/Users/minipro/quantdiff/work/llama-b11869/src/build/bin/llama-server -m /Users/minipro/quantdiff/models/campaign/1ba3362152b9/Sage-A1.5.i1-Q2_K.gguf --host 127.0.0.1 --port 8091 -c 16384 -np 4 -ngl 999 -fa on --jinja --seed 1234 --chat-template-kwargs "{\"enable_thinking\": false}" --no-webui -a quant 0.00.044.006 W Setting 'enable_thinking' via --chat-template-kwargs is deprecated. Use --reasoning on / --reasoning off instead. 0.00.044.056 I srv llama_server: initializing ... 0.00.044.061 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.044.144 I srv init_listene: The UI is disabled 0.00.044.145 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.044.181 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) 0.00.045.815 I srv load_model: loading model '/Users/minipro/quantdiff/models/campaign/1ba3362152b9/Sage-A1.5.i1-Q2_K.gguf' 0.00.344.281 W model has unused tensor blk.40.attn_norm.weight (size = 8192 bytes) -- ignoring 0.00.344.292 W model has unused tensor blk.40.post_attention_norm.weight (size = 8192 bytes) -- ignoring 0.00.344.299 W model has unused tensor blk.40.attn_q.weight (size = 5505024 bytes) -- ignoring 0.00.344.301 W model has unused tensor blk.40.attn_k.weight (size = 344064 bytes) -- ignoring 0.00.344.304 W model has unused tensor blk.40.attn_v.weight (size = 589824 bytes) -- ignoring 0.00.344.311 W model has unused tensor blk.40.attn_output.weight (size = 3604480 bytes) -- ignoring 0.00.344.313 W model has unused tensor blk.40.attn_q_norm.weight (size = 1024 bytes) -- ignoring 0.00.344.315 W model has unused tensor blk.40.attn_k_norm.weight (size = 1024 bytes) -- ignoring 0.00.344.317 W model has unused tensor blk.40.ffn_gate_inp.weight (size = 2097152 bytes) -- ignoring 0.00.344.320 W model has unused tensor blk.40.ffn_down_exps.weight (size = 115343360 bytes) -- ignoring 0.00.344.324 W model has unused tensor blk.40.ffn_gate_exps.weight (size = 88080384 bytes) -- ignoring 0.00.344.326 W model has unused tensor blk.40.ffn_up_exps.weight (size = 88080384 bytes) -- ignoring 0.00.344.329 W model has unused tensor blk.40.ffn_gate_inp_shexp.weight (size = 8192 bytes) -- ignoring 0.00.344.331 W model has unused tensor blk.40.ffn_gate_shexp.weight (size = 344064 bytes) -- ignoring 0.00.344.333 W model has unused tensor blk.40.ffn_up_shexp.weight (size = 344064 bytes) -- ignoring 0.00.344.335 W model has unused tensor blk.40.ffn_down_shexp.weight (size = 450560 bytes) -- ignoring 0.00.344.338 W model has unused tensor blk.40.nextn.eh_proj.weight (size = 2752512 bytes) -- ignoring 0.00.344.341 W model has unused tensor blk.40.nextn.enorm.weight (size = 8192 bytes) -- ignoring 0.00.344.343 W model has unused tensor blk.40.nextn.hnorm.weight (size = 8192 bytes) -- ignoring 0.00.344.350 W model has unused tensor blk.40.nextn.shared_head_norm.weight (size = 8192 bytes) -- ignoring 0.00.970.444 I cmn init: llama threadpool init, n_threads = 8 0.01.058.435 I srv load_model: initializing, n_slots = 4, n_ctx_slot = 4096, kv_unified = 'false' 0.01.062.854 W srv init: chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve) 0.01.062.867 I srv server_run_i: model loaded 0.01.062.869 I srv server_on_li: listening on http://127.0.0.1:8091 0.31.578.244 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.31.578.275 I slot launch_slot_: id 0 | task 0 | processing task, is_child = 0 0.31.578.276 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.31.578.304 I slot launch_slot_: id 1 | task 1 | processing task, is_child = 0 0.31.578.306 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.31.578.325 I slot launch_slot_: id 2 | task 2 | processing task, is_child = 0 0.31.578.326 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.31.578.340 I slot launch_slot_: id 3 | task 3 | processing task, is_child = 0 0.32.676.388 I slot print_timing: id 0 | task 0 | prompt eval time = 1044.52 ms / 115 tokens ( 9.08 ms per token, 110.10 tokens per second) 0.32.676.390 I slot print_timing: id 0 | task 0 | eval time = 53.51 ms / 2 tokens ( 53.51 ms per token, 18.69 tokens per second) 0.32.676.390 I slot print_timing: id 0 | task 0 | total time = 1098.03 ms / 117 tokens 0.32.676.391 I slot print_timing: id 0 | task 0 | graphs reused = 1 0.32.676.391 I slot print_timing: id 0 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.676.415 I slot release: id 0 | task 0 | stop processing: n_tokens = 116, truncated = 0 0.32.676.573 I slot print_timing: id 1 | task 1 | prompt eval time = 1044.82 ms / 130 tokens ( 8.04 ms per token, 124.42 tokens per second) 0.32.676.578 I slot print_timing: id 1 | task 1 | eval time = 53.40 ms / 2 tokens ( 53.40 ms per token, 18.73 tokens per second) 0.32.676.579 I slot print_timing: id 1 | task 1 | total time = 1098.21 ms / 132 tokens 0.32.676.580 I slot print_timing: id 1 | task 1 | graphs reused = 1 0.32.676.580 I slot print_timing: id 1 | task 1 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.676.591 I slot release: id 1 | task 1 | stop processing: n_tokens = 131, truncated = 0 0.32.676.758 I slot print_timing: id 2 | task 2 | prompt eval time = 1045.15 ms / 115 tokens ( 9.09 ms per token, 110.03 tokens per second) 0.32.676.759 I slot print_timing: id 2 | task 2 | eval time = 53.25 ms / 2 tokens ( 53.25 ms per token, 18.78 tokens per second) 0.32.676.760 I slot print_timing: id 2 | task 2 | total time = 1098.40 ms / 117 tokens 0.32.676.760 I slot print_timing: id 2 | task 2 | graphs reused = 1 0.32.676.761 I slot print_timing: id 2 | task 2 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.676.774 I slot release: id 2 | task 2 | stop processing: n_tokens = 116, truncated = 0 0.32.676.939 I slot print_timing: id 3 | task 3 | prompt eval time = 1045.60 ms / 122 tokens ( 8.57 ms per token, 116.68 tokens per second) 0.32.676.944 I slot print_timing: id 3 | task 3 | eval time = 52.97 ms / 2 tokens ( 52.97 ms per token, 18.88 tokens per second) 0.32.676.945 I slot print_timing: id 3 | task 3 | total time = 1098.57 ms / 124 tokens 0.32.676.945 I slot print_timing: id 3 | task 3 | graphs reused = 1 0.32.676.945 I slot print_timing: id 3 | task 3 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.676.954 I slot release: id 3 | task 3 | stop processing: n_tokens = 123, truncated = 0 0.32.684.990 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.269 (> 0.100 thold), f_keep = 0.221 0.32.694.443 I slot launch_slot_: id 1 | task 7 | processing task, is_child = 0 0.32.721.766 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.191 (> 0.100 thold), f_keep = 0.250 0.32.721.813 I slot launch_slot_: id 2 | task 8 | processing task, is_child = 0 0.32.721.845 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.241 0.32.721.885 I slot launch_slot_: id 0 | task 9 | processing task, is_child = 0 0.32.721.905 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.140 (> 0.100 thold), f_keep = 0.228 0.32.721.939 I slot launch_slot_: id 3 | task 10 | processing task, is_child = 0 0.34.255.262 I slot print_timing: id 0 | task 9 | prompt eval time = 1480.30 ms / 160 tokens ( 9.25 ms per token, 108.09 tokens per second) 0.34.255.265 I slot print_timing: id 0 | task 9 | eval time = 53.00 ms / 2 tokens ( 53.00 ms per token, 18.87 tokens per second) 0.34.255.265 I slot print_timing: id 0 | task 9 | total time = 1533.31 ms / 162 tokens 0.34.255.266 I slot print_timing: id 0 | task 9 | graphs reused = 1 0.34.255.266 I slot print_timing: id 0 | task 9 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.255.291 I slot release: id 0 | task 9 | stop processing: n_tokens = 161, truncated = 0 0.34.255.444 I slot print_timing: id 1 | task 7 | prompt eval time = 1480.44 ms / 108 tokens ( 13.71 ms per token, 72.95 tokens per second) 0.34.255.448 I slot print_timing: id 1 | task 7 | eval time = 53.04 ms / 2 tokens ( 53.04 ms per token, 18.86 tokens per second) 0.34.255.449 I slot print_timing: id 1 | task 7 | total time = 1533.48 ms / 110 tokens 0.34.255.449 I slot print_timing: id 1 | task 7 | graphs reused = 1 0.34.255.449 I slot print_timing: id 1 | task 7 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.255.458 I slot release: id 1 | task 7 | stop processing: n_tokens = 109, truncated = 0 0.34.255.619 I slot print_timing: id 2 | task 8 | prompt eval time = 1480.61 ms / 152 tokens ( 9.74 ms per token, 102.66 tokens per second) 0.34.255.624 I slot print_timing: id 2 | task 8 | eval time = 53.04 ms / 2 tokens ( 53.04 ms per token, 18.85 tokens per second) 0.34.255.624 I slot print_timing: id 2 | task 8 | total time = 1533.64 ms / 154 tokens 0.34.255.624 I slot print_timing: id 2 | task 8 | graphs reused = 1 0.34.255.624 I slot print_timing: id 2 | task 8 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.255.632 I slot release: id 2 | task 8 | stop processing: n_tokens = 153, truncated = 0 0.34.255.802 I slot print_timing: id 3 | task 10 | prompt eval time = 1480.76 ms / 200 tokens ( 7.40 ms per token, 135.07 tokens per second) 0.34.255.805 I slot print_timing: id 3 | task 10 | eval time = 53.05 ms / 2 tokens ( 53.05 ms per token, 18.85 tokens per second) 0.34.255.805 I slot print_timing: id 3 | task 10 | total time = 1533.81 ms / 202 tokens 0.34.255.805 I slot print_timing: id 3 | task 10 | graphs reused = 1 0.34.255.806 I slot print_timing: id 3 | task 10 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.255.817 I slot release: id 3 | task 10 | stop processing: n_tokens = 201, truncated = 0 0.34.261.055 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.239 (> 0.100 thold), f_keep = 0.174 0.34.270.323 I slot launch_slot_: id 0 | task 14 | processing task, is_child = 0 0.34.298.044 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.246 (> 0.100 thold), f_keep = 0.266 0.34.298.095 I slot launch_slot_: id 1 | task 15 | processing task, is_child = 0 0.34.298.129 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.224 (> 0.100 thold), f_keep = 0.183 0.34.298.162 I slot launch_slot_: id 2 | task 16 | processing task, is_child = 0 0.34.298.182 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.187 (> 0.100 thold), f_keep = 0.139 0.34.298.215 I slot launch_slot_: id 3 | task 17 | processing task, is_child = 0 0.35.543.787 I slot print_timing: id 0 | task 14 | prompt eval time = 1192.60 ms / 117 tokens ( 10.19 ms per token, 98.10 tokens per second) 0.35.543.789 I slot print_timing: id 0 | task 14 | eval time = 52.96 ms / 2 tokens ( 52.96 ms per token, 18.88 tokens per second) 0.35.543.790 I slot print_timing: id 0 | task 14 | total time = 1245.56 ms / 119 tokens 0.35.543.790 I slot print_timing: id 0 | task 14 | graphs reused = 1 0.35.543.791 I slot print_timing: id 0 | task 14 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.543.809 I slot release: id 0 | task 14 | stop processing: n_tokens = 118, truncated = 0 0.35.543.967 I slot print_timing: id 1 | task 15 | prompt eval time = 1192.74 ms / 118 tokens ( 10.11 ms per token, 98.93 tokens per second) 0.35.543.968 I slot print_timing: id 1 | task 15 | eval time = 52.98 ms / 2 tokens ( 52.98 ms per token, 18.87 tokens per second) 0.35.543.969 I slot print_timing: id 1 | task 15 | total time = 1245.73 ms / 120 tokens 0.35.543.969 I slot print_timing: id 1 | task 15 | graphs reused = 1 0.35.543.970 I slot print_timing: id 1 | task 15 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.543.981 I slot release: id 1 | task 15 | stop processing: n_tokens = 119, truncated = 0 0.35.544.156 I slot print_timing: id 2 | task 16 | prompt eval time = 1192.90 ms / 125 tokens ( 9.54 ms per token, 104.79 tokens per second) 0.35.544.158 I slot print_timing: id 2 | task 16 | eval time = 53.01 ms / 2 tokens ( 53.01 ms per token, 18.86 tokens per second) 0.35.544.158 I slot print_timing: id 2 | task 16 | total time = 1245.91 ms / 127 tokens 0.35.544.159 I slot print_timing: id 2 | task 16 | graphs reused = 1 0.35.544.159 I slot print_timing: id 2 | task 16 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.544.171 I slot release: id 2 | task 16 | stop processing: n_tokens = 126, truncated = 0 0.35.544.347 I slot print_timing: id 3 | task 17 | prompt eval time = 1193.05 ms / 150 tokens ( 7.95 ms per token, 125.73 tokens per second) 0.35.544.349 I slot print_timing: id 3 | task 17 | eval time = 53.03 ms / 2 tokens ( 53.03 ms per token, 18.86 tokens per second) 0.35.544.349 I slot print_timing: id 3 | task 17 | total time = 1246.08 ms / 152 tokens 0.35.544.349 I slot print_timing: id 3 | task 17 | graphs reused = 1 0.35.544.350 I slot print_timing: id 3 | task 17 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.544.358 I slot release: id 3 | task 17 | stop processing: n_tokens = 151, truncated = 0 0.35.549.605 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.235 (> 0.100 thold), f_keep = 0.237 0.35.558.638 I slot launch_slot_: id 0 | task 21 | processing task, is_child = 0 0.35.586.230 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 0.35.586.290 I slot launch_slot_: id 1 | task 23 | processing task, is_child = 0 0.35.586.323 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.196 (> 0.100 thold), f_keep = 0.222 0.35.586.354 I slot launch_slot_: id 2 | task 22 | processing task, is_child = 0 0.35.586.372 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 0.35.586.404 I slot launch_slot_: id 3 | task 24 | processing task, is_child = 0 0.37.007.346 I slot print_timing: id 0 | task 21 | prompt eval time = 1367.96 ms / 119 tokens ( 11.50 ms per token, 86.99 tokens per second) 0.37.007.348 I slot print_timing: id 0 | task 21 | eval time = 52.97 ms / 2 tokens ( 52.97 ms per token, 18.88 tokens per second) 0.37.007.349 I slot print_timing: id 0 | task 21 | total time = 1420.93 ms / 121 tokens 0.37.007.349 I slot print_timing: id 0 | task 21 | graphs reused = 1 0.37.007.349 I slot print_timing: id 0 | task 21 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.007.372 I slot release: id 0 | task 21 | stop processing: n_tokens = 120, truncated = 0 0.37.007.525 I slot print_timing: id 1 | task 23 | prompt eval time = 1368.10 ms / 136 tokens ( 10.06 ms per token, 99.41 tokens per second) 0.37.007.530 I slot print_timing: id 1 | task 23 | eval time = 53.00 ms / 2 tokens ( 53.00 ms per token, 18.87 tokens per second) 0.37.007.531 I slot print_timing: id 1 | task 23 | total time = 1421.10 ms / 138 tokens 0.37.007.531 I slot print_timing: id 1 | task 23 | graphs reused = 1 0.37.007.531 I slot print_timing: id 1 | task 23 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.007.544 I slot release: id 1 | task 23 | stop processing: n_tokens = 137, truncated = 0 0.37.007.715 I slot print_timing: id 2 | task 22 | prompt eval time = 1368.27 ms / 143 tokens ( 9.57 ms per token, 104.51 tokens per second) 0.37.007.717 I slot print_timing: id 2 | task 22 | eval time = 53.01 ms / 2 tokens ( 53.01 ms per token, 18.86 tokens per second) 0.37.007.717 I slot print_timing: id 2 | task 22 | total time = 1421.28 ms / 145 tokens 0.37.007.717 I slot print_timing: id 2 | task 22 | graphs reused = 1 0.37.007.717 I slot print_timing: id 2 | task 22 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.007.726 I slot release: id 2 | task 22 | stop processing: n_tokens = 144, truncated = 0 0.37.007.898 I slot print_timing: id 3 | task 24 | prompt eval time = 1368.42 ms / 181 tokens ( 7.56 ms per token, 132.27 tokens per second) 0.37.007.900 I slot print_timing: id 3 | task 24 | eval time = 53.03 ms / 2 tokens ( 53.03 ms per token, 18.86 tokens per second) 0.37.007.900 I slot print_timing: id 3 | task 24 | total time = 1421.45 ms / 183 tokens 0.37.007.901 I slot print_timing: id 3 | task 24 | graphs reused = 1 0.37.007.901 I slot print_timing: id 3 | task 24 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.007.909 I slot release: id 3 | task 24 | stop processing: n_tokens = 182, truncated = 0 0.37.013.039 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 0.37.023.557 I slot launch_slot_: id 0 | task 29 | processing task, is_child = 0 0.37.045.761 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 0.37.047.228 I slot launch_slot_: id 1 | task 28 | processing task, is_child = 0 0.37.047.271 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 0.37.047.307 I slot launch_slot_: id 2 | task 30 | processing task, is_child = 0 0.37.047.326 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 0.37.047.361 I slot launch_slot_: id 3 | task 31 | processing task, is_child = 0 0.38.437.908 I slot print_timing: id 0 | task 29 | prompt eval time = 1337.62 ms / 131 tokens ( 10.21 ms per token, 97.94 tokens per second) 0.38.437.911 I slot print_timing: id 0 | task 29 | eval time = 52.91 ms / 2 tokens ( 52.91 ms per token, 18.90 tokens per second) 0.38.437.911 I slot print_timing: id 0 | task 29 | total time = 1390.53 ms / 133 tokens 0.38.437.912 I slot print_timing: id 0 | task 29 | graphs reused = 1 0.38.437.912 I slot print_timing: id 0 | task 29 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.437.932 I slot release: id 0 | task 29 | stop processing: n_tokens = 132, truncated = 0 0.38.438.091 I slot print_timing: id 1 | task 28 | prompt eval time = 1337.77 ms / 122 tokens ( 10.97 ms per token, 91.20 tokens per second) 0.38.438.093 I slot print_timing: id 1 | task 28 | eval time = 52.95 ms / 2 tokens ( 52.95 ms per token, 18.89 tokens per second) 0.38.438.094 I slot print_timing: id 1 | task 28 | total time = 1390.71 ms / 124 tokens 0.38.438.094 I slot print_timing: id 1 | task 28 | graphs reused = 1 0.38.438.094 I slot print_timing: id 1 | task 28 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.438.104 I slot release: id 1 | task 28 | stop processing: n_tokens = 123, truncated = 0 0.38.438.283 I slot print_timing: id 2 | task 30 | prompt eval time = 1337.93 ms / 144 tokens ( 9.29 ms per token, 107.63 tokens per second) 0.38.438.285 I slot print_timing: id 2 | task 30 | eval time = 52.96 ms / 2 tokens ( 52.96 ms per token, 18.88 tokens per second) 0.38.438.286 I slot print_timing: id 2 | task 30 | total time = 1390.89 ms / 146 tokens 0.38.438.286 I slot print_timing: id 2 | task 30 | graphs reused = 1 0.38.438.286 I slot print_timing: id 2 | task 30 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.438.300 I slot release: id 2 | task 30 | stop processing: n_tokens = 145, truncated = 0 0.38.438.473 I slot print_timing: id 3 | task 31 | prompt eval time = 1338.09 ms / 178 tokens ( 7.52 ms per token, 133.03 tokens per second) 0.38.438.475 I slot print_timing: id 3 | task 31 | eval time = 52.98 ms / 2 tokens ( 52.98 ms per token, 18.87 tokens per second) 0.38.438.475 I slot print_timing: id 3 | task 31 | total time = 1391.07 ms / 180 tokens 0.38.438.475 I slot print_timing: id 3 | task 31 | graphs reused = 1 0.38.438.475 I slot print_timing: id 3 | task 31 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.438.484 I slot release: id 3 | task 31 | stop processing: n_tokens = 179, truncated = 0 0.38.443.450 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.248 (> 0.100 thold), f_keep = 0.212 0.38.449.824 I slot launch_slot_: id 0 | task 35 | processing task, is_child = 0 0.38.476.829 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.197 (> 0.100 thold), f_keep = 0.228 0.38.476.878 I slot launch_slot_: id 1 | task 36 | processing task, is_child = 0 0.38.476.911 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.233 (> 0.100 thold), f_keep = 0.193 0.38.476.940 I slot launch_slot_: id 2 | task 37 | processing task, is_child = 0 0.38.476.959 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 0.38.476.992 I slot launch_slot_: id 3 | task 38 | processing task, is_child = 0 0.39.845.164 I slot print_timing: id 0 | task 35 | prompt eval time = 1315.34 ms / 113 tokens ( 11.64 ms per token, 85.91 tokens per second) 0.39.845.166 I slot print_timing: id 0 | task 35 | eval time = 52.82 ms / 2 tokens ( 52.82 ms per token, 18.93 tokens per second) 0.39.845.166 I slot print_timing: id 0 | task 35 | total time = 1368.16 ms / 115 tokens 0.39.845.167 I slot print_timing: id 0 | task 35 | graphs reused = 1 0.39.845.167 I slot print_timing: id 0 | task 35 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.845.186 I slot release: id 0 | task 35 | stop processing: n_tokens = 114, truncated = 0 0.39.845.336 I slot print_timing: id 1 | task 36 | prompt eval time = 1315.49 ms / 142 tokens ( 9.26 ms per token, 107.94 tokens per second) 0.39.845.338 I slot print_timing: id 1 | task 36 | eval time = 52.84 ms / 2 tokens ( 52.84 ms per token, 18.93 tokens per second) 0.39.845.339 I slot print_timing: id 1 | task 36 | total time = 1368.32 ms / 144 tokens 0.39.845.339 I slot print_timing: id 1 | task 36 | graphs reused = 1 0.39.845.339 I slot print_timing: id 1 | task 36 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.845.352 I slot release: id 1 | task 36 | stop processing: n_tokens = 143, truncated = 0 0.39.845.517 I slot print_timing: id 2 | task 37 | prompt eval time = 1315.63 ms / 120 tokens ( 10.96 ms per token, 91.21 tokens per second) 0.39.845.519 I slot print_timing: id 2 | task 37 | eval time = 52.85 ms / 2 tokens ( 52.85 ms per token, 18.92 tokens per second) 0.39.845.519 I slot print_timing: id 2 | task 37 | total time = 1368.48 ms / 122 tokens 0.39.845.519 I slot print_timing: id 2 | task 37 | graphs reused = 1 0.39.845.519 I slot print_timing: id 2 | task 37 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.845.530 I slot release: id 2 | task 37 | stop processing: n_tokens = 121, truncated = 0 0.39.845.698 I slot print_timing: id 3 | task 38 | prompt eval time = 1315.79 ms / 144 tokens ( 9.14 ms per token, 109.44 tokens per second) 0.39.845.700 I slot print_timing: id 3 | task 38 | eval time = 52.87 ms / 2 tokens ( 52.87 ms per token, 18.92 tokens per second) 0.39.845.700 I slot print_timing: id 3 | task 38 | total time = 1368.65 ms / 146 tokens 0.39.845.701 I slot print_timing: id 3 | task 38 | graphs reused = 1 0.39.845.701 I slot print_timing: id 3 | task 38 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.845.709 I slot release: id 3 | task 38 | stop processing: n_tokens = 145, truncated = 0 0.39.850.873 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.257 (> 0.100 thold), f_keep = 0.246 0.39.861.398 I slot launch_slot_: id 0 | task 43 | processing task, is_child = 0 0.39.892.500 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.259 (> 0.100 thold), f_keep = 0.240 0.39.892.558 I slot launch_slot_: id 2 | task 42 | processing task, is_child = 0 0.39.892.595 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.196 (> 0.100 thold), f_keep = 0.196 0.39.892.630 I slot launch_slot_: id 1 | task 44 | processing task, is_child = 0 0.39.892.654 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.193 0.39.892.689 I slot launch_slot_: id 3 | task 45 | processing task, is_child = 0 0.41.141.837 I slot print_timing: id 0 | task 43 | prompt eval time = 1196.08 ms / 109 tokens ( 10.97 ms per token, 91.13 tokens per second) 0.41.141.838 I slot print_timing: id 0 | task 43 | eval time = 53.06 ms / 2 tokens ( 53.06 ms per token, 18.85 tokens per second) 0.41.141.839 I slot print_timing: id 0 | task 43 | total time = 1249.14 ms / 111 tokens 0.41.141.839 I slot print_timing: id 0 | task 43 | graphs reused = 1 0.41.141.840 I slot print_timing: id 0 | task 43 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.141.860 I slot release: id 0 | task 43 | stop processing: n_tokens = 110, truncated = 0 0.41.142.016 I slot print_timing: id 1 | task 44 | prompt eval time = 1196.25 ms / 143 tokens ( 8.37 ms per token, 119.54 tokens per second) 0.41.142.018 I slot print_timing: id 1 | task 44 | eval time = 53.05 ms / 2 tokens ( 53.05 ms per token, 18.85 tokens per second) 0.41.142.018 I slot print_timing: id 1 | task 44 | total time = 1249.30 ms / 145 tokens 0.41.142.018 I slot print_timing: id 1 | task 44 | graphs reused = 1 0.41.142.019 I slot print_timing: id 1 | task 44 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.142.030 I slot release: id 1 | task 44 | stop processing: n_tokens = 144, truncated = 0 0.41.142.199 I slot print_timing: id 2 | task 42 | prompt eval time = 1196.43 ms / 112 tokens ( 10.68 ms per token, 93.61 tokens per second) 0.41.142.202 I slot print_timing: id 2 | task 42 | eval time = 53.04 ms / 2 tokens ( 53.04 ms per token, 18.85 tokens per second) 0.41.142.202 I slot print_timing: id 2 | task 42 | total time = 1249.47 ms / 114 tokens 0.41.142.203 I slot print_timing: id 2 | task 42 | graphs reused = 1 0.41.142.203 I slot print_timing: id 2 | task 42 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.142.212 I slot release: id 2 | task 42 | stop processing: n_tokens = 113, truncated = 0 0.41.142.371 I slot print_timing: id 3 | task 45 | prompt eval time = 1196.62 ms / 123 tokens ( 9.73 ms per token, 102.79 tokens per second) 0.41.142.374 I slot print_timing: id 3 | task 45 | eval time = 53.00 ms / 2 tokens ( 53.00 ms per token, 18.87 tokens per second) 0.41.142.374 I slot print_timing: id 3 | task 45 | total time = 1249.63 ms / 125 tokens 0.41.142.374 I slot print_timing: id 3 | task 45 | graphs reused = 1 0.41.142.374 I slot print_timing: id 3 | task 45 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.142.384 I slot release: id 3 | task 45 | stop processing: n_tokens = 124, truncated = 0 0.41.147.112 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 0.41.157.241 I slot launch_slot_: id 0 | task 49 | processing task, is_child = 0 0.41.187.232 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.259 (> 0.100 thold), f_keep = 0.257 0.41.187.277 I slot launch_slot_: id 2 | task 50 | processing task, is_child = 0 0.41.187.315 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 0.41.188.764 I slot launch_slot_: id 1 | task 51 | processing task, is_child = 0 0.41.188.790 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.206 (> 0.100 thold), f_keep = 0.226 0.41.188.823 I slot launch_slot_: id 3 | task 52 | processing task, is_child = 0 0.42.536.479 I slot print_timing: id 0 | task 49 | prompt eval time = 1294.69 ms / 102 tokens ( 12.69 ms per token, 78.78 tokens per second) 0.42.536.483 I slot print_timing: id 0 | task 49 | eval time = 52.96 ms / 2 tokens ( 52.96 ms per token, 18.88 tokens per second) 0.42.536.483 I slot print_timing: id 0 | task 49 | total time = 1347.65 ms / 104 tokens 0.42.536.483 I slot print_timing: id 0 | task 49 | graphs reused = 1 0.42.536.484 I slot print_timing: id 0 | task 49 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.536.501 I slot release: id 0 | task 49 | stop processing: n_tokens = 103, truncated = 0 0.42.536.655 I slot print_timing: id 1 | task 51 | prompt eval time = 1294.87 ms / 129 tokens ( 10.04 ms per token, 99.62 tokens per second) 0.42.536.658 I slot print_timing: id 1 | task 51 | eval time = 52.95 ms / 2 tokens ( 52.95 ms per token, 18.89 tokens per second) 0.42.536.658 I slot print_timing: id 1 | task 51 | total time = 1347.82 ms / 131 tokens 0.42.536.658 I slot print_timing: id 1 | task 51 | graphs reused = 1 0.42.536.659 I slot print_timing: id 1 | task 51 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.536.671 I slot release: id 1 | task 51 | stop processing: n_tokens = 130, truncated = 0 0.42.536.849 I slot print_timing: id 2 | task 50 | prompt eval time = 1295.06 ms / 112 tokens ( 11.56 ms per token, 86.48 tokens per second) 0.42.536.851 I slot print_timing: id 2 | task 50 | eval time = 52.94 ms / 2 tokens ( 52.94 ms per token, 18.89 tokens per second) 0.42.536.851 I slot print_timing: id 2 | task 50 | total time = 1348.00 ms / 114 tokens 0.42.536.852 I slot print_timing: id 2 | task 50 | graphs reused = 1 0.42.536.852 I slot print_timing: id 2 | task 50 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.536.860 I slot release: id 2 | task 50 | stop processing: n_tokens = 113, truncated = 0 0.42.537.050 I slot print_timing: id 3 | task 52 | prompt eval time = 1295.27 ms / 136 tokens ( 9.52 ms per token, 105.00 tokens per second) 0.42.537.052 I slot print_timing: id 3 | task 52 | eval time = 52.93 ms / 2 tokens ( 52.93 ms per token, 18.89 tokens per second) 0.42.537.052 I slot print_timing: id 3 | task 52 | total time = 1348.19 ms / 138 tokens 0.42.537.052 I slot print_timing: id 3 | task 52 | graphs reused = 1 0.42.537.053 I slot print_timing: id 3 | task 52 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.537.060 I slot release: id 3 | task 52 | stop processing: n_tokens = 137, truncated = 0 0.42.542.135 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.212 (> 0.100 thold), f_keep = 0.272 0.42.545.540 I slot launch_slot_: id 0 | task 56 | processing task, is_child = 0 0.42.575.667 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 0.42.575.714 I slot launch_slot_: id 1 | task 57 | processing task, is_child = 0 0.42.575.747 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.169 (> 0.100 thold), f_keep = 0.248 0.42.575.777 I slot launch_slot_: id 2 | task 58 | processing task, is_child = 0 0.42.575.795 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.158 (> 0.100 thold), f_keep = 0.204 0.42.575.827 I slot launch_slot_: id 3 | task 59 | processing task, is_child = 0 0.44.056.581 I slot print_timing: id 0 | task 56 | prompt eval time = 1427.89 ms / 132 tokens ( 10.82 ms per token, 92.44 tokens per second) 0.44.056.583 I slot print_timing: id 0 | task 56 | eval time = 52.85 ms / 2 tokens ( 52.85 ms per token, 18.92 tokens per second) 0.44.056.585 I slot print_timing: id 0 | task 56 | total time = 1480.75 ms / 134 tokens 0.44.056.585 I slot print_timing: id 0 | task 56 | graphs reused = 1 0.44.056.585 I slot print_timing: id 0 | task 56 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.056.604 I slot release: id 0 | task 56 | stop processing: n_tokens = 133, truncated = 0 0.44.056.760 I slot print_timing: id 1 | task 57 | prompt eval time = 1428.08 ms / 182 tokens ( 7.85 ms per token, 127.44 tokens per second) 0.44.056.764 I slot print_timing: id 1 | task 57 | eval time = 52.83 ms / 2 tokens ( 52.83 ms per token, 18.93 tokens per second) 0.44.056.765 I slot print_timing: id 1 | task 