot release: id 2 | task 4795 | stop processing: n_tokens = 1080, truncated = 0 9.38.329.152 I slot print_timing: id 0 | task 4793 | prompt processing, n_tokens = 515, progress = 0.50, t = 3.40 s / 151.45 tokens per second 9.38.332.976 I slot print_timing: id 3 | task 4796 | prompt processing, n_tokens = 501, progress = 0.49, t = 3.39 s / 147.62 tokens per second 9.39.026.673 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1079, t_last = 389019749404 9.39.026.751 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 330.218 MiB) 9.39.724.066 I slot launch_slot_: id 1 | task 4801 | processing task, is_child = 0 9.39.724.142 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 327.539 MiB) 9.39.737.481 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1080, t_last = 389019749626 9.39.737.586 I slot launch_slot_: id 2 | task 4802 | processing task, is_child = 0 9.39.737.594 I slot print_timing: id 0 | task 4793 | prompt processing, n_tokens = 878, progress = 0.85, t = 4.10 s / 214.23 tokens per second 9.39.739.617 I slot print_timing: id 3 | task 4796 | prompt processing, n_tokens = 878, progress = 0.86, t = 4.09 s / 214.57 tokens per second 9.40.993.370 I slot print_timing: id 0 | task 4793 | prompt processing, n_tokens = 1027, progress = 1.00, t = 6.07 s / 169.33 tokens per second 9.41.298.862 I slot print_timing: id 3 | task 4796 | prompt processing, n_tokens = 1013, progress = 1.00, t = 6.06 s / 167.20 tokens per second 9.42.926.232 I slot print_timing: id 0 | task 4793 | prompt eval time = 7135.91 ms / 1031 tokens ( 6.92 ms per token, 144.48 tokens per second) 9.42.926.238 I slot print_timing: id 0 | task 4793 | eval time = 862.01 ms / 2 tokens ( 862.01 ms per token, 1.16 tokens per second) 9.42.926.239 I slot print_timing: id 0 | task 4793 | total time = 7997.93 ms / 1033 tokens 9.42.926.239 I slot print_timing: id 0 | task 4793 | graphs reused = 3489 9.42.926.240 I slot print_timing: id 0 | task 4793 | graph reallocs = 0 / 0 (same size) / (changed size) 9.42.926.285 I slot release: id 0 | task 4793 | stop processing: n_tokens = 1032, truncated = 0 9.42.926.528 I slot print_timing: id 3 | task 4796 | prompt eval time = 7129.60 ms / 1017 tokens ( 7.01 ms per token, 142.64 tokens per second) 9.42.926.531 I slot print_timing: id 3 | task 4796 | eval time = 862.10 ms / 2 tokens ( 862.10 ms per token, 1.16 tokens per second) 9.42.926.531 I slot print_timing: id 3 | task 4796 | total time = 7991.70 ms / 1019 tokens 9.42.926.531 I slot print_timing: id 3 | task 4796 | graphs reused = 3489 9.42.926.532 I slot print_timing: id 3 | task 4796 | graph reallocs = 0 / 0 (same size) / (changed size) 9.42.926.559 I slot release: id 3 | task 4796 | stop processing: n_tokens = 1018, truncated = 0 9.42.926.567 I slot print_timing: id 1 | task 4801 | prompt processing, n_tokens = 590, progress = 0.53, t = 3.19 s / 185.15 tokens per second 9.42.930.262 I slot print_timing: id 2 | task 4802 | prompt processing, n_tokens = 555, progress = 0.52, t = 3.19 s / 174.17 tokens per second 9.44.043.848 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.867 (> 0.100 thold), f_keep = 0.878 9.44.043.921 I slot launch_slot_: id 0 | task 4807 | processing task, is_child = 0 9.44.043.982 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 330.726 MiB) 9.44.237.971 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 9.44.238.063 I slot launch_slot_: id 3 | task 4808 | processing task, is_child = 0 9.44.242.490 I slot print_timing: id 1 | task 4801 | prompt processing, n_tokens = 878, progress = 0.79, t = 4.30 s / 203.98 tokens per second 9.44.244.372 I slot print_timing: id 2 | task 4802 | prompt processing, n_tokens = 878, progress = 0.82, t = 4.30 s / 203.98 tokens per second 9.46.104.537 I slot print_timing: id 1 | task 4801 | prompt processing, n_tokens = 1102, progress = 1.00, t = 6.18 s / 178.40 tokens per second 9.46.107.986 I slot print_timing: id 2 | task 4802 | prompt processing, n_tokens = 1067, progress = 1.00, t = 6.18 s / 172.74 tokens per second 9.46.272.540 I slot print_timing: id 0 | task 4807 | prompt eval time = 1983.37 ms / 167 tokens ( 11.88 ms per token, 84.20 tokens per second) 9.46.272.542 I slot print_timing: id 0 | task 4807 | eval time = 51.09 ms / 2 tokens ( 51.09 ms per token, 19.57 tokens per second) 9.46.272.543 I slot print_timing: id 0 | task 4807 | total time = 2034.46 ms / 169 tokens 9.46.272.543 I slot print_timing: id 0 | task 4807 | graphs reused = 3489 9.46.272.544 I slot print_timing: id 0 | task 4807 | graph reallocs = 0 / 0 (same size) / (changed size) 9.46.272.593 I slot release: id 0 | task 4807 | stop processing: n_tokens = 1046, truncated = 0 9.46.272.743 I slot print_timing: id 1 | task 4801 | prompt eval time = 6482.13 ms / 1106 tokens ( 5.86 ms per token, 170.62 tokens per second) 9.46.272.744 I slot print_timing: id 1 | task 4801 | eval time = 51.14 ms / 2 tokens ( 51.14 ms per token, 19.55 tokens per second) 9.46.272.744 I slot print_timing: id 1 | task 4801 | total time = 6533.27 ms / 1108 tokens 9.46.272.745 I slot print_timing: id 1 | task 4801 | graphs reused = 3489 9.46.272.745 I slot print_timing: id 1 | task 4801 | graph reallocs = 0 / 0 (same size) / (changed size) 9.46.272.779 I slot release: id 1 | task 4801 | stop processing: n_tokens = 1107, truncated = 0 9.46.272.930 I slot print_timing: id 2 | task 4802 | prompt eval time = 6482.22 ms / 1071 tokens ( 6.05 ms per token, 165.22 tokens per second) 9.46.272.931 I slot print_timing: id 2 | task 4802 | eval time = 51.16 ms / 2 tokens ( 51.16 ms per token, 19.55 tokens per second) 9.46.272.931 I slot print_timing: id 2 | task 4802 | total time = 6533.38 ms / 1073 tokens 9.46.272.932 I slot print_timing: id 2 | task 4802 | graphs reused = 3489 9.46.272.932 I slot print_timing: id 2 | task 4802 | graph reallocs = 0 / 0 (same size) / (changed size) 9.46.272.960 I slot release: id 2 | task 4802 | stop processing: n_tokens = 1072, truncated = 0 9.46.273.134 I slot print_timing: id 3 | task 4808 | prompt eval time = 1975.69 ms / 152 tokens ( 13.00 ms per token, 76.93 tokens per second) 9.46.273.135 I slot print_timing: id 3 | task 4808 | eval time = 51.19 ms / 2 tokens ( 51.19 ms per token, 19.54 tokens per second) 9.46.273.135 I slot print_timing: id 3 | task 4808 | total time = 2026.88 ms / 154 tokens 9.46.273.135 I slot print_timing: id 3 | task 4808 | graphs reused = 3489 9.46.273.136 I slot print_timing: id 3 | task 4808 | graph reallocs = 0 / 0 (same size) / (changed size) 9.46.273.185 I slot release: id 3 | task 4808 | stop processing: n_tokens = 1031, truncated = 0 9.46.285.396 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1046, t_last = 389027693075 9.46.285.449 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.791 MiB) 9.46.295.785 I slot launch_slot_: id 0 | task 4812 | processing task, is_child = 0 9.46.295.843 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.028 MiB) 9.46.306.992 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.478 MiB) 9.46.317.947 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.067 MiB) 9.46.328.153 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1107, t_last = 389027693260 9.46.328.259 I slot launch_slot_: id 1 | task 4813 | processing task, is_child = 0 9.46.328.368 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1072, t_last = 389027693441 9.46.328.435 I slot launch_slot_: id 2 | task 4814 | processing task, is_child = 0 9.46.328.485 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1031, t_last = 389027693666 9.46.328.554 I slot launch_slot_: id 3 | task 4815 | processing task, is_child = 0 9.50.591.870 I slot print_timing: id 0 | task 4812 | prompt processing, n_tokens = 623, progress = 0.85, t = 4.26 s / 146.13 tokens per second 9.50.663.082 I slot print_timing: id 1 | task 4813 | prompt processing, n_tokens = 623, progress = 0.84, t = 4.26 s / 146.13 tokens per second 9.50.665.908 I slot print_timing: id 2 | task 4814 | prompt processing, n_tokens = 623, progress = 0.83, t = 4.26 s / 146.14 tokens per second 9.50.667.774 I slot print_timing: id 3 | task 4815 | prompt processing, n_tokens = 281, progress = 0.35, t = 4.26 s / 65.91 tokens per second 9.51.762.380 I slot print_timing: id 0 | task 4812 | prompt processing, n_tokens = 725, progress = 0.99, t = 5.43 s / 133.42 tokens per second 9.52.229.998 I slot print_timing: id 1 | task 4813 | prompt processing, n_tokens = 736, progress = 0.99, t = 5.43 s / 135.45 tokens per second 9.52.233.362 I slot print_timing: id 2 | task 4814 | prompt processing, n_tokens = 749, progress = 0.99, t = 5.43 s / 137.84 tokens per second 9.52.235.605 I slot print_timing: id 3 | task 4815 | prompt processing, n_tokens = 623, progress = 0.78, t = 5.43 s / 114.66 tokens per second 9.52.758.214 I slot print_timing: id 3 | task 4815 | prompt processing, n_tokens = 793, progress = 0.99, t = 6.43 s / 123.35 tokens per second 9.52.847.062 I slot print_timing: id 0 | task 4812 | prompt eval time = 6429.13 ms / 729 tokens ( 8.82 ms per token, 113.39 tokens per second) 9.52.847.065 I slot print_timing: id 0 | task 4812 | eval time = 89.37 ms / 2 tokens ( 89.37 ms per token, 11.19 tokens per second) 9.52.847.065 I slot print_timing: id 0 | task 4812 | total time = 6518.50 ms / 731 tokens 9.52.847.066 I slot print_timing: id 0 | task 4812 | graphs reused = 3489 9.52.847.066 I slot print_timing: id 0 | task 4812 | graph reallocs = 0 / 0 (same size) / (changed size) 9.52.847.104 I slot release: id 0 | task 4812 | stop processing: n_tokens = 730, truncated = 0 9.52.847.267 I slot print_timing: id 1 | task 4813 | prompt eval time = 6429.32 ms / 740 tokens ( 8.69 ms per token, 115.10 tokens per second) 9.52.847.269 I slot print_timing: id 1 | task 4813 | eval time = 89.31 ms / 2 tokens ( 89.31 ms per token, 11.20 tokens per second) 9.52.847.270 I slot print_timing: id 1 | task 4813 | total time = 6518.63 ms / 742 tokens 9.52.847.270 I slot print_timing: id 1 | task 4813 | graphs reused = 3489 9.52.847.270 I slot print_timing: id 1 | task 4813 | graph reallocs = 0 / 0 (same size) / (changed size) 9.52.847.291 I slot release: id 1 | task 4813 | stop processing: n_tokens = 741, truncated = 0 9.52.847.446 I slot print_timing: id 2 | task 4814 | prompt eval time = 6429.49 ms / 753 tokens ( 8.54 ms per token, 117.12 tokens per second) 9.52.847.449 I slot print_timing: id 2 | task 4814 | eval time = 89.24 ms / 2 tokens ( 89.24 ms per token, 11.21 tokens per second) 9.52.847.449 I slot print_timing: id 2 | task 4814 | total time = 6518.73 ms / 755 tokens 9.52.847.449 I slot print_timing: id 2 | task 4814 | graphs reused = 3489 9.52.847.450 I slot print_timing: id 2 | task 4814 | graph reallocs = 0 / 0 (same size) / (changed size) 9.52.847.469 I slot release: id 2 | task 4814 | stop processing: n_tokens = 754, truncated = 0 9.52.870.428 I slot print_timing: id 3 | task 4815 | prompt eval time = 6518.92 ms / 797 tokens ( 8.18 ms per token, 122.26 tokens per second) 9.52.870.430 I slot print_timing: id 3 | task 4815 | eval time = 22.72 ms / 2 tokens ( 22.72 ms per token, 44.02 tokens per second) 9.52.870.431 I slot print_timing: id 3 | task 4815 | total time = 6541.64 ms / 799 tokens 9.52.870.431 I slot print_timing: id 3 | task 4815 | graphs reused = 3489 9.52.870.431 I slot print_timing: id 3 | task 4815 | graph reallocs = 0 / 0 (same size) / (changed size) 9.52.870.477 I slot release: id 3 | task 4815 | stop processing: n_tokens = 798, truncated = 0 9.52.870.484 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.892 9.52.870.524 I slot launch_slot_: id 0 | task 4823 | processing task, is_child = 0 9.52.870.572 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 327.969 MiB) 9.52.880.803 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 327.911 MiB) 9.52.894.056 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.106 MiB) 9.52.902.029 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.873 (> 0.100 thold), f_keep = 0.879 9.52.902.084 I slot launch_slot_: id 1 | task 4824 | processing task, is_child = 0 9.52.902.170 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.866 9.52.902.194 I slot launch_slot_: id 2 | task 4825 | processing task, is_child = 0 9.52.902.240 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.862 (> 0.100 thold), f_keep = 0.816 9.52.902.262 I slot launch_slot_: id 3 | task 4826 | processing task, is_child = 0 9.54.117.651 I slot print_timing: id 0 | task 4823 | prompt eval time = 1164.53 ms / 110 tokens ( 10.59 ms per token, 94.46 tokens per second) 9.54.117.655 I slot print_timing: id 0 | task 4823 | eval time = 50.85 ms / 2 tokens ( 50.85 ms per token, 19.66 tokens per second) 9.54.117.655 I slot print_timing: id 0 | task 4823 | total time = 1215.38 ms / 112 tokens 9.54.117.656 I slot print_timing: id 0 | task 4823 | graphs reused = 3489 9.54.117.656 I slot print_timing: id 0 | task 4823 | graph reallocs = 0 / 0 (same size) / (changed size) 9.54.117.691 I slot release: id 0 | task 4823 | stop processing: n_tokens = 734, truncated = 0 9.54.117.842 I slot print_timing: id 1 | task 4824 | prompt eval time = 1161.42 ms / 123 tokens ( 9.44 ms per token, 105.90 tokens per second) 9.54.117.844 I slot print_timing: id 1 | task 4824 | eval time = 50.84 ms / 2 tokens ( 50.84 ms per token, 19.67 tokens per second) 9.54.117.844 I slot print_timing: id 1 | task 4824 | total time = 1212.27 ms / 125 tokens 9.54.117.845 I slot print_timing: id 1 | task 4824 | graphs reused = 3489 9.54.117.845 I slot print_timing: id 1 | task 4824 | graph reallocs = 0 / 0 (same size) / (changed size) 9.54.117.871 I slot release: id 1 | task 4824 | stop processing: n_tokens = 747, truncated = 0 9.54.118.040 I slot print_timing: id 2 | task 4825 | prompt eval time = 1158.38 ms / 116 tokens ( 9.99 ms per token, 100.14 tokens per second) 9.54.118.041 I slot print_timing: id 2 | task 4825 | eval time = 50.84 ms / 2 tokens ( 50.84 ms per token, 19.67 tokens per second) 9.54.118.042 I slot print_timing: id 2 | task 4825 | total time = 1209.22 ms / 118 tokens 9.54.118.042 I slot print_timing: id 2 | task 4825 | graphs reused = 3489 9.54.118.042 I slot print_timing: id 2 | task 4825 | graph reallocs = 0 / 0 (same size) / (changed size) 9.54.118.077 I slot release: id 2 | task 4825 | stop processing: n_tokens = 740, truncated = 0 9.54.118.262 I slot print_timing: id 3 | task 4826 | prompt eval time = 1155.35 ms / 132 tokens ( 8.75 ms per token, 114.25 tokens per second) 9.54.118.264 I slot print_timing: id 3 | task 4826 | eval time = 50.85 ms / 2 tokens ( 50.85 ms per token, 19.66 tokens per second) 9.54.118.265 I slot print_timing: id 3 | task 4826 | total time = 1206.21 ms / 134 tokens 9.54.118.265 I slot print_timing: id 3 | task 4826 | graphs reused = 3489 9.54.118.265 I slot print_timing: id 3 | task 4826 | graph reallocs = 0 / 0 (same size) / (changed size) 9.54.118.286 I slot release: id 3 | task 4826 | stop processing: n_tokens = 756, truncated = 0 9.54.126.280 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 9.54.126.305 I slot launch_slot_: id 0 | task 4830 | processing task, is_child = 0 9.54.126.350 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 327.950 MiB) 9.54.134.171 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.771 MiB) 9.54.141.990 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.087 MiB) 9.54.149.805 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 747, t_last = 389035538352 9.54.149.893 I slot launch_slot_: id 1 | task 4831 | processing task, is_child = 0 9.54.149.970 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 740, t_last = 389035538558 9.54.150.034 I slot launch_slot_: id 2 | task 4832 | processing task, is_child = 0 9.54.150.075 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 756, t_last = 389035538767 9.54.150.135 I slot launch_slot_: id 3 | task 4833 | processing task, is_child = 0 9.57.228.165 I slot print_timing: id 0 | task 4830 | prompt eval time = 2212.82 ms / 124 tokens ( 17.85 ms per token, 56.04 tokens per second) 9.57.228.167 I slot print_timing: id 0 | task 4830 | eval time = 865.20 ms / 2 tokens ( 865.20 ms per token, 1.16 tokens per second) 9.57.228.168 I slot print_timing: id 0 | task 4830 | total time = 3078.02 ms / 126 tokens 9.57.228.168 I slot print_timing: id 0 | task 4830 | graphs reused = 3489 9.57.228.169 I slot print_timing: id 0 | task 4830 | graph reallocs = 0 / 0 (same size) / (changed size) 9.57.228.212 I slot release: id 0 | task 4830 | stop processing: n_tokens = 748, truncated = 0 9.57.228.223 I slot print_timing: id 1 | task 4831 | prompt processing, n_tokens = 457, progress = 0.47, t = 3.07 s / 148.64 tokens per second 9.57.231.333 I slot print_timing: id 2 | task 4832 | prompt processing, n_tokens = 439, progress = 0.46, t = 3.07 s / 142.79 tokens per second 9.57.233.234 I slot print_timing: id 3 | task 4833 | prompt processing, n_tokens = 474, progress = 0.48, t = 3.07 s / 154.18 tokens per second 9.59.283.820 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 748, t_last = 389038648693 9.59.283.884 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.294 MiB) 9.59.399.346 I slot launch_slot_: id 0 | task 4838 | processing task, is_child = 0 9.59.399.430 I slot print_timing: id 1 | task 4831 | prompt processing, n_tokens = 820, progress = 0.84, t = 5.13 s / 159.83 tokens per second 9.59.401.469 I slot print_timing: id 2 | task 4832 | prompt processing, n_tokens = 820, progress = 0.86, t = 5.13 s / 159.84 tokens per second 9.59.403.364 I slot print_timing: id 3 | task 4833 | prompt processing, n_tokens = 820, progress = 0.83, t = 5.13 s / 159.84 tokens per second 10.00.857.600 I slot print_timing: id 1 | task 4831 | prompt processing, n_tokens = 969, progress = 1.00, t = 6.51 s / 148.78 tokens per second 10.00.860.037 I slot print_timing: id 2 | task 4832 | prompt processing, n_tokens = 951, progress = 1.00, t = 6.51 s / 146.02 tokens per second 10.00.862.003 I slot print_timing: id 3 | task 4833 | prompt processing, n_tokens = 986, progress = 1.00, t = 6.51 s / 151.39 tokens per second 10.01.863.907 I slot print_timing: id 1 | task 4831 | prompt eval time = 7245.20 ms / 973 tokens ( 7.45 ms per token, 134.30 tokens per second) 10.01.863.912 I slot print_timing: id 1 | task 4831 | eval time = 465.22 ms / 2 tokens ( 465.22 ms per token, 2.15 tokens per second) 10.01.863.913 I slot print_timing: id 1 | task 4831 | total time = 7710.43 ms / 975 tokens 10.01.863.913 I slot print_timing: id 1 | task 4831 | graphs reused = 3489 10.01.863.913 I slot print_timing: id 1 | task 4831 | graph reallocs = 0 / 0 (same size) / (changed size) 10.01.863.980 I slot release: id 1 | task 4831 | stop processing: n_tokens = 974, truncated = 0 10.01.864.210 I slot print_timing: id 2 | task 4832 | prompt eval time = 7245.41 ms / 955 tokens ( 7.59 ms per token, 131.81 tokens per second) 10.01.864.213 I slot print_timing: id 2 | task 4832 | eval time = 465.26 ms / 2 tokens ( 465.26 ms per token, 2.15 tokens per second) 10.01.864.213 I slot print_timing: id 2 | task 4832 | total time = 7710.67 ms / 957 tokens 10.01.864.214 I slot print_timing: id 2 | task 4832 | graphs reused = 3489 10.01.864.214 I slot print_timing: id 2 | task 4832 | graph reallocs = 0 / 0 (same size) / (changed size) 10.01.864.256 I slot release: id 2 | task 4832 | stop processing: n_tokens = 956, truncated = 0 10.01.864.499 I slot print_timing: id 3 | task 4833 | prompt eval time = 7245.61 ms / 990 tokens ( 7.32 ms per token, 136.63 tokens per second) 10.01.864.502 I slot print_timing: id 3 | task 4833 | eval time = 465.29 ms / 2 tokens ( 465.29 ms per token, 2.15 tokens per second) 10.01.864.503 I slot print_timing: id 3 | task 4833 | total time = 7710.90 ms / 992 tokens 10.01.864.503 I slot print_timing: id 3 | task 4833 | graphs reused = 3489 10.01.864.503 I slot print_timing: id 3 | task 4833 | graph reallocs = 0 / 0 (same size) / (changed size) 10.01.864.528 I slot release: id 3 | task 4833 | stop processing: n_tokens = 991, truncated = 0 10.02.469.779 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 