57 | total time = 1480.91 ms / 184 tokens 0.44.056.765 I slot print_timing: id 1 | task 57 | graphs reused = 1 0.44.056.765 I slot print_timing: id 1 | task 57 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.056.780 I slot release: id 1 | task 57 | stop processing: n_tokens = 183, truncated = 0 0.44.056.950 I slot print_timing: id 2 | task 58 | prompt eval time = 1428.28 ms / 166 tokens ( 8.60 ms per token, 116.22 tokens per second) 0.44.056.952 I slot print_timing: id 2 | task 58 | eval time = 52.82 ms / 2 tokens ( 52.82 ms per token, 18.93 tokens per second) 0.44.056.953 I slot print_timing: id 2 | task 58 | total time = 1481.09 ms / 168 tokens 0.44.056.953 I slot print_timing: id 2 | task 58 | graphs reused = 1 0.44.056.953 I slot print_timing: id 2 | task 58 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.056.964 I slot release: id 2 | task 58 | stop processing: n_tokens = 167, truncated = 0 0.44.057.127 I slot print_timing: id 3 | task 59 | prompt eval time = 1428.48 ms / 177 tokens ( 8.07 ms per token, 123.91 tokens per second) 0.44.057.130 I slot print_timing: id 3 | task 59 | eval time = 52.77 ms / 2 tokens ( 52.77 ms per token, 18.95 tokens per second) 0.44.057.130 I slot print_timing: id 3 | task 59 | total time = 1481.26 ms / 179 tokens 0.44.057.130 I slot print_timing: id 3 | task 59 | graphs reused = 1 0.44.057.130 I slot print_timing: id 3 | task 59 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.057.139 I slot release: id 3 | task 59 | stop processing: n_tokens = 178, truncated = 0 0.44.062.191 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.211 0.44.072.719 I slot launch_slot_: id 0 | task 63 | processing task, is_child = 0 0.44.103.366 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.166 (> 0.100 thold), f_keep = 0.153 0.44.103.432 I slot launch_slot_: id 1 | task 64 | processing task, is_child = 0 0.44.103.470 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.200 (> 0.100 thold), f_keep = 0.168 0.44.104.956 I slot launch_slot_: id 2 | task 65 | processing task, is_child = 0 0.44.104.986 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.157 0.44.105.026 I slot launch_slot_: id 3 | task 66 | processing task, is_child = 0 0.45.532.316 I slot print_timing: id 0 | task 63 | prompt eval time = 1374.26 ms / 123 tokens ( 11.17 ms per token, 89.50 tokens per second) 0.45.532.321 I slot print_timing: id 0 | task 63 | eval time = 53.02 ms / 2 tokens ( 53.02 ms per token, 18.86 tokens per second) 0.45.532.322 I slot print_timing: id 0 | task 63 | total time = 1427.28 ms / 125 tokens 0.45.532.322 I slot print_timing: id 0 | task 63 | graphs reused = 1 0.45.532.323 I slot print_timing: id 0 | task 63 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.532.341 I slot release: id 0 | task 63 | stop processing: n_tokens = 124, truncated = 0 0.45.532.500 I slot print_timing: id 1 | task 64 | prompt eval time = 1374.44 ms / 169 tokens ( 8.13 ms per token, 122.96 tokens per second) 0.45.532.502 I slot print_timing: id 1 | task 64 | eval time = 53.01 ms / 2 tokens ( 53.01 ms per token, 18.86 tokens per second) 0.45.532.502 I slot print_timing: id 1 | task 64 | total time = 1427.45 ms / 171 tokens 0.45.532.503 I slot print_timing: id 1 | task 64 | graphs reused = 1 0.45.532.503 I slot print_timing: id 1 | task 64 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.532.520 I slot release: id 1 | task 64 | stop processing: n_tokens = 170, truncated = 0 0.45.532.684 I slot print_timing: id 2 | task 65 | prompt eval time = 1374.62 ms / 140 tokens ( 9.82 ms per token, 101.85 tokens per second) 0.45.532.685 I slot print_timing: id 2 | task 65 | eval time = 52.99 ms / 2 tokens ( 52.99 ms per token, 18.87 tokens per second) 0.45.532.686 I slot print_timing: id 2 | task 65 | total time = 1427.62 ms / 142 tokens 0.45.532.686 I slot print_timing: id 2 | task 65 | graphs reused = 1 0.45.532.686 I slot print_timing: id 2 | task 65 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.532.697 I slot release: id 2 | task 65 | stop processing: n_tokens = 141, truncated = 0 0.45.532.857 I slot print_timing: id 3 | task 66 | prompt eval time = 1374.82 ms / 149 tokens ( 9.23 ms per token, 108.38 tokens per second) 0.45.532.859 I slot print_timing: id 3 | task 66 | eval time = 52.96 ms / 2 tokens ( 52.96 ms per token, 18.88 tokens per second) 0.45.532.859 I slot print_timing: id 3 | task 66 | total time = 1427.78 ms / 151 tokens 0.45.532.859 I slot print_timing: id 3 | task 66 | graphs reused = 1 0.45.532.860 I slot print_timing: id 3 | task 66 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.532.868 I slot release: id 3 | task 66 | stop processing: n_tokens = 150, truncated = 0 0.45.538.109 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 0.45.545.494 I slot launch_slot_: id 2 | task 70 | processing task, is_child = 0 0.45.572.990 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 0.45.573.039 I slot launch_slot_: id 0 | task 71 | processing task, is_child = 0 0.45.573.072 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.172 (> 0.100 thold), f_keep = 0.165 0.45.573.105 I slot launch_slot_: id 1 | task 72 | processing task, is_child = 0 0.45.573.121 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.174 (> 0.100 thold), f_keep = 0.187 0.45.573.155 I slot launch_slot_: id 3 | task 73 | processing task, is_child = 0 0.47.024.739 I slot print_timing: id 0 | task 71 | prompt eval time = 1398.56 ms / 128 tokens ( 10.93 ms per token, 91.52 tokens per second) 0.47.024.742 I slot print_timing: id 0 | task 71 | eval time = 53.01 ms / 2 tokens ( 53.01 ms per token, 18.86 tokens per second) 0.47.024.743 I slot print_timing: id 0 | task 71 | total time = 1451.58 ms / 130 tokens 0.47.024.744 I slot print_timing: id 0 | task 71 | graphs reused = 1 0.47.024.744 I slot print_timing: id 0 | task 71 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.024.767 I slot release: id 0 | task 71 | stop processing: n_tokens = 129, truncated = 0 0.47.024.922 I slot print_timing: id 1 | task 72 | prompt eval time = 1398.75 ms / 163 tokens ( 8.58 ms per token, 116.53 tokens per second) 0.47.024.925 I slot print_timing: id 1 | task 72 | eval time = 52.99 ms / 2 tokens ( 52.99 ms per token, 18.87 tokens per second) 0.47.024.925 I slot print_timing: id 1 | task 72 | total time = 1451.75 ms / 165 tokens 0.47.024.925 I slot print_timing: id 1 | task 72 | graphs reused = 1 0.47.024.926 I slot print_timing: id 1 | task 72 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.024.939 I slot release: id 1 | task 72 | stop processing: n_tokens = 164, truncated = 0 0.47.025.111 I slot print_timing: id 2 | task 70 | prompt eval time = 1398.95 ms / 111 tokens ( 12.60 ms per token, 79.35 tokens per second) 0.47.025.113 I slot print_timing: id 2 | task 70 | eval time = 52.97 ms / 2 tokens ( 52.97 ms per token, 18.88 tokens per second) 0.47.025.113 I slot print_timing: id 2 | task 70 | total time = 1451.92 ms / 113 tokens 0.47.025.114 I slot print_timing: id 2 | task 70 | graphs reused = 1 0.47.025.114 I slot print_timing: id 2 | task 70 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.025.122 I slot release: id 2 | task 70 | stop processing: n_tokens = 112, truncated = 0 0.47.025.304 I slot print_timing: id 3 | task 73 | prompt eval time = 1399.16 ms / 161 tokens ( 8.69 ms per token, 115.07 tokens per second) 0.47.025.306 I slot print_timing: id 3 | task 73 | eval time = 52.95 ms / 2 tokens ( 52.95 ms per token, 18.89 tokens per second) 0.47.025.307 I slot print_timing: id 3 | task 73 | total time = 1452.10 ms / 163 tokens 0.47.025.307 I slot print_timing: id 3 | task 73 | graphs reused = 1 0.47.025.307 I slot print_timing: id 3 | task 73 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.025.316 I slot release: id 3 | task 73 | stop processing: n_tokens = 162, truncated = 0 0.47.030.368 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 0.47.041.016 I slot launch_slot_: id 1 | task 77 | processing task, is_child = 0 0.47.071.479 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 0.47.071.535 I slot launch_slot_: id 0 | task 78 | processing task, is_child = 0 0.47.071.569 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 0.47.071.602 I slot launch_slot_: id 2 | task 79 | processing task, is_child = 0 0.47.071.621 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 0.47.071.653 I slot launch_slot_: id 3 | task 80 | processing task, is_child = 0 0.48.333.151 I slot print_timing: id 0 | task 78 | prompt eval time = 1208.08 ms / 112 tokens ( 10.79 ms per token, 92.71 tokens per second) 0.48.333.153 I slot print_timing: id 0 | task 78 | eval time = 53.41 ms / 2 tokens ( 53.41 ms per token, 18.72 tokens per second) 0.48.333.155 I slot print_timing: id 0 | task 78 | total time = 1261.49 ms / 114 tokens 0.48.333.155 I slot print_timing: id 0 | task 78 | graphs reused = 1 0.48.333.155 I slot print_timing: id 0 | task 78 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.333.174 I slot release: id 0 | task 78 | stop processing: n_tokens = 113, truncated = 0 0.48.333.339 I slot print_timing: id 1 | task 77 | prompt eval time = 1208.26 ms / 109 tokens ( 11.08 ms per token, 90.21 tokens per second) 0.48.333.341 I slot print_timing: id 1 | task 77 | eval time = 53.41 ms / 2 tokens ( 53.41 ms per token, 18.72 tokens per second) 0.48.333.342 I slot print_timing: id 1 | task 77 | total time = 1261.67 ms / 111 tokens 0.48.333.342 I slot print_timing: id 1 | task 77 | graphs reused = 1 0.48.333.342 I slot print_timing: id 1 | task 77 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.333.353 I slot release: id 1 | task 77 | stop processing: n_tokens = 110, truncated = 0 0.48.333.518 I slot print_timing: id 2 | task 79 | prompt eval time = 1208.46 ms / 167 tokens ( 7.24 ms per token, 138.19 tokens per second) 0.48.333.520 I slot print_timing: id 2 | task 79 | eval time = 53.37 ms / 2 tokens ( 53.37 ms per token, 18.74 tokens per second) 0.48.333.520 I slot print_timing: id 2 | task 79 | total time = 1261.83 ms / 169 tokens 0.48.333.520 I slot print_timing: id 2 | task 79 | graphs reused = 1 0.48.333.520 I slot print_timing: id 2 | task 79 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.333.532 I slot release: id 2 | task 79 | stop processing: n_tokens = 168, truncated = 0 0.48.333.713 I slot print_timing: id 3 | task 80 | prompt eval time = 1208.67 ms / 164 tokens ( 7.37 ms per token, 135.69 tokens per second) 0.48.333.715 I slot print_timing: id 3 | task 80 | eval time = 53.34 ms / 2 tokens ( 53.34 ms per token, 18.75 tokens per second) 0.48.333.715 I slot print_timing: id 3 | task 80 | total time = 1262.01 ms / 166 tokens 0.48.333.715 I slot print_timing: id 3 | task 80 | graphs reused = 1 0.48.333.716 I slot print_timing: id 3 | task 80 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.333.728 I slot release: id 3 | task 80 | stop processing: n_tokens = 165, truncated = 0 0.48.339.173 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 0.48.351.768 I slot launch_slot_: id 0 | task 85 | processing task, is_child = 0 0.48.375.345 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 0.48.375.394 I slot launch_slot_: id 1 | task 84 | processing task, is_child = 0 0.48.375.427 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 0.48.375.459 I slot launch_slot_: id 2 | task 86 | processing task, is_child = 0 0.48.375.479 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 0.48.375.512 I slot launch_slot_: id 3 | task 87 | processing task, is_child = 0 0.49.627.211 I slot print_timing: id 0 | task 85 | prompt eval time = 1198.62 ms / 122 tokens ( 9.82 ms per token, 101.78 tokens per second) 0.49.627.217 I slot print_timing: id 0 | task 85 | eval time = 53.07 ms / 2 tokens ( 53.07 ms per token, 18.84 tokens per second) 0.49.627.217 I slot print_timing: id 0 | task 85 | total time = 1251.69 ms / 124 tokens 0.49.627.218 I slot print_timing: id 0 | task 85 | graphs reused = 1 0.49.627.218 I slot print_timing: id 0 | task 85 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.627.244 I slot release: id 0 | task 85 | stop processing: n_tokens = 123, truncated = 0 0.49.627.396 I slot print_timing: id 1 | task 84 | prompt eval time = 1198.82 ms / 147 tokens ( 8.16 ms per token, 122.62 tokens per second) 0.49.627.399 I slot print_timing: id 1 | task 84 | eval time = 53.05 ms / 2 tokens ( 53.05 ms per token, 18.85 tokens per second) 0.49.627.400 I slot print_timing: id 1 | task 84 | total time = 1251.87 ms / 149 tokens 0.49.627.400 I slot print_timing: id 1 | task 84 | graphs reused = 1 0.49.627.400 I slot print_timing: id 1 | task 84 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.627.411 I slot release: id 1 | task 84 | stop processing: n_tokens = 148, truncated = 0 0.49.627.582 I slot print_timing: id 2 | task 86 | prompt eval time = 1199.01 ms / 131 tokens ( 9.15 ms per token, 109.26 tokens per second) 0.49.627.587 I slot print_timing: id 2 | task 86 | eval time = 53.04 ms / 2 tokens ( 53.04 ms per token, 18.85 tokens per second) 0.49.627.587 I slot print_timing: id 2 | task 86 | total time = 1252.04 ms / 133 tokens 0.49.627.588 I slot print_timing: id 2 | task 86 | graphs reused = 1 0.49.627.588 I slot print_timing: id 2 | task 86 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.627.597 I slot release: id 2 | task 86 | stop processing: n_tokens = 132, truncated = 0 0.49.627.764 I slot print_timing: id 3 | task 87 | prompt eval time = 1199.19 ms / 120 tokens ( 9.99 ms per token, 100.07 tokens per second) 0.49.627.769 I slot print_timing: id 3 | task 87 | eval time = 53.01 ms / 2 tokens ( 53.01 ms per token, 18.86 tokens per second) 0.49.627.769 I slot print_timing: id 3 | task 87 | total time = 1252.21 ms / 122 tokens 0.49.627.770 I slot print_timing: id 3 | task 87 | graphs reused = 1 0.49.627.770 I slot print_timing: id 3 | task 87 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.627.778 I slot release: id 3 | task 87 | stop processing: n_tokens = 121, truncated = 0 0.49.633.042 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 0.49.643.416 I slot launch_slot_: id 0 | task 91 | processing task, is_child = 0 0.49.673.327 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 0.49.673.376 I slot launch_slot_: id 1 | task 92 | processing task, is_child = 0 0.49.673.407 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.212 0.49.674.842 I slot launch_slot_: id 2 | task 93 | processing task, is_child = 0 0.49.674.861 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.194 (> 0.100 thold), f_keep = 0.231 0.49.674.896 I slot launch_slot_: id 3 | task 94 | processing task, is_child = 0 0.50.889.678 I slot print_timing: id 0 | task 91 | prompt eval time = 1161.60 ms / 131 tokens ( 8.87 ms per token, 112.78 tokens per second) 0.50.889.680 I slot print_timing: id 0 | task 91 | eval time = 53.17 ms / 2 tokens ( 53.17 ms per token, 18.81 tokens per second) 0.50.889.681 I slot print_timing: id 0 | task 91 | total time = 1214.77 ms / 133 tokens 0.50.889.681 I slot print_timing: id 0 | task 91 | graphs reused = 1 0.50.889.682 I slot print_timing: id 0 | task 91 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.889.700 I slot release: id 0 | task 91 | stop processing: n_tokens = 132, truncated = 0 0.50.889.850 I slot print_timing: id 1 | task 92 | prompt eval time = 1161.78 ms / 124 tokens ( 9.37 ms per token, 106.73 tokens per second) 0.50.889.852 I slot print_timing: id 1 | task 92 | eval time = 53.15 ms / 2 tokens ( 53.15 ms per token, 18.81 tokens per second) 0.50.889.853 I slot print_timing: id 1 | task 92 | total time = 1214.93 ms / 126 tokens 0.50.889.853 I slot print_timing: id 1 | task 92 | graphs reused = 1 0.50.889.854 I slot print_timing: id 1 | task 92 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.889.865 I slot release: id 1 | task 92 | stop processing: n_tokens = 125, truncated = 0 0.50.890.025 I slot print_timing: id 2 | task 93 | prompt eval time = 1161.97 ms / 141 tokens ( 8.24 ms per token, 121.35 tokens per second) 0.50.890.027 I slot print_timing: id 2 | task 93 | eval time = 53.13 ms / 2 tokens ( 53.13 ms per token, 18.82 tokens per second) 0.50.890.027 I slot print_timing: id 2 | task 93 | total time = 1215.10 ms / 143 tokens 0.50.890.028 I slot print_timing: id 2 | task 93 | graphs reused = 1 0.50.890.028 I slot print_timing: id 2 | task 93 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.890.038 I slot release: id 2 | task 93 | stop processing: n_tokens = 142, truncated = 0 0.50.890.226 I slot print_timing: id 3 | task 94 | prompt eval time = 1162.17 ms / 144 tokens ( 8.07 ms per token, 123.91 tokens per second) 0.50.890.229 I slot print_timing: id 3 | task 94 | eval time = 53.11 ms / 2 tokens ( 53.11 ms per token, 18.83 tokens per second) 0.50.890.229 I slot print_timing: id 3 | task 94 | total time = 1215.28 ms / 146 tokens 0.50.890.229 I slot print_timing: id 3 | task 94 | graphs reused = 1 0.50.890.229 I slot print_timing: id 3 | task 94 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.890.239 I slot release: id 3 | task 94 | stop processing: n_tokens = 145, truncated = 0 0.50.894.858 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.246 (> 0.100 thold), f_keep = 0.220 0.50.902.266 I slot launch_slot_: id 0 | task 99 | processing task, is_child = 0 0.50.930.086 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.271 (> 0.100 thold), f_keep = 0.200 0.50.930.142 I slot launch_slot_: id 3 | task 98 | processing task, is_child = 0 0.50.930.179 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.169 (> 0.100 thold), f_keep = 0.204 0.50.930.216 I slot launch_slot_: id 2 | task 100 | processing task, is_child = 0 0.50.930.236 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.231 (> 0.100 thold), f_keep = 0.224 0.50.930.277 I slot launch_slot_: id 1 | task 101 | processing task, is_child = 0 0.52.238.686 I slot print_timing: id 0 | task 99 | prompt eval time = 1255.05 ms / 118 tokens ( 10.64 ms per token, 94.02 tokens per second) 0.52.238.688 I slot print_timing: id 0 | task 99 | eval time = 53.35 ms / 2 tokens ( 53.35 ms per token, 18.75 tokens per second) 0.52.238.689 I slot print_timing: id 0 | task 99 | total time = 1308.40 ms / 120 tokens 0.52.238.689 I slot print_timing: id 0 | task 99 | graphs reused = 1 0.52.238.690 I slot print_timing: id 0 | task 99 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.238.708 I slot release: id 0 | task 99 | stop processing: n_tokens = 119, truncated = 0 0.52.238.859 I slot print_timing: id 1 | task 101 | prompt eval time = 1255.23 ms / 121 tokens ( 10.37 ms per token, 96.40 tokens per second) 0.52.238.864 I slot print_timing: id 1 | task 101 | eval time = 53.33 ms / 2 tokens ( 53.33 ms per token, 18.75 tokens per second) 0.52.238.864 I slot print_timing: id 1 | task 101 | total time = 1308.56 ms / 123 tokens 0.52.238.865 I slot print_timing: id 1 | task 101 | graphs reused = 1 0.52.238.865 I slot print_timing: id 1 | task 101 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.238.875 I slot release: id 1 | task 101 | stop processing: n_tokens = 122, truncated = 0 0.52.239.047 I slot print_timing: id 2 | task 100 | prompt eval time = 1255.41 ms / 172 tokens ( 7.30 ms per token, 137.01 tokens per second) 0.52.239.049 I slot print_timing: id 2 | task 100 | eval time = 53.32 ms / 2 tokens ( 53.32 ms per token, 18.75 tokens per second) 0.52.239.050 I slot print_timing: id 2 | task 100 | total time = 1308.73 ms / 174 tokens 0.52.239.050 I slot print_timing: id 2 | task 100 | graphs reused = 1 0.52.239.050 I slot print_timing: id 2 | task 100 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.239.061 I slot release: id 2 | task 100 | stop processing: n_tokens = 173, truncated = 0 0.52.239.216 I slot print_timing: id 3 | task 98 | prompt eval time = 1255.61 ms / 107 tokens ( 11.73 ms per token, 85.22 tokens per second) 0.52.239.218 I slot print_timing: id 3 | task 98 | eval time = 53.28 ms / 2 tokens ( 53.28 ms per token, 18.77 tokens per second) 0.52.239.218 I slot print_timing: id 3 | task 98 | total time = 1308.89 ms / 109 tokens 0.52.239.219 I slot print_timing: id 3 | task 98 | graphs reused = 1 0.52.239.219 I slot print_timing: id 3 | task 98 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.239.227 I slot release: id 3 | task 98 | stop processing: n_tokens = 108, truncated = 0 0.52.244.287 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.250 (> 0.100 thold), f_keep = 0.244 0.52.254.402 I slot launch_slot_: id 0 | task 105 | processing task, is_child = 0 0.52.285.292 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.213 (> 0.100 thold), f_keep = 0.269 0.52.285.348 I slot launch_slot_: id 3 | task 106 | processing task, is_child = 0 0.52.285.385 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.158 (> 0.100 thold), f_keep = 0.230 0.52.285.418 I slot launch_slot_: id 1 | task 107 | processing task, is_child = 0 0.52.285.437 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.117 (> 0.100 thold), f_keep = 0.162 0.52.285.469 I slot launch_slot_: id 2 | task 108 | processing task, is_child = 0 0.53.902.262 I slot print_timing: id 0 | task 105 | prompt eval time = 1563.94 ms / 116 tokens ( 13.48 ms per token, 74.17 tokens per second) 0.53.902.264 I slot print_timing: id 0 | task 105 | eval time = 52.84 ms / 2 tokens ( 52.84 ms per token, 18.93 tokens per second) 0.53.902.265 I slot print_timing: id 0 | task 105 | total time = 1616.78 ms / 118 tokens 0.53.902.265 I slot print_timing: id 0 | task 105 | graphs reused = 1 0.53.902.265 I slot print_timing: id 0 | task 105 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.902.283 I slot release: id 0 | task 105 | stop processing: n_tokens = 117, truncated = 0 0.53.902.450 I slot print_timing: id 1 | task 107 | prompt eval time = 1564.13 ms / 177 tokens ( 8.84 ms per token, 113.16 tokens per second) 0.53.902.455 I slot print_timing: id 1 | task 107 | eval time = 52.84 ms / 2 tokens ( 52.84 ms per token, 18.93 tokens per second) 0.53.902.455 I slot print_timing: id 1 | task 107 | total time = 1616.96 ms / 179 tokens 0.53.902.455 I slot print_timing: id 1 | task 107 | graphs reused = 1 0.53.902.455 I slot print_timing: id 1 | task 107 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.902.468 I slot release: id 1 | task 107 | stop processing: n_tokens = 178, truncated = 0 0.53.902.636 I slot print_timing: id 2 | task 108 | prompt eval time = 1564.31 ms / 240 tokens ( 6.52 ms per token, 153.42 tokens per second) 0.53.902.639 I slot print_timing: id 2 | task 108 | eval time = 52.83 ms / 2 tokens ( 52.83 ms per token, 18.93 tokens per second) 0.53.902.639 I slot print_timing: id 2 | task 108 | total time = 1617.14 ms / 242 tokens 0.53.902.639 I slot print_timing: id 2 | task 108 | graphs reused = 1 0.53.902.640 I slot print_timing: id 2 | task 108 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.902.656 I slot release: id 2 | task 108 | stop processing: n_tokens = 241, truncated = 0 0.53.902.822 I slot print_timing: id 3 | task 106 | prompt eval time = 1564.50 ms / 136 tokens ( 11.50 ms per token, 86.93 tokens per second) 0.53.902.826 I slot print_timing: id 3 | task 106 | eval time = 52.80 ms / 2 tokens ( 52.80 ms per token, 18.94 tokens per second) 0.53.902.826 I slot print_timing: id 3 | task 106 | total time = 1617.31 ms / 138 tokens 0.53.902.827 I slot print_timing: id 3 | task 106 | graphs reused = 1 0.53.902.827 I slot print_timing: id 3 | task 106 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.902.838 I slot release: id 3 | task 106 | stop processing: n_tokens = 137, truncated = 0 0.53.907.657 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.239 0.53.917.991 I slot launch_slot_: id 0 | task 112 | processing task, is_child = 0 0.53.949.332 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.204 (> 0.100 thold), f_keep = 0.212 0.53.950.816 I slot launch_slot_: id 3 | task 113 | processing task, is_child = 0 0.53.950.860 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.181 (> 0.100 thold), f_keep = 0.157 0.53.952.356 I slot launch_slot_: id 1 | task 114 | processing task, is_child = 0 0.53.952.381 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.124 (> 0.100 thold), f_keep = 0.116 0.53.952.418 I slot launch_slot_: id 2 | task 115 | processing task, is_child = 0 0.55.639.162 I slot print_timing: id 0 | task 112 | prompt eval time = 1633.46 ms / 160 tokens ( 10.21 ms per token, 97.95 tokens per second) 0.55.639.164 I slot print_timing: id 0 | task 112 | eval time = 53.28 ms / 2 tokens ( 53.28 ms per token, 18.77 tokens per second) 0.55.639.165 I slot print_timing: id 0 | task 112 | total time = 1686.73 ms / 162 tokens 0.55.639.165 I slot print_timing: id 0 | task 112 | graphs reused = 1 0.55.639.166 I slot print_timing: id 0 | task 112 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.639.186 I slot release: id 0 | task 112 | stop processing: n_tokens = 161, truncated = 0 0.55.639.345 I slot print_timing: id 1 | task 114 | prompt eval time = 1633.63 ms / 155 tokens ( 10.54 ms per token, 94.88 tokens per second) 0.55.639.348 I slot print_timing: id 1 | task 114 | eval time = 53.28 ms / 2 tokens ( 53.28 ms per token, 18.77 tokens per second) 0.55.639.348 I slot print_timing: id 1 | task 114 | total time = 1686.91 ms / 157 tokens 0.55.639.349 I slot print_timing: id 1 | task 114 | graphs reused = 1 0.55.639.349 I slot print_timing: id 1 | task 114 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.639.360 I slot release: id 1 | task 114 | stop processing: n_tokens = 156, truncated = 0 0.55.639.536 I slot print_timing: id 2 | task 115 | prompt eval time = 1633.82 ms / 226 tokens ( 7.23 ms per token, 138.33 tokens per second) 0.55.639.538 I slot print_timing: id 2 | task 115 | eval time = 53.27 ms / 2 tokens ( 53.27 ms per token, 18.77 tokens per second) 0.55.639.539 I slot print_timing: id 2 | task 115 | total time = 1687.09 ms / 228 tokens 0.55.639.539 I slot print_timing: id 2 | task 115 | graphs reused = 1 0.55.639.539 I slot print_timing: id 2 | task 115 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.639.563 I slot release: id 2 | task 115 | stop processing: n_tokens = 227, truncated = 0 0.55.639.726 I slot print_timing: id 3 | task 113 | prompt eval time = 1634.02 ms / 142 tokens ( 11.51 ms per token, 86.90 tokens per second) 0.55.639.728 I slot print_timing: id 3 | task 113 | eval time = 53.25 ms / 2 tokens ( 53.25 ms per token, 18.78 tokens per second) 0.55.639.729 I slot print_timing: id 3 | task 113 | total time = 1687.27 ms / 144 tokens 0.55.639.729 I slot print_timing: id 3 | task 113 | graphs reused = 1 0.55.639.729 I slot print_timing: id 3 | task 113 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.639.739 I slot release: id 3 | task 113 | stop processing: n_tokens = 143, truncated = 0 0.55.644.485 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.295 (> 0.100 thold), f_keep = 0.217 0.55.651.614 I slot launch_slot_: id 3 | task 119 | processing task, is_child = 0 0.55.673.084 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 0.55.673.136 I slot launch_slot_: id 1 | task 120 | processing task, is_child = 0 0.55.673.172 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 0.55.673.205 I slot launch_slot_: id 0 | task 121 | processing task, is_child = 0 0.55.673.226 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.146 (> 0.100 thold), f_keep = 0.123 0.55.674.697 I slot launch_slot_: id 2 | task 122 | processing task, is_child = 0 0.57.153.879 I slot print_timing: id 0 | task 121 | prompt eval time = 1425.88 ms / 141 tokens ( 10.11 ms per token, 98.89 tokens per second) 0.57.153.882 I slot print_timing: id 0 | task 121 | eval time = 53.29 ms / 2 tokens ( 53.29 ms per token, 18.76 tokens per second) 0.57.153.882 I slot print_timing: id 0 | task 121 | total time = 1479.17 ms / 143 tokens 0.57.153.883 I slot print_timing: id 0 | task 121 | graphs reused = 1 0.57.153.883 I slot print_timing: id 0 | task 121 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.153.906 I slot release: id 0 | task 121 | stop processing: n_tokens = 142, truncated = 0 0.57.154.072 I slot print_timing: id 1 | task 120 | prompt eval time = 1426.06 ms / 114 tokens ( 12.51 ms per token, 79.94 tokens per second) 0.57.154.073 I slot print_timing: id 1 | task 120 | eval time = 53.29 ms / 2 tokens ( 53.29 ms per token, 18.76 tokens per second) 0.57.154.073 I slot print_timing: id 1 | task 120 | total time = 1479.35 ms / 116 tokens 0.57.154.074 I slot print_timing: id 1 | task 120 | graphs reused = 1 0.57.154.074 I slot print_timing: id 1 | task 120 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.154.084 I slot release: id 1 | task 120 | stop processing: n_tokens = 115, truncated = 0 0.57.154.263 I slot print_timing: id 2 | task 122 | prompt eval time = 1426.25 ms / 192 tokens ( 7.43 ms per token, 134.62 tokens per second) 0.57.154.266 I slot print_timing: id 2 | task 122 | eval time = 53.28 ms / 2 tokens ( 53.28 ms per token, 18.77 tokens per second) 0.57.154.266 I slot print_timing: id 2 | task 122 | total time = 1479.53 ms / 194 tokens 0.57.154.267 I slot print_timing: id 2 | task 122 | graphs reused = 1 0.57.154.267 I slot print_timing: id 2 | task 122 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.154.279 I slot release: id 2 | task 122 | stop processing: n_tokens = 193, truncated = 0 0.57.154.470 I slot print_timing: id 3 | task 119 | prompt eval time = 1426.45 ms / 105 tokens ( 13.59 ms per token, 73.61 tokens per second) 0.57.154.471 I slot print_timing: id 3 | task 119 | eval time = 53.27 ms / 2 tokens ( 53.27 ms per token, 18.77 tokens per second) 0.57.154.471 I slot print_timing: id 3 | task 119 | total time = 1479.73 ms / 107 tokens 0.57.154.472 I slot print_timing: id 3 | task 119 | graphs reused = 1 0.57.154.472 I slot print_timing: id 3 | task 119 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.154.482 I slot release: id 3 | task 119 | stop processing: n_tokens = 106, truncated = 0 0.57.159.264 