974, t_last = 389043284461 10.02.469.836 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.606 MiB) 10.02.956.373 I slot launch_slot_: id 1 | task 4844 | processing task, is_child = 0 10.02.956.437 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 335.185 MiB) 10.02.965.840 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 335.028 MiB) 10.02.973.575 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 956, t_last = 389043284737 10.02.973.676 I slot launch_slot_: id 2 | task 4845 | processing task, is_child = 0 10.02.973.724 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 991, t_last = 389043285009 10.02.973.794 I slot launch_slot_: id 3 | task 4846 | processing task, is_child = 0 10.02.973.801 I slot print_timing: id 0 | task 4838 | prompt processing, n_tokens = 1040, progress = 1.00, t = 3.07 s / 338.72 tokens per second 10.05.794.935 I slot print_timing: id 0 | task 4838 | prompt eval time = 5226.28 ms / 1044 tokens ( 5.01 ms per token, 199.76 tokens per second) 10.05.794.937 I slot print_timing: id 0 | task 4838 | eval time = 1169.29 ms / 2 tokens ( 1169.29 ms per token, 0.86 tokens per second) 10.05.794.938 I slot print_timing: id 0 | task 4838 | total time = 6395.57 ms / 1046 tokens 10.05.794.938 I slot print_timing: id 0 | task 4838 | graphs reused = 3489 10.05.794.939 I slot print_timing: id 0 | task 4838 | graph reallocs = 0 / 0 (same size) / (changed size) 10.05.795.012 I slot release: id 0 | task 4838 | stop processing: n_tokens = 1045, truncated = 0 10.08.391.851 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1045, t_last = 389047215493 10.08.391.921 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 335.204 MiB) 10.08.720.399 I slot launch_slot_: id 0 | task 4850 | processing task, is_child = 0 10.08.720.514 I slot print_timing: id 1 | task 4844 | prompt processing, n_tokens = 608, progress = 0.54, t = 5.42 s / 112.26 tokens per second 10.08.724.036 I slot print_timing: id 2 | task 4845 | prompt processing, n_tokens = 645, progress = 0.56, t = 5.42 s / 119.09 tokens per second 10.08.725.926 I slot print_timing: id 3 | task 4846 | prompt processing, n_tokens = 1575, progress = 0.75, t = 5.42 s / 290.81 tokens per second 10.11.248.377 I slot print_timing: id 1 | task 4844 | prompt processing, n_tokens = 977, progress = 0.87, t = 8.24 s / 118.57 tokens per second 10.11.252.081 I slot print_timing: id 2 | task 4845 | prompt processing, n_tokens = 977, progress = 0.84, t = 8.24 s / 118.57 tokens per second 10.11.253.955 I slot print_timing: id 3 | task 4846 | prompt processing, n_tokens = 1761, progress = 0.84, t = 8.24 s / 213.72 tokens per second 10.13.062.748 I slot print_timing: id 0 | task 4850 | prompt processing, n_tokens = 640, progress = 0.31, t = 4.34 s / 147.39 tokens per second 10.13.062.779 I slot print_timing: id 1 | task 4844 | prompt processing, n_tokens = 1120, progress = 1.00, t = 10.09 s / 111.03 tokens per second 10.13.450.688 I slot print_timing: id 2 | task 4845 | prompt processing, n_tokens = 1157, progress = 1.00, t = 10.09 s / 114.70 tokens per second 10.13.453.437 I slot print_timing: id 3 | task 4846 | prompt processing, n_tokens = 2087, progress = 1.00, t = 10.09 s / 206.90 tokens per second 10.15.256.768 I slot print_timing: id 0 | task 4850 | prompt processing, n_tokens = 1578, progress = 0.75, t = 6.54 s / 241.45 tokens per second 10.15.744.874 I slot print_timing: id 1 | task 4844 | prompt eval time = 12280.52 ms / 1124 tokens ( 10.93 ms per token, 91.53 tokens per second) 10.15.744.877 I slot print_timing: id 1 | task 4844 | eval time = 488.57 ms / 2 tokens ( 488.57 ms per token, 2.05 tokens per second) 10.15.744.877 I slot print_timing: id 1 | task 4844 | total time = 12769.10 ms / 1126 tokens 10.15.744.878 I slot print_timing: id 1 | task 4844 | graphs reused = 3489 10.15.744.878 I slot print_timing: id 1 | task 4844 | graph reallocs = 0 / 0 (same size) / (changed size) 10.15.744.931 I slot release: id 1 | task 4844 | stop processing: n_tokens = 1125, truncated = 0 10.15.745.181 I slot print_timing: id 2 | task 4845 | prompt eval time = 12280.68 ms / 1161 tokens ( 10.58 ms per token, 94.54 tokens per second) 10.15.745.184 I slot print_timing: id 2 | task 4845 | eval time = 488.65 ms / 2 tokens ( 488.65 ms per token, 2.05 tokens per second) 10.15.745.184 I slot print_timing: id 2 | task 4845 | total time = 12769.33 ms / 1163 tokens 10.15.745.185 I slot print_timing: id 2 | task 4845 | graphs reused = 3489 10.15.745.185 I slot print_timing: id 2 | task 4845 | graph reallocs = 0 / 0 (same size) / (changed size) 10.15.745.213 I slot release: id 2 | task 4845 | stop processing: n_tokens = 1162, truncated = 0 10.15.745.456 I slot print_timing: id 3 | task 4846 | prompt eval time = 12280.84 ms / 2091 tokens ( 5.87 ms per token, 170.27 tokens per second) 10.15.745.464 I slot print_timing: id 3 | task 4846 | eval time = 488.70 ms / 2 tokens ( 488.70 ms per token, 2.05 tokens per second) 10.15.745.464 I slot print_timing: id 3 | task 4846 | total time = 12769.54 ms / 2093 tokens 10.15.745.464 I slot print_timing: id 3 | task 4846 | graphs reused = 3489 10.15.745.464 I slot print_timing: id 3 | task 4846 | graph reallocs = 0 / 0 (same size) / (changed size) 10.15.745.535 I slot release: id 3 | task 4846 | stop processing: n_tokens = 2092, truncated = 0 10.15.745.545 I slot print_timing: id 0 | task 4850 | prompt processing, n_tokens = 1761, progress = 0.84, t = 7.02 s / 250.70 tokens per second 10.15.753.347 I slot print_timing: id 0 | task 4850 | prompt processing, n_tokens = 2090, progress = 1.00, t = 7.03 s / 297.17 tokens per second 10.16.455.721 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.870 (> 0.100 thold), f_keep = 0.856 10.16.455.778 I slot launch_slot_: id 3 | task 4857 | processing task, is_child = 0 10.16.455.843 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 335.067 MiB) 10.16.464.776 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 335.243 MiB) 10.16.472.553 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1125, t_last = 389057165412 10.16.472.655 I slot launch_slot_: id 1 | task 4858 | processing task, is_child = 0 10.16.472.709 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1162, t_last = 389057165694 10.16.472.781 I slot launch_slot_: id 2 | task 4859 | processing task, is_child = 0 10.18.455.862 I slot print_timing: id 0 | task 4850 | prompt eval time = 7735.29 ms / 2094 tokens ( 3.69 ms per token, 270.71 tokens per second) 10.18.455.865 I slot print_timing: id 0 | task 4850 | eval time = 2000.14 ms / 2 tokens ( 2000.14 ms per token, 0.50 tokens per second) 10.18.455.866 I slot print_timing: id 0 | task 4850 | total time = 9735.43 ms / 2096 tokens 10.18.455.866 I slot print_timing: id 0 | task 4850 | graphs reused = 3489 10.18.455.867 I slot print_timing: id 0 | task 4850 | graph reallocs = 0 / 0 (same size) / (changed size) 10.18.455.973 I slot release: id 0 | task 4850 | stop processing: n_tokens = 2095, truncated = 0 10.19.505.784 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.840 (> 0.100 thold), f_keep = 0.854 10.19.505.854 I slot launch_slot_: id 0 | task 4862 | processing task, is_child = 0 10.19.511.646 I slot print_timing: id 1 | task 4858 | prompt processing, n_tokens = 640, progress = 0.31, t = 3.03 s / 211.03 tokens per second 10.19.511.668 I slot print_timing: id 2 | task 4859 | prompt processing, n_tokens = 640, progress = 0.30, t = 3.03 s / 211.04 tokens per second 10.23.357.220 I slot print_timing: id 3 | task 4857 | prompt eval time = 3032.84 ms / 296 tokens ( 10.25 ms per token, 97.60 tokens per second) 10.23.357.223 I slot print_timing: id 3 | task 4857 | eval time = 3851.44 ms / 2 tokens ( 3851.44 ms per token, 0.26 tokens per second) 10.23.357.223 I slot print_timing: id 3 | task 4857 | total time = 6884.27 ms / 298 tokens 10.23.357.223 I slot print_timing: id 3 | task 4857 | graphs reused = 3489 10.23.357.224 I slot print_timing: id 3 | task 4857 | graph reallocs = 0 / 0 (same size) / (changed size) 10.23.357.304 I slot release: id 3 | task 4857 | stop processing: n_tokens = 2058, truncated = 0 10.23.357.320 I slot print_timing: id 0 | task 4862 | prompt processing, n_tokens = 365, progress = 1.00, t = 3.85 s / 94.78 tokens per second 10.23.361.078 I slot print_timing: id 1 | task 4858 | prompt processing, n_tokens = 1525, progress = 0.75, t = 6.88 s / 221.52 tokens per second 10.23.363.832 I slot print_timing: id 2 | task 4859 | prompt processing, n_tokens = 1437, progress = 0.68, t = 6.88 s / 208.74 tokens per second 10.24.324.487 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.868 (> 0.100 thold), f_keep = 0.869 10.24.324.564 I slot launch_slot_: id 3 | task 4865 | processing task, is_child = 0 10.24.324.575 I slot print_timing: id 1 | task 4858 | prompt processing, n_tokens = 1761, progress = 0.86, t = 7.85 s / 224.29 tokens per second 10.24.327.932 I slot print_timing: id 2 | task 4859 | prompt processing, n_tokens = 1589, progress = 0.75, t = 7.85 s / 202.39 tokens per second 10.26.019.302 I slot print_timing: id 0 | task 4862 | prompt eval time = 4818.61 ms / 369 tokens ( 13.06 ms per token, 76.58 tokens per second) 10.26.019.305 I slot print_timing: id 0 | task 4862 | eval time = 1694.82 ms / 2 tokens ( 1694.82 ms per token, 0.59 tokens per second) 10.26.019.306 I slot print_timing: id 0 | task 4862 | total time = 6513.43 ms / 371 tokens 10.26.019.306 I slot print_timing: id 0 | task 4862 | graphs reused = 3489 10.26.019.307 I slot print_timing: id 0 | task 4862 | graph reallocs = 0 / 0 (same size) / (changed size) 10.26.019.393 I slot release: id 0 | task 4862 | stop processing: n_tokens = 2131, truncated = 0 10.26.019.407 I slot print_timing: id 1 | task 4858 | prompt processing, n_tokens = 2037, progress = 1.00, t = 9.55 s / 213.38 tokens per second 10.26.022.791 I slot print_timing: id 2 | task 4859 | prompt processing, n_tokens = 1761, progress = 0.84, t = 9.55 s / 184.47 tokens per second 10.26.789.782 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.836 (> 0.100 thold), f_keep = 0.840 10.26.789.849 I slot launch_slot_: id 0 | task 4868 | processing task, is_child = 0 10.26.794.942 I slot print_timing: id 2 | task 4859 | prompt processing, n_tokens = 2101, progress = 1.00, t = 10.32 s / 203.66 tokens per second 10.27.608.506 I slot print_timing: id 1 | task 4858 | prompt eval time = 10316.74 ms / 2041 tokens ( 5.05 ms per token, 197.83 tokens per second) 10.27.608.509 I slot print_timing: id 1 | task 4858 | eval time = 818.98 ms / 2 tokens ( 818.98 ms per token, 1.22 tokens per second) 10.27.608.510 I slot print_timing: id 1 | task 4858 | total time = 11135.71 ms / 2043 tokens 10.27.608.510 I slot print_timing: id 1 | task 4858 | graphs reused = 3489 10.27.608.510 I slot print_timing: id 1 | task 4858 | graph reallocs = 0 / 0 (same size) / (changed size) 10.27.608.606 I slot release: id 1 | task 4858 | stop processing: n_tokens = 2042, truncated = 0 10.27.608.947 I slot print_timing: id 3 | task 4865 | prompt eval time = 2458.70 ms / 300 tokens ( 8.20 ms per token, 122.02 tokens per second) 10.27.608.951 I slot print_timing: id 3 | task 4865 | eval time = 819.17 ms / 2 tokens ( 819.17 ms per token, 1.22 tokens per second) 10.27.608.951 I slot print_timing: id 3 | task 4865 | total time = 3277.87 ms / 302 tokens 10.27.608.952 I slot print_timing: id 3 | task 4865 | graphs reused = 3489 10.27.608.952 I slot print_timing: id 3 | task 4865 | graph reallocs = 0 / 0 (same size) / (changed size) 10.27.609.017 I slot release: id 3 | task 4865 | stop processing: n_tokens = 2062, truncated = 0 10.27.678.210 I slot print_timing: id 2 | task 4859 | prompt eval time = 11135.93 ms / 2105 tokens ( 5.29 ms per token, 189.03 tokens per second) 10.27.678.212 I slot print_timing: id 2 | task 4859 | eval time = 69.41 ms / 2 tokens ( 69.41 ms per token, 14.41 tokens per second) 10.27.678.213 I slot print_timing: id 2 | task 4859 | total time = 11205.33 ms / 2107 tokens 10.27.678.213 I slot print_timing: id 2 | task 4859 | graphs reused = 3489 10.27.678.213 I slot print_timing: id 2 | task 4859 | graph reallocs = 0 / 0 (same size) / (changed size) 10.27.678.292 I slot release: id 2 | task 4859 | stop processing: n_tokens = 2106, truncated = 0 10.27.678.301 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.803 (> 0.100 thold), f_keep = 0.877 10.27.678.341 I slot launch_slot_: id 1 | task 4871 | processing task, is_child = 0 10.27.678.440 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 335.263 MiB) 10.27.691.991 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 335.126 MiB) 10.27.707.240 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.850 10.27.707.299 I slot launch_slot_: id 2 | task 4872 | processing task, is_child = 0 10.27.707.388 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.886 (> 0.100 thold), f_keep = 0.868 10.27.707.411 I slot launch_slot_: id 3 | task 4873 | processing task, is_child = 0 10.29.803.987 I slot print_timing: id 0 | task 4868 | prompt eval time = 888.19 ms / 380 tokens ( 2.34 ms per token, 427.84 tokens per second) 10.29.803.989 I slot print_timing: id 0 | task 4868 | eval time = 2125.93 ms / 2 tokens ( 2125.93 ms per token, 0.47 tokens per second) 10.29.803.989 I slot print_timing: id 0 | task 4868 | total time = 3014.12 ms / 382 tokens 10.29.803.990 I slot print_timing: id 0 | task 4868 | graphs reused = 3489 10.29.803.990 I slot print_timing: id 0 | task 4868 | graph reallocs = 0 / 0 (same size) / (changed size) 10.29.804.070 I slot release: id 0 | task 4868 | stop processing: n_tokens = 2142, truncated = 0 10.29.903.709 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.835 10.29.903.778 I slot launch_slot_: id 0 | task 4876 | processing task, is_child = 0 10.30.491.950 I slot print_timing: id 1 | task 4871 | prompt eval time = 2195.92 ms / 467 tokens ( 4.70 ms per token, 212.67 tokens per second) 10.30.491.952 I slot print_timing: id 1 | task 4871 | eval time = 588.61 ms / 2 tokens ( 588.61 ms per token, 1.70 tokens per second) 10.30.491.953 I slot print_timing: id 1 | task 4871 | total time = 2784.52 ms / 469 tokens 10.30.491.953 I slot print_timing: id 1 | task 4871 | graphs reused = 3489 10.30.491.953 I slot print_timing: id 1 | task 4871 | graph reallocs = 0 / 0 (same size) / (changed size) 10.30.492.038 I slot release: id 1 | task 4871 | stop processing: n_tokens = 2229, truncated = 0 10.30.492.202 I slot print_timing: id 2 | task 4872 | prompt eval time = 2192.74 ms / 210 tokens ( 10.44 ms per token, 95.77 tokens per second) 10.30.492.205 I slot print_timing: id 2 | task 4872 | eval time = 588.66 ms / 2 tokens ( 588.66 ms per token, 1.70 tokens per second) 10.30.492.205 I slot print_timing: id 2 | task 4872 | total time = 2781.40 ms / 212 tokens 10.30.492.205 I slot print_timing: id 2 | task 4872 | graphs reused = 3489 10.30.492.206 I slot print_timing: id 2 | task 4872 | graph reallocs = 0 / 0 (same size) / (changed size) 10.30.492.260 I slot release: id 2 | task 4872 | stop processing: n_tokens = 1972, truncated = 0 10.30.492.420 I slot print_timing: id 3 | task 4873 | prompt eval time = 2189.57 ms / 258 tokens ( 8.49 ms per token, 117.83 tokens per second) 10.30.492.423 I slot print_timing: id 3 | task 4873 | eval time = 588.72 ms / 2 tokens ( 588.72 ms per token, 1.70 tokens per second) 10.30.492.423 I slot print_timing: id 3 | task 4873 | total time = 2778.29 ms / 260 tokens 10.30.492.423 I slot print_timing: id 3 | task 4873 | graphs reused = 3489 10.30.492.424 I slot print_timing: id 3 | task 4873 | graph reallocs = 0 / 0 (same size) / (changed size) 10.30.492.472 I slot release: id 3 | task 4873 | stop processing: n_tokens = 2020, truncated = 0 10.30.539.327 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 10.30.539.365 I slot launch_slot_: id 1 | task 4879 | processing task, is_child = 0 10.30.539.459 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 335.107 MiB) 10.30.554.037 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 335.204 MiB) 10.30.568.439 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.867 (> 0.100 thold), f_keep = 0.908 10.30.568.500 I slot launch_slot_: id 2 | task 4880 | processing task, is_child = 0 10.30.568.588 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.886 10.30.568.610 I slot launch_slot_: id 3 | task 4881 | processing task, is_child = 0 10.32.529.268 I slot print_timing: id 0 | task 4876 | prompt eval time = 635.53 ms / 253 tokens ( 2.51 ms per token, 398.09 tokens per second) 10.32.529.270 I slot print_timing: id 0 | task 4876 | eval time = 1989.94 ms / 2 tokens ( 1989.94 ms per token, 0.50 tokens per second) 10.32.529.271 I slot print_timing: id 0 | task 4876 | total time = 2625.47 ms / 255 tokens 10.32.529.271 I slot print_timing: id 0 | task 4876 | graphs reused = 3489 10.32.529.272 I slot print_timing: id 0 | task 4876 | graph reallocs = 0 / 0 (same size) / (changed size) 10.32.529.357 I slot release: id 0 | task 4876 | stop processing: n_tokens = 2015, truncated = 0 10.32.629.935 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.866 (> 0.100 thold), f_keep = 0.888 10.32.630.001 I slot launch_slot_: id 0 | task 4884 | processing task, is_child = 0 10.33.301.949 I slot print_timing: id 1 | task 4879 | prompt eval time = 2060.98 ms / 345 tokens ( 5.97 ms per token, 167.40 tokens per second) 10.33.301.952 I slot print_timing: id 1 | task 4879 | eval time = 672.34 ms / 2 tokens ( 672.34 ms per token, 1.49 tokens per second) 10.33.301.953 I slot print_timing: id 1 | task 4879 | total time = 2733.33 ms / 347 tokens 10.33.301.953 I slot print_timing: id 1 | task 4879 | graphs reused = 3489 10.33.301.954 I slot print_timing: id 1 | task 4879 | graph reallocs = 0 / 0 (same size) / (changed size) 10.33.302.034 I slot release: id 1 | task 4879 | stop processing: n_tokens = 2107, truncated = 0 10.33.302.189 I slot print_timing: id 2 | task 4880 | prompt eval time = 2057.87 ms / 304 tokens ( 6.77 ms per token, 147.73 tokens per second) 10.33.302.191 I slot print_timing: id 2 | task 4880 | eval time = 672.43 ms / 2 tokens ( 672.43 ms per token, 1.49 tokens per second) 10.33.302.192 I slot print_timing: id 2 | task 4880 | total time = 2730.29 ms / 306 tokens 10.33.302.192 I slot print_timing: id 2 | task 4880 | graphs reused = 3489 10.33.302.192 I slot print_timing: id 2 | task 4880 | graph reallocs = 0 / 0 (same size) / (changed size) 10.33.302.251 I slot release: id 2 | task 4880 | stop processing: n_tokens = 2066, truncated = 0 10.33.302.478 I slot print_timing: id 3 | task 4881 | prompt eval time = 2054.81 ms / 212 tokens ( 9.69 ms per token, 103.17 tokens per second) 10.33.302.481 I slot print_timing: id 3 | task 4881 | eval time = 672.55 ms / 2 tokens ( 672.55 ms per token, 1.49 tokens per second) 10.33.302.481 I slot print_timing: id 3 | task 4881 | total time = 2727.35 ms / 214 tokens 10.33.302.481 I slot print_timing: id 3 | task 4881 | graphs reused = 3489 10.33.302.481 I slot print_timing: id 3 | task 4881 | graph reallocs = 0 / 0 (same size) / (changed size) 10.33.302.524 I slot release: id 3 | task 4881 | stop processing: n_tokens = 1974, truncated = 0 10.33.349.686 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.850 10.33.349.731 I slot launch_slot_: id 1 | task 4887 | processing task, is_child = 0 10.33.349.828 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 335.165 MiB) 10.33.364.777 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 335.185 MiB) 10.33.379.144 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.847 (> 0.100 thold), f_keep = 0.866 10.33.379.206 I slot launch_slot_: id 2 | task 4888 | processing task, is_child = 0 10.33.379.289 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.826 (> 0.100 thold), f_keep = 0.906 10.33.379.311 I slot launch_slot_: id 3 | task 4889 | processing task, is_child = 0 10.35.510.259 I slot print_timing: id 0 | task 4884 | prompt eval time = 719.66 ms / 304 tokens ( 2.37 ms per token, 422.42 tokens per second) 10.35.510.262 I slot print_timing: id 0 | task 4884 | eval time = 2160.59 ms / 2 tokens ( 2160.59 ms per token, 0.46 tokens per second) 10.35.510.262 I slot print_timing: id 0 | task 4884 | total time = 2880.24 ms / 306 tokens 10.35.510.263 I slot print_timing: id 0 | task 4884 | graphs reused = 3489 10.35.510.263 I slot print_timing: id 0 | task 4884 | graph reallocs = 0 / 0 (same size) / (changed size) 10.35.510.342 I slot release: id 0 | task 4884 | stop processing: n_tokens = 2066, truncated = 0 10.35.610.075 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.823 (> 0.100 thold), f_keep = 0.866 10.35.610.145 I slot launch_slot_: id 0 | task 4892 | processing task, is_child = 0 10.36.426.974 I slot print_timing: id 1 | task 4887 | prompt eval time = 2230.39 ms / 210 tokens ( 10.62 ms per token, 94.15 tokens per second) 10.36.426.978 I slot print_timing: id 1 | task 4887 | eval time = 817.26 ms / 2 tokens ( 817.26 ms per token, 1.22 tokens per second) 10.36.426.979 I slot print_timing: id 1 | task 4887 | total time = 3047.65 ms / 212 tokens 10.36.426.979 I slot print_timing: id 1 | task 4887 | graphs reused = 3489 10.36.426.980 I slot print_timing: id 1 | task 4887 | graph reallocs = 0 / 0 (same size) / (changed size) 10.36.427.069 I slot release: id 1 | task 4887 | stop processing: n_tokens = 1972, truncated = 0 10.36.427.233 I slot print_timing: id 2 | task 4888 | prompt eval time = 2227.27 ms / 353 tokens ( 6.31 ms per token, 158.49 tokens per second) 10.36.427.236 I slot print_timing: id 2 | task 4888 | eval time = 817.36 ms / 2 tokens ( 817.36 ms per token, 1.22 tokens per second) 10.36.427.236 I slot print_timing: id 2 | task 4888 | total time = 3044.63 ms / 355 tokens 10.36.427.236 I slot print_timing: id 2 | task 4888 | graphs reused = 3489 10.36.427.237 I slot print_timing: id 2 | task 4888 | graph reallocs = 0 / 0 (same size) / (changed size) 10.36.427.300 I slot release: id 2 | task 4888 | stop processing: n_tokens = 2115, truncated = 0 10.36.427.525 I slot print_timing: id 3 | task 4889 | prompt eval time = 2224.22 ms / 405 tokens ( 5.49 ms per token, 182.09 tokens per second) 10.36.427.528 I slot print_timing: id 3 | task 4889 | eval time = 817.46 ms / 2 tokens ( 817.46 ms per token, 1.22 tokens per second) 10.36.427.529 I slot print_timing: id 3 | task 4889 | total time = 3041.68 ms / 407 tokens 10.36.427.529 I slot print_timing: id 3 | task 4889 | graphs reused = 3489 10.36.427.529 I slot print_timing: id 3 | task 4889 | graph reallocs = 0 / 0 (same size) / (changed size) 10.36.427.579 I slot release: id 3 | task 4889 | stop processing: n_tokens = 2167, truncated = 0 10.36.474.629 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.896 (> 0.100 thold), f_keep = 0.907 10.36.474.671 I slot launch_slot_: id 1 | task 4895 | processing task, is_child = 0 10.36.474.775 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 333.972 MiB) 10.36.489.857 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 334.520 MiB) 10.36.505.014 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.846 10.36.505.074 I slot launch_slot_: id 2 | task 4896 | processing task, is_child = 0 10.36.505.166 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.880 (> 0.100 thold), f_keep = 0.826 10.36.505.188 I slot launch_slot_: id 3 | task 4897 | processing task, is_child = 0 10.38.200.256 I slot print_timing: id 0 | task 4892 | prompt eval time = 864.46 ms / 413 tokens ( 2.09 ms per token, 477.75 tokens per second) 10.38.200.259 I slot print_timing: id 0 | task 4892 | eval time = 1725.63 ms / 2 tokens ( 1725.63 ms per token, 0.58 tokens per second) 10.38.200.259 I slot print_timing: id 0 | task 4892 | total time = 2590.09 ms / 415 tokens 10.38.200.260 I slot print_timing: id 0 | task 4892 | graphs reused = 3489 10.38.200.260 I slot print_timing: id 0 | task 4892 | graph reallocs = 0 / 0 (same size) / (changed size) 10.38.200.349 I slot release: id 0 | task 4892 | stop processing: n_tokens = 2175, truncated = 0 10.38.300.059 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.823 10.38.300.128 I slot launch_slot_: id 0 | task 4900 | processing task, is_child = 0 10.38.731.864 I slot print_timing: id 1 | task 4895 | prompt eval time = 1794.51 ms / 236 tokens ( 7.60 ms per token, 131.51 tokens per second) 10.38.731.867 I slot print_timing: id 1 | task 4895 | eval time = 432.15 ms / 2 tokens ( 432.15 ms per token, 2.31 tokens per second) 10.38.731.867 I slot print_timing: id 1 | task 4895 | total time = 2226.66 ms / 238 tokens 10.38.731.868 I slot print_timing: id 1 | task 4895 | graphs reused = 3489 10.38.731.868 I slot print_timing: id 1 | task 4895 | graph reallocs = 0 / 0 (same size) / (changed size) 10.38.731.946 I slot release: id 1 | task 4895 | stop processing: n_tokens = 1998, truncated = 0 10.38.732.111 I slot print_timing: id 2 | task 4896 | prompt eval time = 1791.36 ms / 264 tokens ( 6.79 ms per token, 147.37 tokens per second) 10.38.732.114 I slot print_timing: id 2 | task 4896 | eval time = 432.24 ms / 2 tokens ( 432.24 ms per token, 2.31 tokens per second) 10.38.732.114 I slot print_timing: id 2 | task 4896 | total time = 2223.60 ms / 266 tokens 10.38.732.115 I slot print_timing: id 2 | task 4896 | graphs reused = 3489 10.38.732.115 I slot print_timing: id 2 | task 4896 | graph reallocs = 0 / 0 (same size) / (changed size) 10.38.732.170 I slot release: id 2 | task 4896 | stop processing: n_tokens = 2026, truncated = 0 10.38.732.399 I slot print_timing: id 3 | task 4897 | prompt eval time = 1788.31 ms / 272 tokens ( 6.57 ms per token, 152.10 tokens per second) 10.38.732.403 I slot print_timing: id 3 | task 4897 | eval time = 432.35 ms / 2 tokens ( 432.35 ms per token, 2.31 tokens per second) 10.38.732.403 I slot print_timing: id 3 | task 4897 | total time = 2220.66 ms / 274 tokens 10.38.732.403 I slot print_timing: id 3 | task 4897 | graphs reused = 3489 10.38.732.404 I slot print_timing: id 3 | task 4897 | graph reallocs = 0 / 0 (same size) / (changed size) 10.38.732.447 I slot release: id 3 | task 4897 | stop processing: n_tokens = 2034, truncated = 0 10.38.778.758 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1998, t_last = 389080152427 10.38.778.860 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 335.713 MiB) 10.38.799.208 I slot launch_slot_: id 1 | task 4903 | processing task, is_child = 0 10.38.799.307 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 335.028 MiB) 10.38.811.127 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 334.227 MiB) 10.38.811.132 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.556 MiB) 10.38.824.223 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.883 10.38.824.277 I slot launch_slot_: id 2 | task 4904 | processing task, is_child = 0 10.38.824.375 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.899 (> 0.100 thold), f_keep = 0.880 10.38.824.396 I slot launch_slot_: id 3 | task 4905 | processing task, is_child = 0 10.40.660.142 I slot print_timing: id 0 | task 4900 | prompt eval time = 478.62 ms / 149 tokens ( 3.21 ms per token, 311.31 tokens per second) 10.40.660.145 I slot print_timing: id 0 | task 4900 | eval time = 1881.38 ms / 2 tokens ( 1881.38 ms per token, 0.53 tokens per second) 10.40.660.145 I slot print_timing: id 0 | task 4900 | total time = 2360.00 ms / 151 tokens 10.40.660.146 I slot print_timing: id 0 | task 4900 | graphs reused = 3489 10.40.660.146 I slot print_timing: id 0 | task 4900 | graph reallocs = 0 / 0 (same size) / (changed size) 10.40.660.227 I slot release: id 0 | task 4900 | stop processing: n_tokens = 1911, truncated = 0 10.41.234.906 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1911, t_last = 389082080708 10.41.235.015 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.810 MiB) 10.41.253.046 I slot launch_slot_: id 0 | task 4908 | processing task, is_child = 0 10.42.783.557 I slot print_timing: id 2 | task 4904 | prompt eval time = 2410.10 ms / 196 tokens ( 12.30 ms per token, 81.32 tokens per second) 10.42.783.559 I slot print_timing: id 2 | task 4904 | eval time = 1548.89 ms / 2 tokens ( 1548.89 ms per token, 0.65 tokens per second) 10.42.783.560 I slot print_timing: id 2 | task 4904 | total time = 3958.99 ms / 198 tokens 10.42.783.560 I slot print_timing: id 2 | task 4904 | graphs reused = 3489 10.42.783.561 I slot print_timing: id 2 | task 4904 | graph reallocs = 0 / 0 (same size) / (changed size) 10.42.783.640 I slot release: id 2 | task 4904 | stop processing: n_tokens = 1958, truncated = 0 10.42.783.878 I slot print_timing: id 3 | task 4905 | prompt eval time = 2407.13 ms / 230 tokens ( 10.47 ms per token, 95.55 tokens per second) 10.42.783.880 I slot print_timing: id 3 | task 4905 | eval time = 1548.98 ms / 2 tokens ( 1548.98 ms per token, 0.65 tokens per second) 10.42.783.880 I slot print_timing: id 3 | task 4905 | total time = 3956.11 ms / 232 tokens 10.42.783.881 I slot print_timing: id 3 | task 4905 | graphs reused = 3489 10.42.783.881 I slot print_timing: id 3 | task 4905 | graph reallocs = 0 / 0 (same size) / (changed size) 10.42.783.934 I slot release: id 3 | task 4905 | stop processing: n_tokens = 1992, truncated = 0 10.42.787.887 I slot print_timing: id 1 | task 4903 | prompt processing, n_tokens = 959, progress = 0.65, t = 3.96 s / 242.24 tokens per second 10.43.580.433 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1958, t_last = 389084204121 10.43.580.549 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 329.671 MiB) 10.43.910.457 I slot launch_slot_: id 2 | task 4911 | processing task, is_child = 0 10.43.910.557 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.673 MiB) 10.43.936.236 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1992, t_last = 389084204415 10.43.936.380 I slot launch_slot_: id 3 | task 4912 | processing task, is_child = 0 10.43.936.407 I slot print_timing: id 1 | task 4903 | prompt processing, n_tokens = 1275, progress = 0.86, t = 4.76 s / 268.08 tokens per second 10.46.513.186 I slot print_timing: id 0 | task 4908 | prompt processing, n_tokens = 1161, progress = 0.69, t = 5.26 s / 220.72 