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 0.57.166.374 I slot launch_slot_: id 1 | task 126 | processing task, is_child = 0 0.57.193.864 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 0.57.193.914 I slot launch_slot_: id 0 | task 127 | processing task, is_child = 0 0.57.193.954 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.238 (> 0.100 thold), f_keep = 0.274 0.57.193.993 I slot launch_slot_: id 3 | task 128 | processing task, is_child = 0 0.57.194.013 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.163 (> 0.100 thold), f_keep = 0.145 0.57.194.048 I slot launch_slot_: id 2 | task 129 | processing task, is_child = 0 0.58.629.957 I slot print_timing: id 0 | task 127 | prompt eval time = 1382.73 ms / 135 tokens ( 10.24 ms per token, 97.63 tokens per second) 0.58.629.962 I slot print_timing: id 0 | task 127 | eval time = 53.17 ms / 2 tokens ( 53.17 ms per token, 18.81 tokens per second) 0.58.629.963 I slot print_timing: id 0 | task 127 | total time = 1435.90 ms / 137 tokens 0.58.629.963 I slot print_timing: id 0 | task 127 | graphs reused = 1 0.58.629.964 I slot print_timing: id 0 | task 127 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.629.988 I slot release: id 0 | task 127 | stop processing: n_tokens = 136, truncated = 0 0.58.630.138 I slot print_timing: id 1 | task 126 | prompt eval time = 1382.92 ms / 108 tokens ( 12.80 ms per token, 78.10 tokens per second) 0.58.630.141 I slot print_timing: id 1 | task 126 | eval time = 53.15 ms / 2 tokens ( 53.15 ms per token, 18.81 tokens per second) 0.58.630.142 I slot print_timing: id 1 | task 126 | total time = 1436.07 ms / 110 tokens 0.58.630.142 I slot print_timing: id 1 | task 126 | graphs reused = 1 0.58.630.142 I slot print_timing: id 1 | task 126 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.630.153 I slot release: id 1 | task 126 | stop processing: n_tokens = 109, truncated = 0 0.58.630.323 I slot print_timing: id 2 | task 129 | prompt eval time = 1383.11 ms / 172 tokens ( 8.04 ms per token, 124.36 tokens per second) 0.58.630.327 I slot print_timing: id 2 | task 129 | eval time = 53.13 ms / 2 tokens ( 53.13 ms per token, 18.82 tokens per second) 0.58.630.328 I slot print_timing: id 2 | task 129 | total time = 1436.24 ms / 174 tokens 0.58.630.328 I slot print_timing: id 2 | task 129 | graphs reused = 1 0.58.630.328 I slot print_timing: id 2 | task 129 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.630.342 I slot release: id 2 | task 129 | stop processing: n_tokens = 173, truncated = 0 0.58.630.508 I slot print_timing: id 3 | task 128 | prompt eval time = 1383.30 ms / 122 tokens ( 11.34 ms per token, 88.19 tokens per second) 0.58.630.510 I slot print_timing: id 3 | task 128 | eval time = 53.11 ms / 2 tokens ( 53.11 ms per token, 18.83 tokens per second) 0.58.630.510 I slot print_timing: id 3 | task 128 | total time = 1436.41 ms / 124 tokens 0.58.630.511 I slot print_timing: id 3 | task 128 | graphs reused = 1 0.58.630.511 I slot print_timing: id 3 | task 128 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.630.519 I slot release: id 3 | task 128 | stop processing: n_tokens = 123, truncated = 0 0.58.635.740 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.209 (> 0.100 thold), f_keep = 0.206 0.58.635.767 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.188 MiB) 0.58.643.138 I slot launch_slot_: id 0 | task 133 | processing task, is_child = 0 0.58.643.166 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.895 MiB) 0.58.646.516 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.032 MiB) 0.58.653.832 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.775 MiB) 0.58.657.136 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.207 (> 0.100 thold), f_keep = 0.257 0.58.657.186 I slot launch_slot_: id 1 | task 134 | processing task, is_child = 0 0.58.657.230 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.242 (> 0.100 thold), f_keep = 0.236 0.58.658.901 I slot launch_slot_: id 3 | task 135 | processing task, is_child = 0 0.58.658.928 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.176 (> 0.100 thold), f_keep = 0.162 0.58.658.969 I slot launch_slot_: id 2 | task 136 | processing task, is_child = 0 0.59.986.795 I slot print_timing: id 0 | task 133 | prompt eval time = 1274.63 ms / 134 tokens ( 9.51 ms per token, 105.13 tokens per second) 0.59.986.797 I slot print_timing: id 0 | task 133 | eval time = 53.18 ms / 2 tokens ( 53.18 ms per token, 18.80 tokens per second) 0.59.986.798 I slot print_timing: id 0 | task 133 | total time = 1327.82 ms / 136 tokens 0.59.986.799 I slot print_timing: id 0 | task 133 | graphs reused = 1 0.59.986.799 I slot print_timing: id 0 | task 133 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.986.818 I slot release: id 0 | task 133 | stop processing: n_tokens = 135, truncated = 0 0.59.986.973 I slot print_timing: id 1 | task 134 | prompt eval time = 1274.78 ms / 135 tokens ( 9.44 ms per token, 105.90 tokens per second) 0.59.986.976 I slot print_timing: id 1 | task 134 | eval time = 53.21 ms / 2 tokens ( 53.21 ms per token, 18.79 tokens per second) 0.59.986.976 I slot print_timing: id 1 | task 134 | total time = 1327.98 ms / 137 tokens 0.59.986.976 I slot print_timing: id 1 | task 134 | graphs reused = 1 0.59.986.977 I slot print_timing: id 1 | task 134 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.986.987 I slot release: id 1 | task 134 | stop processing: n_tokens = 136, truncated = 0 0.59.987.158 I slot print_timing: id 2 | task 136 | prompt eval time = 1274.96 ms / 159 tokens ( 8.02 ms per token, 124.71 tokens per second) 0.59.987.163 I slot print_timing: id 2 | task 136 | eval time = 53.20 ms / 2 tokens ( 53.20 ms per token, 18.80 tokens per second) 0.59.987.163 I slot print_timing: id 2 | task 136 | total time = 1328.15 ms / 161 tokens 0.59.987.164 I slot print_timing: id 2 | task 136 | graphs reused = 1 0.59.987.164 I slot print_timing: id 2 | task 136 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.987.176 I slot release: id 2 | task 136 | stop processing: n_tokens = 160, truncated = 0 0.59.987.334 I slot print_timing: id 3 | task 135 | prompt eval time = 1275.15 ms / 120 tokens ( 10.63 ms per token, 94.11 tokens per second) 0.59.987.335 I slot print_timing: id 3 | task 135 | eval time = 53.17 ms / 2 tokens ( 53.17 ms per token, 18.81 tokens per second) 0.59.987.336 I slot print_timing: id 3 | task 135 | total time = 1328.32 ms / 122 tokens 0.59.987.336 I slot print_timing: id 3 | task 135 | graphs reused = 1 0.59.987.336 I slot print_timing: id 3 | task 135 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.987.345 I slot release: id 3 | task 135 | stop processing: n_tokens = 121, truncated = 0 0.59.991.858 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.215 (> 0.100 thold), f_keep = 0.207 0.59.995.296 I slot launch_slot_: id 0 | task 140 | processing task, is_child = 0 0.59.995.324 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.618 MiB) 0.59.998.741 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.557 MiB) 1.00.002.299 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.934 MiB) 1.00.005.755 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.163 (> 0.100 thold), f_keep = 0.206 1.00.005.799 I slot launch_slot_: id 1 | task 141 | processing task, is_child = 0 1.00.005.834 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.156 (> 0.100 thold), f_keep = 0.175 1.00.005.868 I slot launch_slot_: id 2 | task 142 | processing task, is_child = 0 1.00.005.890 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.160 (> 0.100 thold), f_keep = 0.231 1.00.005.922 I slot launch_slot_: id 3 | task 143 | processing task, is_child = 0 1.01.401.517 I slot print_timing: id 0 | task 140 | prompt eval time = 1342.01 ms / 130 tokens ( 10.32 ms per token, 96.87 tokens per second) 1.01.401.520 I slot print_timing: id 0 | task 140 | eval time = 53.57 ms / 2 tokens ( 53.57 ms per token, 18.67 tokens per second) 1.01.401.520 I slot print_timing: id 0 | task 140 | total time = 1395.58 ms / 132 tokens 1.01.401.520 I slot print_timing: id 0 | task 140 | graphs reused = 1 1.01.401.521 I slot print_timing: id 0 | task 140 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.401.544 I slot release: id 0 | task 140 | stop processing: n_tokens = 131, truncated = 0 1.01.401.693 I slot print_timing: id 1 | task 141 | prompt eval time = 1342.20 ms / 172 tokens ( 7.80 ms per token, 128.15 tokens per second) 1.01.401.695 I slot print_timing: id 1 | task 141 | eval time = 53.55 ms / 2 tokens ( 53.55 ms per token, 18.68 tokens per second) 1.01.401.695 I slot print_timing: id 1 | task 141 | total time = 1395.75 ms / 174 tokens 1.01.401.695 I slot print_timing: id 1 | task 141 | graphs reused = 1 1.01.401.696 I slot print_timing: id 1 | task 141 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.401.710 I slot release: id 1 | task 141 | stop processing: n_tokens = 173, truncated = 0 1.01.401.870 I slot print_timing: id 2 | task 142 | prompt eval time = 1342.39 ms / 180 tokens ( 7.46 ms per token, 134.09 tokens per second) 1.01.401.874 I slot print_timing: id 2 | task 142 | eval time = 53.53 ms / 2 tokens ( 53.53 ms per token, 18.68 tokens per second) 1.01.401.874 I slot print_timing: id 2 | task 142 | total time = 1395.92 ms / 182 tokens 1.01.401.875 I slot print_timing: id 2 | task 142 | graphs reused = 1 1.01.401.875 I slot print_timing: id 2 | task 142 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.401.891 I slot release: id 2 | task 142 | stop processing: n_tokens = 181, truncated = 0 1.01.402.056 I slot print_timing: id 3 | task 143 | prompt eval time = 1342.60 ms / 175 tokens ( 7.67 ms per token, 130.34 tokens per second) 1.01.402.059 I slot print_timing: id 3 | task 143 | eval time = 53.49 ms / 2 tokens ( 53.49 ms per token, 18.69 tokens per second) 1.01.402.059 I slot print_timing: id 3 | task 143 | total time = 1396.09 ms / 177 tokens 1.01.402.059 I slot print_timing: id 3 | task 143 | graphs reused = 1 1.01.402.059 I slot print_timing: id 3 | task 143 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.402.068 I slot release: id 3 | task 143 | stop processing: n_tokens = 176, truncated = 0 1.01.407.270 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 1.01.407.296 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.954 MiB) 1.01.414.977 I slot launch_slot_: id 0 | task 147 | processing task, is_child = 0 1.01.415.010 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.091 MiB) 1.01.422.640 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.579 MiB) 1.01.430.262 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.973 MiB) 1.01.437.686 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.162 1.01.437.748 I slot launch_slot_: id 1 | task 148 | processing task, is_child = 0 1.01.437.788 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.155 1.01.439.336 I slot launch_slot_: id 2 | task 150 | processing task, is_child = 0 1.01.439.366 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.243 (> 0.100 thold), f_keep = 0.159 1.01.440.794 I slot launch_slot_: id 3 | task 149 | processing task, is_child = 0 1.02.465.100 I slot print_timing: id 0 | task 147 | prompt eval time = 970.99 ms / 115 tokens ( 8.44 ms per token, 118.44 tokens per second) 1.02.465.103 I slot print_timing: id 0 | task 147 | eval time = 53.31 ms / 2 tokens ( 53.31 ms per token, 18.76 tokens per second) 1.02.465.103 I slot print_timing: id 0 | task 147 | total time = 1024.30 ms / 117 tokens 1.02.465.104 I slot print_timing: id 0 | task 147 | graphs reused = 1 1.02.465.104 I slot print_timing: id 0 | task 147 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.465.122 I slot release: id 0 | task 147 | stop processing: n_tokens = 116, truncated = 0 1.02.465.277 I slot print_timing: id 1 | task 148 | prompt eval time = 971.17 ms / 123 tokens ( 7.90 ms per token, 126.65 tokens per second) 1.02.465.279 I slot print_timing: id 1 | task 148 | eval time = 53.28 ms / 2 tokens ( 53.28 ms per token, 18.77 tokens per second) 1.02.465.279 I slot print_timing: id 1 | task 148 | total time = 1024.45 ms / 125 tokens 1.02.465.280 I slot print_timing: id 1 | task 148 | graphs reused = 1 1.02.465.280 I slot print_timing: id 1 | task 148 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.465.292 I slot release: id 1 | task 148 | stop processing: n_tokens = 124, truncated = 0 1.02.465.465 I slot print_timing: id 2 | task 150 | prompt eval time = 971.36 ms / 123 tokens ( 7.90 ms per token, 126.63 tokens per second) 1.02.465.466 I slot print_timing: id 2 | task 150 | eval time = 53.27 ms / 2 tokens ( 53.27 ms per token, 18.77 tokens per second) 1.02.465.467 I slot print_timing: id 2 | task 150 | total time = 1024.63 ms / 125 tokens 1.02.465.467 I slot print_timing: id 2 | task 150 | graphs reused = 1 1.02.465.467 I slot print_timing: id 2 | task 150 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.465.478 I slot release: id 2 | task 150 | stop processing: n_tokens = 124, truncated = 0 1.02.465.657 I slot print_timing: id 3 | task 149 | prompt eval time = 971.57 ms / 115 tokens ( 8.45 ms per token, 118.36 tokens per second) 1.02.465.659 I slot print_timing: id 3 | task 149 | eval time = 53.24 ms / 2 tokens ( 53.24 ms per token, 18.78 tokens per second) 1.02.465.659 I slot print_timing: id 3 | task 149 | total time = 1024.81 ms / 117 tokens 1.02.465.660 I slot print_timing: id 3 | task 149 | graphs reused = 1 1.02.465.660 I slot print_timing: id 3 | task 149 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.465.667 I slot release: id 3 | task 149 | stop processing: n_tokens = 116, truncated = 0 1.02.470.599 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.215 (> 0.100 thold), f_keep = 0.241 1.02.474.062 I slot launch_slot_: id 0 | task 155 | processing task, is_child = 0 1.02.477.454 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.306 MiB) 1.02.480.963 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.442 MiB) 1.02.484.408 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.219 (> 0.100 thold), f_keep = 0.226 1.02.485.860 I slot launch_slot_: id 1 | task 157 | processing task, is_child = 0 1.02.485.898 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.226 1.02.485.938 I slot launch_slot_: id 2 | task 156 | processing task, is_child = 0 1.02.485.958 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.252 (> 0.100 thold), f_keep = 0.276 1.02.485.991 I slot launch_slot_: id 3 | task 154 | processing task, is_child = 0 1.03.633.668 I slot print_timing: id 0 | task 155 | prompt eval time = 1094.47 ms / 130 tokens ( 8.42 ms per token, 118.78 tokens per second) 1.03.633.671 I slot print_timing: id 0 | task 155 | eval time = 53.20 ms / 2 tokens ( 53.20 ms per token, 18.80 tokens per second) 1.03.633.672 I slot print_timing: id 0 | task 155 | total time = 1147.66 ms / 132 tokens 1.03.633.672 I slot print_timing: id 0 | task 155 | graphs reused = 1 1.03.633.673 I slot print_timing: id 0 | task 155 