tokens per second 10.46.826.400 I slot print_timing: id 1 | task 4903 | prompt processing, n_tokens = 1471, progress = 1.00, t = 7.69 s / 191.32 tokens per second 10.48.091.702 I slot print_timing: id 0 | task 4908 | prompt processing, n_tokens = 1275, progress = 0.76, t = 6.84 s / 186.45 tokens per second 10.48.094.323 I slot print_timing: id 2 | task 4911 | prompt processing, n_tokens = 575, progress = 0.37, t = 4.15 s / 138.45 tokens per second 10.48.094.341 I slot print_timing: id 3 | task 4912 | prompt processing, n_tokens = 409, progress = 0.41, t = 4.15 s / 98.48 tokens per second 10.50.004.391 I slot print_timing: id 1 | task 4903 | prompt eval time = 9267.28 ms / 1475 tokens ( 6.28 ms per token, 159.16 tokens per second) 10.50.004.396 I slot print_timing: id 1 | task 4903 | eval time = 1912.70 ms / 2 tokens ( 1912.70 ms per token, 0.52 tokens per second) 10.50.004.397 I slot print_timing: id 1 | task 4903 | total time = 11179.98 ms / 1477 tokens 10.50.004.397 I slot print_timing: id 1 | task 4903 | graphs reused = 3489 10.50.004.398 I slot print_timing: id 1 | task 4903 | graph reallocs = 0 / 0 (same size) / (changed size) 10.50.004.481 I slot release: id 1 | task 4903 | stop processing: n_tokens = 1476, truncated = 0 10.50.004.497 I slot print_timing: id 0 | task 4908 | prompt processing, n_tokens = 1673, progress = 1.00, t = 8.75 s / 191.18 tokens per second 10.50.008.449 I slot print_timing: id 2 | task 4911 | prompt processing, n_tokens = 1039, progress = 0.67, t = 6.07 s / 171.29 tokens per second 10.50.011.340 I slot print_timing: id 3 | task 4912 | prompt processing, n_tokens = 483, progress = 0.48, t = 6.07 s / 79.63 tokens per second 10.51.267.417 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1476, t_last = 389091424963 10.51.267.493 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.536 MiB) 10.51.278.785 I slot launch_slot_: id 1 | task 4917 | processing task, is_child = 0 10.51.278.908 I slot print_timing: id 2 | task 4911 | prompt processing, n_tokens = 1275, progress = 0.82, t = 7.33 s / 173.97 tokens per second 10.51.280.817 I slot print_timing: id 3 | task 4912 | prompt processing, n_tokens = 853, progress = 0.85, t = 7.33 s / 116.39 tokens per second 10.52.744.021 I slot print_timing: id 0 | task 4908 | prompt eval time = 10014.35 ms / 1677 tokens ( 5.97 ms per token, 167.46 tokens per second) 10.52.744.024 I slot print_timing: id 0 | task 4908 | eval time = 1476.61 ms / 2 tokens ( 1476.61 ms per token, 0.68 tokens per second) 10.52.744.024 I slot print_timing: id 0 | task 4908 | total time = 11490.96 ms / 1679 tokens 10.52.744.025 I slot print_timing: id 0 | task 4908 | graphs reused = 3489 10.52.744.025 I slot print_timing: id 0 | task 4908 | graph reallocs = 0 / 0 (same size) / (changed size) 10.52.744.109 I slot release: id 0 | task 4908 | stop processing: n_tokens = 1678, truncated = 0 10.52.746.997 I slot print_timing: id 2 | task 4911 | prompt processing, n_tokens = 1551, progress = 1.00, t = 8.81 s / 176.14 tokens per second 10.52.750.093 I slot print_timing: id 3 | task 4912 | prompt processing, n_tokens = 995, progress = 1.00, t = 8.81 s / 113.00 tokens per second 10.53.218.253 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1678, t_last = 389094164590 10.53.218.333 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.849 MiB) 10.53.228.322 I slot launch_slot_: id 0 | task 4920 | processing task, is_child = 0 10.54.056.361 I slot print_timing: id 2 | task 4911 | prompt eval time = 9279.78 ms / 1555 tokens ( 5.97 ms per token, 167.57 tokens per second) 10.54.056.363 I slot print_timing: id 2 | task 4911 | eval time = 838.28 ms / 2 tokens ( 838.28 ms per token, 1.19 tokens per second) 10.54.056.364 I slot print_timing: id 2 | task 4911 | total time = 10118.06 ms / 1557 tokens 10.54.056.364 I slot print_timing: id 2 | task 4911 | graphs reused = 3489 10.54.056.365 I slot print_timing: id 2 | task 4911 | graph reallocs = 0 / 0 (same size) / (changed size) 10.54.056.445 I slot release: id 2 | task 4911 | stop processing: n_tokens = 1556, truncated = 0 10.54.056.699 I slot print_timing: id 3 | task 4912 | prompt eval time = 9279.81 ms / 999 tokens ( 9.29 ms per token, 107.65 tokens per second) 10.54.056.702 I slot print_timing: id 3 | task 4912 | eval time = 838.45 ms / 2 tokens ( 838.45 ms per token, 1.19 tokens per second) 10.54.056.703 I slot print_timing: id 3 | task 4912 | total time = 10118.26 ms / 1001 tokens 10.54.056.703 I slot print_timing: id 3 | task 4912 | graphs reused = 3489 10.54.056.704 I slot print_timing: id 3 | task 4912 | graph reallocs = 0 / 0 (same size) / (changed size) 10.54.056.745 I slot release: id 3 | task 4912 | stop processing: n_tokens = 1000, truncated = 0 10.54.664.461 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.882 10.54.664.522 I slot launch_slot_: id 3 | task 4923 | processing task, is_child = 0 10.54.664.598 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.693 MiB) 10.55.178.496 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1556, t_last = 389095476927 10.55.178.653 I slot launch_slot_: id 2 | task 4924 | processing task, is_child = 0 10.55.178.669 I slot print_timing: id 1 | task 4917 | prompt processing, n_tokens = 853, progress = 0.86, t = 3.39 s / 251.95 tokens per second 10.56.298.674 I slot print_timing: id 0 | task 4920 | prompt processing, n_tokens = 461, progress = 0.47, t = 3.07 s / 150.15 tokens per second 10.56.655.324 I slot print_timing: id 1 | task 4917 | prompt processing, n_tokens = 985, progress = 1.00, t = 5.02 s / 196.22 tokens per second 10.57.869.699 I slot print_timing: id 0 | task 4920 | prompt processing, n_tokens = 853, progress = 0.87, t = 4.64 s / 183.80 tokens per second 10.58.491.122 I slot print_timing: id 1 | task 4917 | prompt eval time = 6590.65 ms / 989 tokens ( 6.66 ms per token, 150.06 tokens per second) 10.58.491.125 I slot print_timing: id 1 | task 4917 | eval time = 621.67 ms / 2 tokens ( 621.67 ms per token, 1.61 tokens per second) 10.58.491.125 I slot print_timing: id 1 | task 4917 | total time = 7212.32 ms / 991 tokens 10.58.491.126 I slot print_timing: id 1 | task 4917 | graphs reused = 3489 10.58.491.126 I slot print_timing: id 1 | task 4917 | graph reallocs = 0 / 0 (same size) / (changed size) 10.58.491.190 I slot release: id 1 | task 4917 | stop processing: n_tokens = 990, truncated = 0 10.58.491.350 I slot print_timing: id 3 | task 4923 | prompt eval time = 2688.86 ms / 107 tokens ( 25.13 ms per token, 39.79 tokens per second) 10.58.491.354 I slot print_timing: id 3 | task 4923 | eval time = 621.66 ms / 2 tokens ( 621.66 ms per token, 1.61 tokens per second) 10.58.491.354 I slot print_timing: id 3 | task 4923 | total time = 3310.52 ms / 109 tokens 10.58.491.355 I slot print_timing: id 3 | task 4923 | graphs reused = 3489 10.58.491.355 I slot print_timing: id 3 | task 4923 | graph reallocs = 0 / 0 (same size) / (changed size) 10.58.491.382 I slot release: id 3 | task 4923 | stop processing: n_tokens = 961, truncated = 0 10.58.491.388 I slot print_timing: id 0 | task 4920 | prompt processing, n_tokens = 973, progress = 1.00, t = 5.26 s / 184.89 tokens per second 10.58.495.221 I slot print_timing: id 2 | task 4924 | prompt processing, n_tokens = 467, progress = 0.48, t = 3.31 s / 141.08 tokens per second 10.59.261.190 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.890 10.59.261.257 I slot launch_slot_: id 1 | task 4929 | processing task, is_child = 0 10.59.261.317 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 333.112 MiB) 10.59.269.776 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.917 10.59.269.814 I slot launch_slot_: id 3 | task 4930 | processing task, is_child = 0 10.59.273.035 I slot print_timing: id 2 | task 4924 | prompt processing, n_tokens = 853, progress = 0.87, t = 4.08 s / 209.06 tokens per second 11.00.085.226 I slot print_timing: id 0 | task 4920 | prompt eval time = 6032.85 ms / 977 tokens ( 6.17 ms per token, 161.95 tokens per second) 11.00.085.231 I slot print_timing: id 0 | task 4920 | eval time = 824.04 ms / 2 tokens ( 824.04 ms per token, 1.21 tokens per second) 11.00.085.231 I slot print_timing: id 0 | task 4920 | total time = 6856.89 ms / 979 tokens 11.00.085.232 I slot print_timing: id 0 | task 4920 | graphs reused = 3489 11.00.085.232 I slot print_timing: id 0 | task 4920 | graph reallocs = 0 / 0 (same size) / (changed size) 11.00.085.281 I slot release: id 0 | task 4920 | stop processing: n_tokens = 978, truncated = 0 11.00.088.741 I slot print_timing: id 2 | task 4924 | prompt processing, n_tokens = 979, progress = 1.00, t = 4.90 s / 199.62 tokens per second 11.00.182.950 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 978, t_last = 389101505762 11.00.183.017 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 332.760 MiB) 11.00.192.237 I slot launch_slot_: id 0 | task 4933 | processing task, is_child = 0 11.00.640.629 I slot print_timing: id 1 | task 4929 | prompt eval time = 912.78 ms / 123 tokens ( 7.42 ms per token, 134.75 tokens per second) 11.00.640.632 I slot print_timing: id 1 | task 4929 | eval time = 458.02 ms / 2 tokens ( 458.02 ms per token, 2.18 tokens per second) 11.00.640.632 I slot print_timing: id 1 | task 4929 | total time = 1370.80 ms / 125 tokens 11.00.640.633 I slot print_timing: id 1 | task 4929 | graphs reused = 3489 11.00.640.633 I slot print_timing: id 1 | task 4929 | graph reallocs = 0 / 0 (same size) / (changed size) 11.00.640.677 I slot release: id 1 | task 4929 | stop processing: n_tokens = 977, truncated = 0 11.00.640.826 I slot print_timing: id 2 | task 4924 | prompt eval time = 5002.06 ms / 983 tokens ( 5.09 ms per token, 196.52 tokens per second) 11.00.640.830 I slot print_timing: id 2 | task 4924 | eval time = 458.05 ms / 2 tokens ( 458.05 ms per token, 2.18 tokens per second) 11.00.640.831 I slot print_timing: id 2 | task 4924 | total time = 5460.10 ms / 985 tokens 11.00.640.831 I slot print_timing: id 2 | task 4924 | graphs reused = 3489 11.00.640.831 I slot print_timing: id 2 | task 4924 | graph reallocs = 0 / 0 (same size) / (changed size) 11.00.640.860 I slot release: id 2 | task 4924 | stop processing: n_tokens = 984, truncated = 0 11.00.641.031 I slot print_timing: id 3 | task 4930 | prompt eval time = 908.02 ms / 119 tokens ( 7.63 ms per token, 131.05 tokens per second) 11.00.641.032 I slot print_timing: id 3 | task 4930 | eval time = 458.08 ms / 2 tokens ( 458.08 ms per token, 2.18 tokens per second) 11.00.641.032 I slot print_timing: id 3 | task 4930 | total time = 1366.11 ms / 121 tokens 11.00.641.033 I slot print_timing: id 3 | task 4930 | graphs reused = 3489 11.00.641.033 I slot print_timing: id 3 | task 4930 | graph reallocs = 0 / 0 (same size) / (changed size) 11.00.641.063 I slot release: id 3 | task 4930 | stop processing: n_tokens = 973, truncated = 0 11.01.019.687 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 977, t_last = 389102061158 11.01.019.744 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 333.444 MiB) 11.01.749.204 I slot launch_slot_: id 1 | task 4937 | processing task, is_child = 0 11.01.749.262 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 334.500 MiB) 11.01.757.581 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 336.065 MiB) 11.01.765.464 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 984, t_last = 389102061341 11.01.765.566 I slot launch_slot_: id 2 | task 4938 | processing task, is_child = 0 11.01.765.613 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 973, t_last = 389102061544 11.01.765.684 I slot launch_slot_: id 3 | task 4939 | processing task, is_child = 0 11.03.408.550 I slot print_timing: id 0 | task 4933 | prompt processing, n_tokens = 821, progress = 1.00, t = 3.22 s / 255.26 tokens per second 11.04.912.187 I slot print_timing: id 1 | task 4937 | prompt processing, n_tokens = 533, progress = 0.33, t = 3.14 s / 169.51 tokens per second 11.04.912.207 I slot print_timing: id 2 | task 4938 | prompt processing, n_tokens = 533, progress = 0.33, t = 3.14 s / 169.51 tokens per second 11.04.912.220 I slot print_timing: id 3 | task 4939 | prompt processing, n_tokens = 533, progress = 0.34, t = 3.14 s / 169.52 tokens per second 11.08.010.264 I slot print_timing: id 0 | task 4933 | prompt eval time = 4719.93 ms / 825 tokens ( 5.72 ms per token, 174.79 tokens per second) 11.08.010.266 I slot print_timing: id 0 | task 4933 | eval time = 3098.08 ms / 2 tokens ( 3098.08 ms per token, 0.32 tokens per second) 11.08.010.267 I slot print_timing: id 0 | task 4933 | total time = 7818.01 ms / 827 tokens 11.08.010.268 I slot print_timing: id 0 | task 4933 | graphs reused = 3489 11.08.010.268 I slot print_timing: id 0 | task 4933 | graph reallocs = 0 / 0 (same size) / (changed size) 11.08.010.314 I slot release: id 0 | task 4933 | stop processing: n_tokens = 826, truncated = 0 11.08.010.329 I slot print_timing: id 1 | task 4937 | prompt processing, n_tokens = 1099, progress = 0.68, t = 6.24 s / 176.05 tokens per second 11.08.012.500 I slot print_timing: id 2 | task 4938 | prompt processing, n_tokens = 1113, progress = 0.68, t = 6.24 s / 178.30 tokens per second 11.08.014.678 I slot print_timing: id 3 | task 4939 | prompt processing, n_tokens = 1071, progress = 0.67, t = 6.24 s / 171.57 tokens per second 11.09.513.590 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 826, t_last = 389109430795 11.09.513.659 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 336.788 MiB) 11.09.713.435 I slot launch_slot_: id 0 | task 4944 | processing task, is_child = 0 11.09.713.525 I slot print_timing: id 1 | task 4937 | prompt processing, n_tokens = 1374, progress = 0.85, t = 7.75 s / 177.38 tokens per second 11.09.716.657 I slot print_timing: id 2 | task 4938 | prompt processing, n_tokens = 1374, progress = 0.84, t = 7.75 s / 177.38 tokens per second 11.09.718.547 I slot print_timing: id 3 | task 4939 | prompt processing, n_tokens = 1374, progress = 0.87, t = 7.75 s / 177.39 tokens per second 11.11.974.668 I slot print_timing: id 1 | task 4937 | prompt processing, n_tokens = 1611, progress = 1.00, t = 10.12 s / 159.17 tokens per second 11.11.977.297 I slot print_timing: id 2 | task 4938 | prompt processing, n_tokens = 1625, progress = 1.00, t = 10.12 s / 160.55 tokens per second 11.11.979.336 I slot print_timing: id 3 | task 4939 | prompt processing, n_tokens = 1583, progress = 1.00, t = 10.12 s / 156.40 tokens per second 11.13.688.913 I slot print_timing: id 1 | task 4937 | prompt eval time = 10742.93 ms / 1615 tokens ( 6.65 ms per token, 150.33 tokens per second) 11.13.688.921 I slot print_timing: id 1 | task 4937 | eval time = 1178.39 ms / 2 tokens ( 1178.39 ms per token, 0.85 tokens per second) 11.13.688.921 I slot print_timing: id 1 | task 4937 | total time = 11921.32 ms / 1617 tokens 11.13.688.924 I slot print_timing: id 1 | task 4937 | graphs reused = 3489 11.13.688.924 I slot print_timing: id 1 | task 4937 | graph reallocs = 0 / 0 (same size) / (changed size) 11.13.689.013 I slot release: id 1 | task 4937 | stop processing: n_tokens = 1616, truncated = 0 11.13.689.205 I slot print_timing: id 2 | task 4938 | prompt eval time = 10743.07 ms / 1629 tokens ( 6.59 ms per token, 151.63 tokens per second) 11.13.689.212 I slot print_timing: id 2 | task 4938 | eval time = 1178.47 ms / 2 tokens ( 1178.47 ms per token, 0.85 tokens per second) 11.13.689.212 I slot print_timing: id 2 | task 4938 | total time = 11921.54 ms / 1631 tokens 11.13.689.213 I slot print_timing: id 2 | task 4938 | graphs reused = 3489 11.13.689.213 I slot print_timing: id 2 | task 4938 | graph reallocs = 0 / 0 (same size) / (changed size) 11.13.689.272 I slot release: id 2 | task 4938 | stop processing: n_tokens = 1630, truncated = 0 11.13.689.522 I slot print_timing: id 3 | task 4939 | prompt eval time = 10743.25 ms / 1587 tokens ( 6.77 ms per token, 147.72 tokens per second) 11.13.689.529 I slot print_timing: id 3 | task 4939 | eval time = 1178.54 ms / 2 tokens ( 1178.54 ms per token, 0.85 tokens per second) 11.13.689.530 I slot print_timing: id 3 | task 4939 | total time = 11921.79 ms / 1589 tokens 11.13.689.530 I slot print_timing: id 3 | task 4939 | graphs reused = 3489 11.13.689.530 I slot print_timing: id 3 | task 4939 | graph reallocs = 0 / 0 (same size) / (changed size) 11.13.689.566 I slot release: id 3 | task 4939 | stop processing: n_tokens = 1588, truncated = 0 11.13.689.574 I slot print_timing: id 0 | task 4944 | prompt processing, n_tokens = 1113, progress = 0.68, t = 3.98 s / 279.98 tokens per second 11.13.698.211 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1616, t_last = 389115109494 11.13.698.290 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 355.247 MiB) 11.14.255.090 I slot launch_slot_: id 1 | task 4949 | processing task, is_child = 0 11.14.255.168 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 354.387 MiB) 11.14.266.152 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 352.627 MiB) 11.14.274.742 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1630, t_last = 389115109753 11.14.274.862 I slot launch_slot_: id 2 | task 4950 | processing task, is_child = 0 11.14.274.930 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.816 (> 0.100 thold), f_keep = 0.883 11.14.274.952 I slot launch_slot_: id 3 | task 4951 | processing task, is_child = 0 11.14.274.958 I slot print_timing: id 0 | task 4944 | prompt processing, n_tokens = 1374, progress = 0.84, t = 3.98 s / 344.81 tokens per second 11.15.514.550 I slot print_timing: id 0 | task 4944 | prompt processing, n_tokens = 1625, progress = 1.00, t = 5.80 s / 280.12 tokens per second 11.17.137.509 I slot print_timing: id 0 | task 4944 | prompt eval time = 6869.55 ms / 1629 tokens ( 4.22 ms per token, 237.13 tokens per second) 11.17.137.512 I slot print_timing: id 0 | task 4944 | eval time = 554.51 ms / 2 tokens ( 554.51 ms per token, 1.80 tokens per second) 11.17.137.512 I slot print_timing: id 0 | task 4944 | total time = 7424.05 ms / 1631 tokens 11.17.137.513 I slot print_timing: id 0 | task 4944 | graphs reused = 3489 11.17.137.513 I slot print_timing: id 0 | task 4944 | graph reallocs = 0 / 0 (same size) / (changed size) 11.17.137.585 I slot release: id 0 | task 4944 | stop processing: n_tokens = 1630, truncated = 0 11.17.137.801 I slot print_timing: id 3 | task 4951 | prompt eval time = 2306.17 ms / 344 tokens ( 6.70 ms per token, 149.16 tokens per second) 11.17.137.807 I slot print_timing: id 3 | task 4951 | eval time = 554.56 ms / 2 tokens ( 554.56 ms per token, 1.80 tokens per second) 11.17.137.807 I slot print_timing: id 3 | task 4951 | total time = 2860.73 ms / 346 tokens 11.17.137.807 I slot print_timing: id 3 | task 4951 | graphs reused = 3489 11.17.137.808 I slot print_timing: id 3 | task 4951 | graph reallocs = 0 / 0 (same size) / (changed size) 11.17.137.863 I slot release: id 3 | task 4951 | stop processing: n_tokens = 1719, truncated = 0 11.18.516.793 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1630, t_last = 389118558066 11.18.516.874 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 353.566 MiB) 11.18.667.946 I slot launch_slot_: id 0 | task 4956 | processing task, is_child = 0 11.18.668.026 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 354.465 MiB) 11.18.679.459 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1719, t_last = 389118558344 11.18.679.569 I slot launch_slot_: id 3 | task 4957 | processing task, is_child = 0 11.18.679.707 I slot print_timing: id 1 | task 4949 | prompt processing, n_tokens = 725, progress = 0.87, t = 4.24 s / 170.99 tokens per second 11.18.681.597 I slot print_timing: id 2 | task 4950 | prompt processing, n_tokens = 725, progress = 0.84, t = 4.24 s / 171.00 tokens per second 11.19.970.909 I slot print_timing: id 1 | task 4949 | prompt processing, n_tokens = 834, progress = 1.00, t = 5.62 s / 148.53 tokens per second 11.19.974.058 I slot print_timing: id 2 | task 4950 | prompt processing, n_tokens = 861, progress = 1.00, t = 5.62 s / 153.34 tokens per second 11.21.266.431 I slot print_timing: id 1 | task 4949 | prompt eval time = 6487.86 ms / 838 tokens ( 7.74 ms per token, 129.16 tokens per second) 11.21.266.437 I slot print_timing: id 1 | task 4949 | eval time = 501.70 ms / 2 tokens ( 501.70 ms per token, 1.99 tokens per second) 11.21.266.438 I slot print_timing: id 1 | task 4949 | total time = 6989.56 ms / 840 tokens 11.21.266.438 I slot print_timing: id 1 | task 4949 | graphs reused = 3489 11.21.266.439 I slot print_timing: id 1 | task 4949 | graph reallocs = 0 / 0 (same size) / (changed size) 11.21.266.477 I slot release: id 1 | task 4949 | stop processing: n_tokens = 839, truncated = 0 11.21.266.629 I slot print_timing: id 2 | task 4950 | prompt eval time = 6487.98 ms / 865 tokens ( 7.50 ms per token, 133.32 tokens per second) 11.21.266.631 I slot print_timing: id 2 | task 4950 | eval time = 501.68 ms / 2 tokens ( 501.68 ms per token, 1.99 tokens per second) 11.21.266.632 I slot print_timing: id 2 | task 4950 | total time = 6989.66 ms / 867 tokens 11.21.266.632 I slot print_timing: id 2 | task 4950 | graphs reused = 3489 11.21.266.632 I slot print_timing: id 2 | task 4950 | graph reallocs = 0 / 0 (same size) / (changed size) 11.21.266.658 I slot release: id 2 | task 4950 | stop processing: n_tokens = 866, truncated = 0 11.21.998.403 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 839, t_last = 389122686958 11.21.998.462 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 352.666 MiB) 11.22.685.792 I slot launch_slot_: id 1 | task 4962 | processing task, is_child = 0 11.22.685.843 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 355.423 MiB) 11.22.693.596 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 866, t_last = 389122687139 11.22.693.674 I slot launch_slot_: id 2 | task 4963 | processing task, is_child = 0 11.22.693.682 I slot print_timing: id 0 | task 4956 | prompt processing, n_tokens = 716, progress = 0.85, t = 3.32 s / 215.74 tokens per second 11.22.695.706 I slot print_timing: id 3 | task 4957 | prompt processing, n_tokens = 716, progress = 0.83, t = 3.31 s / 216.00 tokens per second 11.23.799.936 I slot print_timing: id 0 | task 4956 | prompt processing, n_tokens = 838, progress = 1.00, t = 5.12 s / 163.66 tokens per second 11.23.869.840 I slot print_timing: id 3 | task 4957 | prompt processing, n_tokens = 855, progress = 1.00, t = 5.12 s / 167.11 tokens per second 11.24.938.721 I slot print_timing: id 0 | task 4956 | prompt eval time = 5873.70 ms / 842 tokens ( 6.98 ms per token, 143.35 tokens per second) 11.24.938.723 I slot print_timing: id 0 | task 4956 | eval time = 385.43 ms / 2 tokens ( 385.43 ms per token, 2.59 tokens per second) 11.24.938.724 I slot print_timing: id 0 | task 4956 | total time = 6259.13 ms / 844 tokens 11.24.938.724 I slot print_timing: id 0 | task 4956 | graphs reused = 3489 11.24.938.725 I slot print_timing: id 0 | task 4956 | graph reallocs = 0 / 0 (same size) / (changed size) 11.24.938.769 I slot release: id 0 | task 4956 | stop processing: n_tokens = 843, truncated = 0 11.24.939.002 I slot print_timing: id 3 | task 4957 | prompt eval time = 5870.02 ms / 859 tokens ( 6.83 ms per token, 146.34 tokens per second) 11.24.939.004 I slot print_timing: id 3 | task 4957 | eval time = 385.48 ms / 2 tokens ( 385.48 ms per token, 2.59 tokens per second) 11.24.939.005 I slot print_timing: id 3 | task 4957 | total time = 6255.50 ms / 861 tokens 11.24.939.005 I slot print_timing: id 3 | task 4957 | graphs reused = 3489 11.24.939.005 I slot print_timing: id 3 | task 4957 | graph reallocs = 0 / 0 (same size) / (changed size) 11.24.939.033 I slot release: id 3 | task 4957 | stop processing: n_tokens = 860, truncated = 0 11.26.270.696 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 843, t_last = 389126359250 11.26.270.757 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 356.440 MiB) 11.26.386.562 I slot launch_slot_: id 0 | task 4968 | processing task, is_child = 0 11.26.386.620 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 353.135 MiB) 11.26.400.821 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 860, t_last = 389126359514 11.26.400.899 I slot launch_slot_: id 3 | task 4969 | processing task, is_child = 0 11.26.400.972 I slot print_timing: id 1 | task 4962 | prompt processing, n_tokens = 628, progress = 0.81, t = 3.58 s / 175.66 tokens per second 11.26.402.907 I slot print_timing: id 2 | task 4963 | prompt processing, n_tokens = 716, progress = 0.81, t = 3.58 s / 200.28 tokens per second 11.27.779.410 I slot print_timing: id 1 | task 4962 | prompt processing, n_tokens = 776, progress = 0.99, t = 4.97 s / 156.21 tokens per second 11.27.783.604 I slot print_timing: id 2 | task 4963 | prompt processing, n_tokens = 882, progress = 1.00, t = 4.97 s / 177.55 tokens per second 11.29.930.468 I slot print_timing: id 1 | task 4962 | prompt eval time = 5741.52 ms / 780 tokens ( 7.36 ms per token, 135.85 tokens per second) 11.29.930.472 I slot print_timing: id 1 | task 4962 | eval time = 1493.38 ms / 2 tokens ( 1493.38 ms per token, 0.67 tokens per second) 11.29.930.472 I slot print_timing: id 1 | task 4962 | total time = 7234.89 ms / 782 tokens 11.29.930.473 I slot print_timing: id 1 | task 4962 | graphs reused = 3489 11.29.930.473 I slot print_timing: id 1 | task 4962 | graph reallocs = 0 / 0 (same size) / (changed size) 11.29.930.530 I slot release: id 1 | task 4962 | stop processing: n_tokens = 781, truncated = 0 11.29.930.771 I slot print_timing: id 2 | task 4963 | prompt eval time = 5741.62 ms / 886 tokens ( 6.48 ms per token, 154.31 tokens per second) 11.29.930.777 I slot print_timing: id 2 | task 4963 | eval time = 1493.51 ms / 2 tokens ( 1493.51 ms per token, 0.67 tokens per second) 11.29.930.777 I slot print_timing: id 2 | task 4963 | total time = 7235.13 ms / 888 tokens 11.29.930.777 I slot print_timing: id 2 | task 4963 | graphs reused = 3489 11.29.930.778 I slot print_timing: id 2 | task 4963 | graph reallocs = 0 / 0 (same size) / (changed size) 11.29.930.807 I slot release: id 2 | task 4963 | stop processing: n_tokens = 887, truncated = 0 11.29.930.815 I slot print_timing: id 0 | task 4968 | prompt processing, n_tokens = 628, progress = 0.84, t = 3.53 s / 177.94 tokens per second 11.29.933.979 I slot print_timing: id 3 | task 4969 | prompt processing, n_tokens = 571, progress = 0.83, t = 3.53 s / 161.96 tokens per second 11.30.280.288 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 781, t_last = 389131351011 11.30.611.182 I slot launch_slot_: id 1 | task 4974 | processing task, is_child = 0 11.30.611.243 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 353.683 MiB) 11.30.624.984 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 887, t_last = 389131351288 11.30.625.062 I slot launch_slot_: id 2 | task 4975 | processing task, is_child = 0 11.30.625.068 I slot print_timing: id 0 | task 4968 | prompt processing, n_tokens = 745, progress = 0.99, t = 3.88 s / 192.04 tokens per second 11.30.629.009 I slot print_timing: id 3 | task 4969 | prompt processing, n_tokens = 687, progress = 0.99, t = 3.88 s / 177.27 tokens per second 11.31.686.813 I slot print_timing: id 0 | task 4968 | prompt eval time = 4780.11 ms / 749 tokens ( 6.38 ms per token, 156.69 tokens per second) 11.31.686.816 I slot print_timing: id 0 | task 4968 | eval time = 505.80 ms / 2 tokens ( 505.80 ms per token, 1.98 tokens per second) 11.31.686.816 I slot print_timing: id 0 | task 4968 | total time = 5285.90 ms / 751 tokens 11.31.686.817 I slot print_timing: id 0 | task 4968 | graphs reused = 3489 11.31.686.817 I slot print_timing: id 0 | task 4968 | graph reallocs = 0 / 0 (same size) / (changed size) 11.31.686.855 I slot release: id 0 | task 4968 | stop processing: n_tokens = 750, truncated = 0 11.31.686.998 I slot print_timing: id 3 | task 4969 | prompt eval time = 4776.45 ms / 691 tokens ( 6.91 ms per token, 144.67 tokens per second) 11.31.687.000 I slot print_timing: id 3 | task 4969 | eval time = 505.76 ms / 2 tokens ( 505.76 ms per token, 1.98 tokens per second) 11.31.687.000 I slot print_timing: id 3 | task 4969 | total time = 5282.21 ms / 693 tokens 11.31.687.001 I slot print_timing: id 3 | task 4969 | graphs reused = 3489 11.31.687.001 I slot print_timing: id 3 | task 4969 | graph reallocs = 0 / 0 (same size) / (changed size) 11.31.687.043 I slot release: id 3 | task 4969 | stop processing: n_tokens = 692, truncated = 0 11.33.697.010 I slot print_timing: id 1 | task 4974 | prompt processing, n_tokens = 708, progress = 0.99, t = 3.07 s / 230.76 tokens per second 11.33.882.618 I slot print_timing: id 2 | task 4975 | prompt processing, n_tokens = 674, progress = 0.99, t = 3.07 s / 219.68 tokens per second 11.33.986.318 I slot print_timing: id 1 | task 4974 | prompt eval time = 3321.72 ms / 712 tokens ( 4.67 ms per token, 214.35 tokens per second) 11.33.986.323 I slot print_timing: id 1 | task 4974 | eval time = 35.70 ms / 2 tokens ( 35.70 ms per token, 28.01 tokens per second) 11.33.986.324 I slot print_timing: id 1 | task 4974 | total time = 3357.42 ms / 714 tokens 11.33.986.324 I slot print_timing: id 1 | task 4974 | graphs reused = 3489 11.33.986.325 I slot print_timing: id 1 | task 4974 | graph reallocs = 0 / 0 (same size) / (changed size) 11.33.986.356 I slot release: id 1 | task 4974 | stop processing: n_tokens = 713, truncated = 0 11.33.986.488 I slot print_timing: id 2 | task 4975 | prompt eval time = 3321.86 ms / 678 tokens ( 4.90 ms per token, 204.10 tokens per second) 11.33.986.490 I slot print_timing: id 2 | task 4975 | eval time = 35.67 ms / 2 tokens ( 35.67 ms per token, 28.03 tokens per second) 11.33.986.490 I slot print_timing: id 2 | task 4975 | total time = 3357.53 ms / 680 tokens 11.33.986.491 I slot print_timing: id 2 | task 4975 | graphs reused = 3489 11.33.986.491 I slot print_timing: id 2 | task 4975 | graph reallocs = 0 / 0 (same size) / (changed size) 11.33.986.510 I slot release: id 2 | task 4975 | stop processing: n_tokens = 679, truncated = 0 11.37.466.314 I srv operator(): operator(): cleaning up before exit...