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.633.692 I slot release: id 0 | task 155 | stop processing: n_tokens = 131, truncated = 0 1.03.633.850 I slot print_timing: id 1 | task 157 | prompt eval time = 1094.62 ms / 128 tokens ( 8.55 ms per token, 116.94 tokens per second) 1.03.633.855 I slot print_timing: id 1 | task 157 | eval time = 53.22 ms / 2 tokens ( 53.22 ms per token, 18.79 tokens per second) 1.03.633.855 I slot print_timing: id 1 | task 157 | total time = 1147.84 ms / 130 tokens 1.03.633.855 I slot print_timing: id 1 | task 157 | graphs reused = 1 1.03.633.856 I slot print_timing: id 1 | task 157 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.633.868 I slot release: id 1 | task 157 | stop processing: n_tokens = 129, truncated = 0 1.03.634.039 I slot print_timing: id 2 | task 156 | prompt eval time = 1094.80 ms / 141 tokens ( 7.76 ms per token, 128.79 tokens per second) 1.03.634.041 I slot print_timing: id 2 | task 156 | eval time = 53.22 ms / 2 tokens ( 53.22 ms per token, 18.79 tokens per second) 1.03.634.042 I slot print_timing: id 2 | task 156 | total time = 1148.02 ms / 143 tokens 1.03.634.042 I slot print_timing: id 2 | task 156 | graphs reused = 1 1.03.634.042 I slot print_timing: id 2 | task 156 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.634.060 I slot release: id 2 | task 156 | stop processing: n_tokens = 142, truncated = 0 1.03.634.240 I slot print_timing: id 3 | task 154 | prompt eval time = 1095.00 ms / 127 tokens ( 8.62 ms per token, 115.98 tokens per second) 1.03.634.243 I slot print_timing: id 3 | task 154 | eval time = 53.21 ms / 2 tokens ( 53.21 ms per token, 18.79 tokens per second) 1.03.634.244 I slot print_timing: id 3 | task 154 | total time = 1148.21 ms / 129 tokens 1.03.634.244 I slot print_timing: id 3 | task 154 | graphs reused = 1 1.03.634.244 I slot print_timing: id 3 | task 154 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.634.252 I slot release: id 3 | task 154 | stop processing: n_tokens = 128, truncated = 0 1.03.639.532 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.276 (> 0.100 thold), f_keep = 0.227 1.03.642.888 I slot launch_slot_: id 3 | task 161 | processing task, is_child = 0 1.03.642.908 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.186 MiB) 1.03.646.288 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.208 MiB) 1.03.649.607 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.032 MiB) 1.03.652.947 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.214 1.03.652.993 I slot launch_slot_: id 0 | task 162 | processing task, is_child = 0 1.03.653.033 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.217 (> 0.100 thold), f_keep = 0.217 1.03.653.069 I slot launch_slot_: id 1 | task 163 | processing task, is_child = 0 1.03.653.097 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.174 (> 0.100 thold), f_keep = 0.197 1.03.653.129 I slot launch_slot_: id 2 | task 164 | processing task, is_child = 0 1.04.961.753 I slot print_timing: id 0 | task 162 | prompt eval time = 1255.20 ms / 123 tokens ( 10.20 ms per token, 97.99 tokens per second) 1.04.961.756 I slot print_timing: id 0 | task 162 | eval time = 53.41 ms / 2 tokens ( 53.41 ms per token, 18.72 tokens per second) 1.04.961.756 I slot print_timing: id 0 | task 162 | total time = 1308.61 ms / 125 tokens 1.04.961.757 I slot print_timing: id 0 | task 162 | graphs reused = 1 1.04.961.757 I slot print_timing: id 0 | task 162 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.961.781 I slot release: id 0 | task 162 | stop processing: n_tokens = 124, truncated = 0 1.04.961.939 I slot print_timing: id 1 | task 163 | prompt eval time = 1255.40 ms / 129 tokens ( 9.73 ms per token, 102.76 tokens per second) 1.04.961.940 I slot print_timing: id 1 | task 163 | eval time = 53.38 ms / 2 tokens ( 53.38 ms per token, 18.73 tokens per second) 1.04.961.941 I slot print_timing: id 1 | task 163 | total time = 1308.79 ms / 131 tokens 1.04.961.942 I slot print_timing: id 1 | task 163 | graphs reused = 1 1.04.961.942 I slot print_timing: id 1 | task 163 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.961.953 I slot release: id 1 | task 163 | stop processing: n_tokens = 130, truncated = 0 1.04.962.129 I slot print_timing: id 2 | task 164 | prompt eval time = 1255.60 ms / 161 tokens ( 7.80 ms per token, 128.23 tokens per second) 1.04.962.134 I slot print_timing: id 2 | task 164 | eval time = 53.37 ms / 2 tokens ( 53.37 ms per token, 18.74 tokens per second) 1.04.962.135 I slot print_timing: id 2 | task 164 | total time = 1308.96 ms / 163 tokens 1.04.962.135 I slot print_timing: id 2 | task 164 | graphs reused = 1 1.04.962.136 I slot print_timing: id 2 | task 164 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.962.148 I slot release: id 2 | task 164 | stop processing: n_tokens = 162, truncated = 0 1.04.962.314 I slot print_timing: id 3 | task 161 | prompt eval time = 1255.81 ms / 105 tokens ( 11.96 ms per token, 83.61 tokens per second) 1.04.962.316 I slot print_timing: id 3 | task 161 | eval time = 53.33 ms / 2 tokens ( 53.33 ms per token, 18.75 tokens per second) 1.04.962.316 I slot print_timing: id 3 | task 161 | total time = 1309.14 ms / 107 tokens 1.04.962.316 I slot print_timing: id 3 | task 161 | graphs reused = 1 1.04.962.317 I slot print_timing: id 3 | task 161 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.962.326 I slot release: id 3 | task 161 | stop processing: n_tokens = 106, truncated = 0 1.04.966.834 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.264 (> 0.100 thold), f_keep = 0.274 1.04.966.857 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.462 MiB) 1.04.970.833 I slot launch_slot_: id 3 | task 168 | processing task, is_child = 0 1.04.970.856 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.127 MiB) 1.04.974.957 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.856 MiB) 1.04.978.802 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.423 MiB) 1.04.986.842 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.182 (> 0.100 thold), f_keep = 0.226 1.04.986.897 I slot launch_slot_: id 0 | task 170 | processing task, is_child = 0 1.04.986.934 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.215 1.04.986.968 I slot launch_slot_: id 1 | task 169 | processing task, is_child = 0 1.04.986.988 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.171 (> 0.100 thold), f_keep = 0.173 1.04.987.032 I slot launch_slot_: id 2 | task 171 | processing task, is_child = 0 1.06.390.337 I slot print_timing: id 0 | task 170 | prompt eval time = 1350.15 ms / 154 tokens ( 8.77 ms per token, 114.06 tokens per second) 1.06.390.339 I slot print_timing: id 0 | task 170 | eval time = 53.15 ms / 2 tokens ( 53.15 ms per token, 18.82 tokens per second) 1.06.390.339 I slot print_timing: id 0 | task 170 | total time = 1403.30 ms / 156 tokens 1.06.390.340 I slot print_timing: id 0 | task 170 | graphs reused = 1 1.06.390.340 I slot print_timing: id 0 | task 170 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.390.364 I slot release: id 0 | task 170 | stop processing: n_tokens = 155, truncated = 0 1.06.390.524 I slot print_timing: id 1 | task 169 | prompt eval time = 1350.33 ms / 141 tokens ( 9.58 ms per token, 104.42 tokens per second) 1.06.390.529 I slot print_timing: id 1 | task 169 | eval time = 53.14 ms / 2 tokens ( 53.14 ms per token, 18.82 tokens per second) 1.06.390.529 I slot print_timing: id 1 | task 169 | total time = 1403.47 ms / 143 tokens 1.06.390.529 I slot print_timing: id 1 | task 169 | graphs reused = 1 1.06.390.530 I slot print_timing: id 1 | task 169 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.390.542 I slot release: id 1 | task 169 | stop processing: n_tokens = 142, truncated = 0 1.06.390.719 I slot print_timing: id 2 | task 171 | prompt eval time = 1350.53 ms / 164 tokens ( 8.23 ms per token, 121.43 tokens per second) 1.06.390.721 I slot print_timing: id 2 | task 171 | eval time = 53.13 ms / 2 tokens ( 53.13 ms per token, 18.82 tokens per second) 1.06.390.722 I slot print_timing: id 2 | task 171 | total time = 1403.65 ms / 166 tokens 1.06.390.722 I slot print_timing: id 2 | task 171 | graphs reused = 1 1.06.390.723 I slot print_timing: id 2 | task 171 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.390.736 I slot release: id 2 | task 171 | stop processing: n_tokens = 165, truncated = 0 1.06.390.925 I slot print_timing: id 3 | task 168 | prompt eval time = 1350.76 ms / 110 tokens ( 12.28 ms per token, 81.44 tokens per second) 1.06.390.929 I slot print_timing: id 3 | task 168 | eval time = 53.09 ms / 2 tokens ( 53.09 ms per token, 18.83 tokens per second) 1.06.390.930 I slot print_timing: id 3 | task 168 | total time = 1403.85 ms / 112 tokens 1.06.390.930 I slot print_timing: id 3 | task 168 | graphs reused = 1 1.06.390.930 I slot print_timing: id 3 | task 168 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.390.944 I slot release: id 3 | task 168 | stop processing: n_tokens = 111, truncated = 0 1.06.396.247 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.264 (> 0.100 thold), f_keep = 0.261 1.06.396.324 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.993 MiB) 1.06.400.284 I slot launch_slot_: id 3 | task 175 | processing task, is_child = 0 1.06.400.308 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.462 MiB) 1.06.408.349 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.442 MiB) 1.06.412.381 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.051 MiB) 1.06.421.226 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.255 (> 0.100 thold), f_keep = 0.181 1.06.421.280 I slot launch_slot_: id 0 | task 176 | processing task, is_child = 0 1.06.421.317 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.204 (> 0.100 thold), f_keep = 0.197 1.06.421.349 I slot launch_slot_: id 1 | task 177 | processing task, is_child = 0 1.06.421.368 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.189 (> 0.100 thold), f_keep = 0.170 1.06.421.405 I slot launch_slot_: id 2 | task 178 | processing task, is_child = 0 1.07.594.499 I slot print_timing: id 0 | task 176 | prompt eval time = 1119.78 ms / 110 tokens ( 10.18 ms per token, 98.23 tokens per second) 1.07.594.501 I slot print_timing: id 0 | task 176 | eval time = 53.30 ms / 2 tokens ( 53.30 ms per token, 18.76 tokens per second) 1.07.594.502 I slot print_timing: id 0 | task 176 | total time = 1173.08 ms / 112 tokens 1.07.594.502 I slot print_timing: id 0 | task 176 | graphs reused = 1 1.07.594.503 I slot print_timing: id 0 | task 176 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.594.521 I slot release: id 0 | task 176 | stop processing: n_tokens = 111, truncated = 0 1.07.594.682 I slot print_timing: id 1 | task 177 | prompt eval time = 1119.98 ms / 137 tokens ( 8.18 ms per token, 122.32 tokens per second) 1.07.594.684 I slot print_timing: id 1 | task 177 | eval time = 53.28 ms / 2 tokens ( 53.28 ms per token, 18.77 tokens per second) 1.07.594.685 I slot print_timing: id 1 | task 177 | total time = 1173.26 ms / 139 tokens 1.07.594.685 I slot print_timing: id 1 | task 177 | graphs reused = 1 1.07.594.685 I slot print_timing: id 1 | task 177 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.594.703 I slot release: id 1 | task 177 | stop processing: n_tokens = 138, truncated = 0 1.07.594.878 I slot print_timing: id 2 | task 178 | prompt eval time = 1120.16 ms / 148 tokens ( 7.57 ms per token, 132.12 tokens per second) 1.07.594.882 I slot print_timing: id 2 | task 178 | eval time = 53.28 ms / 2 tokens ( 53.28 ms per token, 18.77 tokens per second) 1.07.594.883 I slot print_timing: id 2 | task 178 | total time = 1173.44 ms / 150 tokens 1.07.594.883 I slot print_timing: id 2 | task 178 | graphs reused = 1 1.07.594.883 I slot print_timing: id 2 | task 178 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.594.893 I slot release: id 2 | task 178 | stop processing: n_tokens = 149, truncated = 0 1.07.595.084 I slot print_timing: id 3 | task 175 | prompt eval time = 1120.37 ms / 110 tokens ( 10.19 ms per token, 98.18 tokens per second) 1.07.595.087 I slot print_timing: id 3 | task 175 | eval time = 53.26 ms / 2 tokens ( 53.26 ms per token, 18.77 tokens per second) 1.07.595.089 I slot print_timing: id 3 | task 175 | total time = 1173.63 ms / 112 tokens 1.07.595.090 I slot print_timing: id 3 | task 175 | graphs reused = 1 1.07.595.090 I slot print_timing: id 3 | task 175 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.595.100 I slot release: id 3 | task 175 | stop processing: n_tokens = 111, truncated = 0 1.07.600.163 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.252 1.07.600.190 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.641 MiB) 1.07.603.768 I slot launch_slot_: id 0 | task 182 | processing task, is_child = 0 1.07.603.793 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.169 MiB) 1.07.607.842 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.306 MiB) 1.07.616.677 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.227 MiB) 1.07.620.571 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.215 (> 0.100 thold), f_keep = 0.203 1.07.620.621 I slot launch_slot_: id 1 | task 183 | processing task, is_child = 0 1.07.620.658 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.184 (> 0.100 thold), f_keep = 0.188 1.07.620.699 I slot launch_slot_: id 2 | task 184 | processing task, is_child = 0 1.07.620.719 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.259 (> 0.100 thold), f_keep = 0.261 1.07.620.759 I slot launch_slot_: id 3 | task 185 | processing task, is_child = 0 1.08.950.266 I slot print_timing: id 0 | task 182 | prompt eval time = 1276.37 ms / 123 tokens ( 10.38 ms per token, 96.37 tokens per second) 1.08.950.269 I slot print_timing: id 0 | task 182 | eval time = 53.13 ms / 2 tokens ( 53.13 ms per token, 18.82 tokens per second) 1.08.950.269 I slot print_timing: id 0 | task 182 | total time = 1329.50 ms / 125 tokens 1.08.950.270 I slot print_timing: id 0 | task 182 | graphs reused = 1 1.08.950.270 I slot print_timing: id 0 | task 182 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.950.292 I slot release: id 0 | task 182 | stop processing: n_tokens = 124, truncated = 0 1.08.950.450 I slot print_timing: id 1 | task 183 | prompt eval time = 1276.57 ms / 130 tokens ( 9.82 ms per token, 101.84 tokens per second) 1.08.950.452 I slot print_timing: id 1 | task 183 | eval time = 53.10 ms / 2 tokens ( 53.10 ms per token, 18.83 tokens per second) 1.08.950.453 I slot print_timing: id 1 | task 183 | total time = 1329.67 ms / 132 tokens 1.08.950.453 I slot print_timing: id 1 | task 183 | graphs reused = 1 1.08.950.453 I slot print_timing: id 1 | task 183 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.950.465 I slot release: id 1 | task 183 | stop processing: n_tokens = 131, truncated = 0 1.08.950.639 I slot print_timing: id 2 | task 184 | prompt eval time = 1276.74 ms / 152 tokens ( 8.40 ms per token, 119.05 tokens per second) 1.08.950.641 I slot print_timing: id 2 | task 184 | eval time = 53.08 ms / 2 tokens ( 53.08 ms per token, 18.84 tokens per second) 1.08.950.642 I slot print_timing: id 2 | task 184 | total time = 1329.83 ms / 154 tokens 1.08.950.642 I slot print_timing: id 2 | task 184 | graphs reused = 1 1.08.950.642 I slot print_timing: id 2 | task 184 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.950.653 I slot release: id 2 | task 184 | stop processing: n_tokens = 153, truncated = 0 1.08.950.841 I slot print_timing: id 3 | task 185 | prompt eval time = 1276.94 ms / 112 tokens ( 11.40 ms per token, 87.71 tokens per second) 1.08.950.843 I slot print_timing: id 3 | task 185 | eval time = 53.08 ms / 2 tokens ( 53.08 ms per token, 18.84 tokens per second) 1.08.950.844 I slot print_timing: id 3 | task 185 | total time = 1330.02 ms / 114 tokens 1.08.950.844 I slot print_timing: id 3 | task 185 | graphs reused = 1 1.08.950.844 I slot print_timing: id 3 | task 185 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.950.851 I slot release: id 3 | task 185 | stop processing: n_tokens = 113, truncated = 0 1.08.955.972 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.254 (> 0.100 thold), f_keep = 0.257 1.08.955.995 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.205 MiB) 1.08.960.185 I slot launch_slot_: id 3 | task 190 | processing task, is_child = 0 1.08.960.215 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.892 MiB) 1.08.964.231 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.107 MiB) 1.08.969.313 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.384 MiB) 1.08.972.826 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 1.08.972.871 I slot launch_slot_: id 0 | task 191 | processing task, is_child = 0 1.08.972.906 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.227 (> 0.100 thold), f_keep = 0.221 1.08.972.940 I slot launch_slot_: id 1 | task 189 | processing task, is_child = 0 1.08.972.960 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.169 (> 0.100 thold), f_keep = 0.183 1.08.972.994 I slot launch_slot_: id 2 | task 192 | processing task, is_child = 0 1.10.441.918 I slot print_timing: id 0 | task 191 | prompt eval time = 1415.37 ms / 157 tokens ( 9.02 ms per token, 110.93 tokens per second) 1.10.441.921 I slot print_timing: id 0 | task 191 | eval time = 53.55 ms / 2 tokens ( 53.55 ms per token, 18.68 tokens per second) 1.10.441.921 I slot print_timing: id 0 | task 191 | total time = 1468.92 ms / 159 tokens 1.10.441.922 I slot print_timing: id 0 | task 191 | graphs reused = 1 1.10.441.922 I slot print_timing: id 0 | task 191 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.441.945 I slot release: id 0 | task 191 | stop processing: n_tokens = 158, truncated = 0 1.10.442.098 I slot print_timing: id 1 | task 189 | prompt eval time = 1415.56 ms / 128 tokens ( 11.06 ms per token, 90.42 tokens per second) 1.10.442.103 I slot print_timing: id 1 | task 189 | eval time = 53.53 ms / 2 tokens ( 53.53 ms per token, 18.68 tokens per second) 1.10.442.103 I slot print_timing: id 1 | task 189 | total time = 1469.08 ms / 130 tokens 1.10.442.103 I slot print_timing: id 1 | task 189 | graphs reused = 1 1.10.442.104 I slot print_timing: id 1 | task 189 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.442.116 I slot release: id 1 | task 189 | stop processing: n_tokens = 129, truncated = 0 1.10.442.280 I slot print_timing: id 2 | task 192 | prompt eval time = 1415.75 ms / 166 tokens ( 8.53 ms per token, 117.25 tokens per second) 1.10.442.282 I slot print_timing: id 2 | task 192 | eval time = 53.51 ms / 2 tokens ( 53.51 ms per token, 18.69 tokens per second) 1.10.442.283 I slot print_timing: id 2 | task 192 | total time = 1469.26 ms / 168 tokens 1.10.442.283 I slot print_timing: id 2 | task 192 | graphs reused = 1 1.10.442.283 I slot print_timing: id 2 | task 192 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.442.297 I slot release: id 2 | task 192 | stop processing: n_tokens = 167, truncated = 0 1.10.442.472 I slot print_timing: id 3 | task 190 | prompt eval time = 1415.96 ms / 114 tokens ( 12.42 ms per token, 80.51 tokens per second) 1.10.442.473 I slot print_timing: id 3 | task 190 | eval time = 53.48 ms / 2 tokens ( 53.48 ms per token, 18.70 tokens per second) 1.10.442.474 I slot print_timing: id 3 | task 190 | total time = 1469.44 ms / 116 tokens 1.10.442.474 I slot print_timing: id 3 | task 190 | graphs reused = 1 1.10.442.474 I slot print_timing: id 3 | task 190 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.442.481 I slot release: id 3 | task 190 | stop processing: n_tokens = 115, truncated = 0 1.10.447.650 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.259 (> 0.100 thold), f_keep = 0.177 1.10.447.679 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.051 MiB) 1.10.451.070 I slot launch_slot_: id 0 | task 197 | processing task, is_child = 0 1.10.451.099 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.951 MiB) 1.10.455.030 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.560 MiB) 1.10.459.938 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.834 MiB) 1.10.463.779 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.217 1.10.465.219 I slot launch_slot_: id 1 | task 196 | processing task, is_child = 0 1.10.465.263 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.183 (> 0.100 thold), f_keep = 0.168 1.10.465.301 I slot launch_slot_: id 2 | task 198 | processing task, is_child = 0 1.10.465.322 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.156 (> 0.100 thold), f_keep = 0.243 1.10.465.358 I slot launch_slot_: id 3 | task 199 | processing task, is_child = 0 1.11.973.588 I slot print_timing: id 0 | task 197 | prompt eval time = 1454.62 ms / 108 tokens ( 13.47 ms per token, 74.25 tokens per second) 1.11.973.590 I slot print_timing: id 0 | task 197 | eval time = 53.61 ms / 2 tokens ( 53.61 ms per token, 18.65 tokens per second) 1.11.973.590 I slot print_timing: id 0 | task 197 | total time = 1508.22 ms / 110 tokens 1.11.973.590 I slot print_timing: id 0 | task 197 | graphs reused = 1 1.11.973.591 I slot print_timing: id 0 | task 197 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.973.608 I slot release: id 0 | task 197 | stop processing: n_tokens = 109, truncated = 0 1.11.973.762 I slot print_timing: id 1 | task 196 | prompt eval time = 1454.79 ms / 141 tokens ( 10.32 ms per token, 96.92 tokens per second) 1.11.973.764 I slot print_timing: id 1 | task 196 | eval time = 53.59 ms / 2 tokens ( 53.59 ms per token, 18.66 tokens per second) 1.11.973.765 I slot print_timing: id 1 | task 196 | total time = 1508.38 ms / 143 tokens 1.11.973.765 I slot print_timing: id 1 | task 196 | graphs reused = 1 1.11.973.765 I slot print_timing: id 1 | task 196 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.973.776 I slot release: id 1 | task 196 | stop processing: n_tokens = 142, truncated = 0 1.11.973.951 I slot print_timing: id 2 | task 198 | prompt eval time = 1454.98 ms / 153 tokens ( 9.51 ms per token, 105.16 tokens per second) 1.11.973.952 I slot print_timing: id 2 | task 198 | eval time = 53.57 ms / 2 tokens ( 53.57 ms per token, 18.67 tokens per second) 1.11.973.953 I slot print_timing: id 2 | task 198 | total time = 1508.56 ms / 155 tokens 1.11.973.953 I slot print_timing: id 2 | task 198 | graphs reused = 1 1.11.973.953 I slot print_timing: id 2 | task 198 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.973.971 I slot release: id 2 | task 198 | stop processing: n_tokens = 154, truncated = 0 1.11.974.150 I slot print_timing: id 3 | task 199 | prompt eval time = 1455.18 ms / 179 tokens ( 8.13 ms per token, 123.01 tokens per second) 1.11.974.152 I slot print_timing: id 3 | task 199 | eval time = 53.56 ms / 2 tokens ( 53.56 ms per token, 18.67 tokens per second) 1.11.974.152 I slot print_timing: id 3 | task 199 | total time = 1508.74 ms / 181 tokens 1.11.974.153 I slot print_timing: id 3 | task 199 | graphs reused = 1 1.11.974.153 I slot print_timing: id 3 | task 199 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.974.163 I slot release: id 3 | task 199 | stop processing: n_tokens = 180, truncated = 0 1.11.979.824 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.209 (> 0.100 thold), f_keep = 0.257 1.11.983.243 I slot launch_slot_: id 0 | task 203 | processing task, is_child = 0 1.11.983.265 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.149 MiB) 1.11.987.255 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.794 MiB) 1.11.992.221 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.912 MiB) 1.11.996.284 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.241 (> 0.100 thold), f_keep = 0.197 1.11.997.757 I slot launch_slot_: id 1 | task 204 | processing task, is_child = 0 1.11.997.795 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.207 (> 0.100 thold), f_keep = 0.182 1.11.997.835 I slot launch_slot_: id 2 | task 205 | processing task, is_child = 0 1.11.997.857 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.177 (> 0.100 thold), f_keep = 0.156 1.11.997.891 I slot launch_slot_: id 3 | task 206 | processing task, is_child = 0 1.13.375.842 I slot print_timing: id 0 | task 203 | prompt eval time = 1324.44 ms / 134 tokens ( 9.88 ms per token, 101.17 tokens per second) 1.13.375.844 I slot print_timing: id 0 | task 203 | eval time = 53.50 ms / 2 tokens ( 53.50 ms per token, 18.69 tokens per second) 1.13.375.845 I slot print_timing: id 0 | task 203 | total time = 1377.94 ms / 136 tokens 1.13.375.845 I slot print_timing: id 0 | task 203 | graphs reused = 1 1.13.375.846 I slot print_timing: id 0 | task 203 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.375.865 I slot release: id 0 | task 203 | stop processing: n_tokens = 135, truncated = 0 1.13.376.027 I slot print_timing: id 1 | task 204 | prompt eval time = 1324.65 ms / 116 tokens ( 11.42 ms per token, 87.57 tokens per second) 1.13.376.030 I slot print_timing: id 1 | task 204 | eval time = 53.47 ms / 2 tokens ( 53.47 ms per token, 18.70 tokens per second) 1.13.376.031 I slot print_timing: id 1 | task 204 | total time = 1378.12 ms / 118 tokens 1.13.376.031 I slot print_timing: id 1 | task 204 | graphs reused = 1 1.13.376.031 I slot print_timing: id 1 | task 204 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.376.043 I slot release: id 1 | task 204 | stop processing: n_tokens = 117, truncated = 0 1.13.376.208 I slot print_timing: id 2 | task 205 | prompt eval time = 1324.86 ms / 135 tokens ( 9.81 ms per token, 101.90 tokens per second) 1.13.376.209 I slot print_timing: id 2 | task 205 | eval time = 53.43 ms / 2 tokens ( 53.43 ms per token, 18.71 tokens per second) 1.13.376.210 I slot print_timing: id 2 | task 205 | total time = 1378.29 ms / 137 tokens 1.13.376.210 I slot print_timing: id 2 | task 205 | graphs reused = 1 1.13.376.211 I slot print_timing: id 2 | task 205 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.376.223 I slot release: id 2 | task 205 | stop processing: n_tokens = 136, truncated = 0 1.13.376.391 I slot print_timing: id 3 | task 206 | prompt eval time = 1325.06 ms / 158 tokens ( 8.39 ms per token, 119.24 tokens per second) 1.13.376.393 I slot print_timing: id 3 | task 206 | eval time = 53.40 ms / 2 tokens ( 53.40 ms per token, 18.73 tokens per second) 1.13.376.394 I slot print_timing: id 3 | task 206 | total time = 1378.46 ms / 160 tokens 1.13.376.394 I slot print_timing: id 3 | task 206 | graphs reused = 1 1.13.376.394 I slot print_timing: id 3 | task 206 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.376.405 I slot release: id 3 | task 206 | stop processing: n_tokens = 159, truncated = 0 1.13.381.163 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.248 (> 0.100 thold), f_keep = 0.248 1.13.384.469 I slot launch_slot_: id 1 | task 210 | processing task, is_child = 0 1.13.384.489 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.853 MiB) 1.13.390.010 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.032 MiB) 1.13.393.930 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.521 MiB) 1.13.397.837 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.207 1.13.399.311 I slot launch_slot_: id 0 | task 211 | processing task, is_child = 0 1.13.399.360 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.178 (> 0.100 thold), f_keep = 0.206 1.13.399.396 I slot launch_slot_: id 2 | task 213 | processing task, is_child = 0 1.13.399.415 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.176 1.13.399.448 I slot launch_slot_: id 3 | task 212 | processing task, is_child = 0 1.14.650.299 I slot print_timing: id 0 | task 211 | prompt eval time = 1197.59 ms / 122 tokens ( 9.82 ms per token, 101.87 tokens per second) 1.14.650.301 I slot print_timing: id 0 | task 211 | eval time = 53.25 ms / 2 tokens ( 53.25 ms per token, 18.78 tokens per second) 1.14.650.302 I slot print_timing: id 0 | task 211 | total time = 1250.84 ms / 124 tokens 1.14.650.302 I slot print_timing: id 0 | task 211 | graphs reused = 1 1.14.650.303 I slot print_timing: id 0 | task 211 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.650.327 I slot release: id 0 | task 211 | stop processing: n_tokens = 123, truncated = 0 1.14.650.480 I slot print_timing: id 1 | task 210 | prompt eval time = 1197.78 ms / 117 tokens ( 10.24 ms per token, 97.68 tokens per second) 1.14.650.483 I slot print_timing: id 1 | task 210 | eval time = 53.24 ms / 2 tokens ( 53.24 ms per token, 18.78 tokens per second) 1.14.650.483 I slot print_timing: id 1 | task 210 | total time = 1251.02 ms / 119 tokens 1.14.650.484 I slot print_timing: id 1 | task 210 | graphs reused = 1 1.14.650.484 I slot print_timing: id 1 | task 210 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.650.493 I slot release: id 1 | task 210 | stop processing: n_tokens = 118, truncated = 0 1.14.650.683 I slot print_timing: id 2 | task 213 | prompt eval time = 1197.97 ms / 157 tokens ( 7.63 ms per token, 131.06 tokens per second) 1.14.650.685 I slot print_timing: id 2 | task 213 | eval time = 53.24 ms / 2 tokens ( 53.24 ms per token, 18.78 tokens per second) 1.14.650.685 I slot print_timing: id 2 | task 213 | total time = 1251.21 ms / 159 tokens 1.14.650.686 I slot print_timing: id 2 | task 213 | graphs reused = 1 1.14.650.686 I slot print_timing: id 2 | task 213 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.650.701 I slot release: id 2 | task 213 | stop processing: n_tokens = 158, truncated = 0 1.14.650.887 I slot print_timing: id 3 | task 212 | prompt eval time = 1198.16 ms / 149 tokens ( 8.04 ms per token, 124.36 tokens per second) 1.14.650.890 I slot print_timing: id 3 | task 212 | eval time = 53.24 ms / 2 tokens ( 53.24 ms per token, 18.78 tokens per second) 1.14.650.890 I slot print_timing: id 3 | task 212 | total time = 1251.40 ms / 151 tokens 1.14.650.890 I slot print_timing: id 3 | task 212 | graphs reused = 1 1.14.650.890 I slot print_timing: id 3 | task 212 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.650.901 I slot release: id 3 | task 212 | stop processing: n_tokens = 150, truncated = 0 1.14.656.279 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 1.14.659.632 I slot launch_slot_: id 0 | task 217 | processing task, is_child = 0 1.14.659.653 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.208 MiB) 1.14.663.608 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.993 MiB) 1.14.668.117 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.208 MiB) 1.14.671.545 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.181 (> 0.100 thold), f_keep = 0.237 1.14.671.594 I slot launch_slot_: id 1 | task 219 | processing task, is_child = 0 1.14.671.633 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.177 1.14.671.674 I slot launch_slot_: id 2 | task 218 | processing task, is_child = 0 1.14.671.694 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.182 (> 0.100 thold), f_keep = 0.187 1.14.671.727 I slot launch_slot_: id 3 | task 220 | processing task, is_child = 0 1.16.087.053 I slot print_timing: id 0 | task 217 | prompt eval time = 1361.82 ms / 149 tokens ( 9.14 ms per token, 109.41 tokens per second) 1.16.087.055 I slot print_timing: id 0 | task 217 | eval time = 53.49 ms / 2 tokens ( 53.49 ms per token, 18.69 tokens per second) 1.16.087.056 I slot print_timing: id 0 | task 217 | total time = 1415.31 ms / 151 tokens 1.16.087.056 I slot print_timing: id 0 | task 217 | graphs reused = 1 1.16.087.056 I slot print_timing: id 0 | task 217 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.087.076 I slot release: id 0 | task 217 | stop processing: n_tokens = 150, truncated = 0 1.16.087.234 I slot print_timing: id 1 | task 219 | prompt eval time = 1362.03 ms / 155 tokens ( 8.79 ms per token, 113.80 tokens per second) 1.16.087.236 I slot print_timing: id 1 | task 219 | eval time = 53.46 ms / 2 tokens ( 53.46 ms per token, 18.71 tokens per second) 1.16.087.237 I slot print_timing: id 1 | task 219 | total time = 1415.49 ms / 157 tokens 1.16.087.237 I slot print_timing: id 1 | task 219 | graphs reused = 1 1.16.087.237 I slot print_timing: id 1 | task 219 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.087.249 I slot release: id 1 | task 219 | stop processing: n_tokens = 156, truncated = 0 1.16.087.420 I slot print_timing: id 2 | task 218 | prompt eval time = 1362.22 ms / 160 tokens ( 8.51 ms per token, 117.45 tokens per second) 1.16.087.425 I slot print_timing: id 2 | task 218 | eval time = 53.44 ms / 2 tokens ( 53.44 ms per token, 18.71 tokens per second) 1.16.087.426 I slot print_timing: id 2 | task 218 | total time = 1415.66 ms / 162 tokens 1.16.087.426 I slot print_timing: id 2 | task 218 | graphs reused = 1 1.16.087.426 I slot print_timing: id 2 | task 218 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.087.437 I slot release: id 2 | task 218 | stop processing: n_tokens = 161, truncated = 0 1.16.087.620 I slot print_timing: id 3 | task 220 | prompt eval time = 1362.43 ms / 154 tokens ( 8.85 ms per token, 113.03 tokens per second) 1.16.087.621 I slot print_timing: id 3 | task 220 | eval time = 53.42 ms / 2 tokens ( 53.42 ms per token, 18.72 tokens per second) 1.16.087.621 I slot print_timing: id 3 | task 220 | total time = 1415.85 ms / 156 tokens 1.16.087.621 I slot print_timing: id 3 | task 220 | graphs reused = 1 1.16.087.622 I slot print_timing: id 3 | task 220 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.087.632 I slot release: id 3 | task 220 | stop processing: n_tokens = 155, truncated = 0 1.16.092.606 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.262 (> 0.100 thold), f_keep = 0.187 1.16.092.630 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.071 MiB) 1.16.095.969 I slot launch_slot_: id 0 | task 224 | processing task, is_child = 0 1.16.095.990 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.403 MiB) 1.16.103.921 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.462 MiB) 1.16.112.219 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.954 MiB) 1.16.123.224 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.246 (> 0.100 thold), f_keep = 0.179 1.16.123.275 I slot launch_slot_: id 1 | task 226 | processing task, is_child = 0 1.16.123.309 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.275 (> 0.100 thold), f_keep = 0.174 1.16.124.778 I slot launch_slot_: id 2 | task 225 | processing task, is_child = 0 1.16.124.801 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 1.16.124.835 I slot launch_slot_: id 3 | task 227 | processing task, is_child = 0 1.17.363.731 I slot print_timing: id 0 | task 224 | prompt eval time = 1185.64 ms / 107 tokens ( 11.08 ms per token, 90.25 tokens per second) 1.17.363.733 I slot print_timing: id 0 | task 224 | eval time = 53.25 ms / 2 tokens ( 53.25 ms per token, 18.78 tokens per second) 1.17.363.733 I slot print_timing: id 0 | task 224 | total time = 1238.89 ms / 109 tokens 1.17.363.733 I slot print_timing: id 0 | task 224 | graphs reused = 1 1.17.363.734 I slot print_timing: id 0 | task 224 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.363.755 I slot release: id 0 | task 224 | stop processing: n_tokens = 108, truncated = 0 1.17.363.909 I slot print_timing: id 1 | task 226 | prompt eval time = 1185.83 ms / 114 tokens ( 10.40 ms per token, 96.14 tokens per second) 1.17.363.914 I slot print_timing: id 1 | task 226 | eval time = 53.22 ms / 2 tokens ( 53.22 ms per token, 18.79 tokens per second) 1.17.363.915 I slot print_timing: id 1 | task 226 | total time = 1239.05 ms / 116 tokens 1.17.363.915 I slot print_timing: id 1 | task 226 | graphs reused = 1 1.17.363.915 I slot print_timing: id 1 | task 226 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.363.926 I slot release: id 1 | task 226 | stop processing: n_tokens = 115, truncated = 0 1.17.364.085 I slot print_timing: id 2 | task 225 | prompt eval time = 1186.02 ms / 102 tokens ( 11.63 ms per token, 86.00 tokens per second) 1.17.364.087 I slot print_timing: id 2 | task 225 | eval time = 53.20 ms / 2 tokens ( 53.20 ms per token, 18.80 tokens per second) 1.17.364.088 I slot print_timing: id 2 | task 225 | total time = 1239.22 ms / 104 tokens 1.17.364.088 I slot print_timing: id 2 | task 225 | graphs reused = 1 1.17.364.088 I slot print_timing: id 2 | task 225 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.364.098 I slot release: id 2 | task 225 | stop processing: n_tokens = 103, truncated = 0 1.17.364.264 I slot print_timing: id 3 | task 227 | prompt eval time = 1186.23 ms / 185 tokens ( 6.41 ms per token, 155.96 tokens per second) 1.17.364.266 I slot print_timing: id 3 | task 227 | eval time = 53.15 ms / 2 tokens ( 53.15 ms per token, 18.81 tokens per second) 1.17.364.267 I slot print_timing: id 3 | task 227 | total time = 1239.39 ms / 187 tokens 1.17.364.267 I slot print_timing: id 3 | task 227 | graphs reused = 1 1.17.364.267 I slot print_timing: id 3 | task 227 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.364.281 I slot release: id 3 | task 227 | stop processing: n_tokens = 186, truncated = 0 1.17.369.166 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.222 (> 0.100 thold), f_keep = 0.259 1.17.372.488 I slot launch_slot_: id 0 | task 233 | processing task, is_child = 0 1.17.372.510 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.012 MiB) 1.17.376.371 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.010 MiB) 1.17.380.245 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.107 MiB) 1.17.393.053 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.264 (> 0.100 thold), f_keep = 0.282 1.17.393.128 I slot launch_slot_: id 2 | task 232 | processing task, is_child = 0 1.17.393.169 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.243 1.17.393.211 I slot launch_slot_: id 1 | task 231 | processing task, is_child = 0 1.17.393.233 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 1.17.393.279 I slot launch_slot_: id 3 | task 234 | processing task, is_child = 0 1.18.708.776 I slot print_timing: id 0 | task 233 | prompt eval time = 1262.15 ms / 126 tokens ( 10.02 ms per token, 99.83 tokens per second) 1.18.708.778 I slot print_timing: id 0 | task 233 | eval time = 53.33 ms / 2 tokens ( 53.33 ms per token, 18.75 tokens per second) 1.18.708.779 I slot print_timing: id 0 | task 233 | total time = 1315.48 ms / 128 tokens 1.18.708.779 I slot print_timing: id 0 | task 233 | graphs reused = 1 1.18.708.780 I slot print_timing: id 0 | task 233 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.708.803 I slot release: id 0 | task 233 | stop processing: n_tokens = 127, truncated = 0 1.18.708.962 I slot print_timing: id 1 | task 231 | prompt eval time = 1262.33 ms / 122 tokens ( 10.35 ms per token, 96.65 tokens per second) 1.18.708.964 I slot print_timing: id 1 | task 231 | eval time = 53.32 ms / 2 tokens ( 53.32 ms per token, 18.75 tokens per second) 1.18.708.964 I slot print_timing: id 1 | task 231 | total time = 1315.66 ms / 124 tokens 1.18.708.965 I slot print_timing: id 1 | task 231 | graphs reused = 1 1.18.708.965 I slot print_timing: id 1 | task 231 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.708.975 I slot release: id 1 | task 231 | stop processing: n_tokens = 123, truncated = 0 1.18.709.149 I slot print_timing: id 2 | task 232 | prompt eval time = 1262.54 ms / 110 tokens ( 11.48 ms per token, 87.13 tokens per second) 1.18.709.151 I slot print_timing: id 2 | task 232 | eval time = 53.29 ms / 2 tokens ( 53.29 ms per token, 18.77 tokens per second) 1.18.709.151 I slot print_timing: id 2 | task 232 | total time = 1315.83 ms / 112 tokens 1.18.709.151 I slot print_timing: id 2 | task 232 | graphs reused = 1 1.18.709.152 I slot print_timing: id 2 | task 232 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.709.160 I slot release: id 2 | task 232 | stop processing: n_tokens = 111, truncated = 0 1.18.709.339 I slot print_timing: id 3 | task 234 | prompt eval time = 1262.75 ms / 164 tokens ( 7.70 ms per token, 129.88 tokens per second) 1.18.709.342 I slot print_timing: id 3 | task 234 | eval time = 53.27 ms / 2 tokens ( 53.27 ms per token, 18.77 tokens per second) 1.18.709.342 I slot print_timing: id 3 | task 234 | total time = 1316.01 ms / 166 tokens 1.18.709.342 I slot print_timing: id 3 | task 234 | graphs reused = 1 1.18.709.343 I slot print_timing: id 3 | task 234 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.709.354 I slot release: id 3 | task 234 | stop processing: n_tokens = 165, truncated = 0 1.18.714.632 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.224 (> 0.100 thold), f_keep = 0.220 1.18.714.656 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 130.339 MiB) 1.18.718.769 I slot launch_slot_: id 0 | task 238 | processing task, is_child = 0 1.18.718.797 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.306 MiB) 1.18.723.636 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.423 MiB) 1.18.726.944 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.775 MiB) 1.18.730.301 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 1.18.730.352 I slot launch_slot_: id 1 | task 239 | processing task, is_child = 0 1.18.730.395 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.212 (> 0.100 thold), f_keep = 0.261 1.18.730.431 I slot launch_slot_: id 2 | task 240 | processing task, is_child = 0 1.18.730.450 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 1.18.731.891 I slot launch_slot_: id 3 | task 241 | processing task, is_child = 0 1.19.935.071 I slot print_timing: id 0 | task 238 | prompt eval time = 1149.89 ms / 125 tokens ( 9.20 ms per token, 108.71 tokens per second) 1.19.935.074 I slot print_timing: id 0 | task 238 | eval time = 53.28 ms / 2 tokens ( 53.28 ms per token, 18.77 tokens per second) 1.19.935.075 I slot print_timing: id 0 | task 238 | total time = 1203.16 ms / 127 tokens 1.19.935.075 I slot print_timing: id 0 | task 238 | graphs reused = 1 1.19.935.076 I slot print_timing: id 0 | task 238 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.935.094 I slot release: id 0 | task 238 | stop processing: n_tokens = 126, truncated = 0 1.19.935.269 I slot print_timing: id 1 | task 239 | prompt eval time = 1150.05 ms / 122 tokens ( 9.43 ms per token, 106.08 tokens per second) 1.19.935.271 I slot print_timing: id 1 | task 239 | eval time = 53.31 ms / 2 tokens ( 53.31 ms per token, 18.76 tokens per second) 1.19.935.272 I slot print_timing: id 1 | task 239 | total time = 1203.36 ms / 124 tokens 1.19.935.272 I slot print_timing: id 1 | task 239 | graphs reused = 1 1.19.935.272 I slot print_timing: id 1 | task 239 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.935.288 I slot release: id 1 | task 239 | stop processing: n_tokens = 123, truncated = 0 1.19.935.470 I slot print_timing: id 2 | task 240 | prompt eval time = 1150.24 ms / 137 tokens ( 8.40 ms per token, 119.11 tokens per second) 1.19.935.472 I slot print_timing: id 2 | task 240 | eval time = 53.31 ms / 2 tokens ( 53.31 ms per token, 18.76 tokens per second) 1.19.935.472 I slot print_timing: id 2 | task 240 | total time = 1203.55 ms / 139 tokens 1.19.935.472 I slot print_timing: id 2 | task 240 | graphs reused = 1 1.19.935.473 I slot print_timing: id 2 | task 240 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.935.484 I slot release: id 2 | task 240 | stop processing: n_tokens = 138, truncated = 0 1.19.935.648 I slot print_timing: id 3 | task 241 | prompt eval time = 1150.44 ms / 138 tokens ( 8.34 ms per token, 119.95 tokens per second) 1.19.935.650 I slot print_timing: id 3 | task 241 | eval time = 53.27 ms / 2 tokens ( 53.27 ms per token, 18.77 tokens per second) 1.19.935.650 I slot print_timing: id 3 | task 241 | total time = 1203.71 ms / 140 tokens 1.19.935.650 I slot print_timing: id 3 | task 241 | graphs reused = 1 1.19.935.651 I slot print_timing: id 3 | task 241 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.935.661 I slot release: id 3 | task 241 | stop processing: n_tokens = 139, truncated = 0 1.19.940.297 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 1.19.943.767 I slot launch_slot_: id 0 | task 245 | processing task, is_child = 0 1.19.943.791 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.677 MiB) 1.19.947.134 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 130.065 MiB) 1.19.950.513 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.403 MiB) 1.19.953.906 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.177 (> 0.100 thold), f_keep = 0.228 1.19.955.410 I slot launch_slot_: id 1 | task 246 | processing task, is_child = 0 1.19.955.452 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.167 (> 0.100 thold), f_keep = 0.203 1.19.955.490 I slot launch_slot_: id 2 | task 247 | processing task, is_child = 0 1.19.955.510 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.200 (> 0.100 thold), f_keep = 0.201 1.19.955.557 I slot launch_slot_: id 3 | task 248 | processing task, is_child = 0 1.21.365.189 I slot print_timing: id 0 | task 245 | prompt eval time = 1356.14 ms / 120 tokens ( 11.30 ms per token, 88.49 tokens per second) 1.21.365.191 I slot print_timing: id 0 | task 245 | eval time = 53.49 ms / 2 tokens ( 53.49 ms per token, 18.70 tokens per second) 1.21.365.192 I slot print_timing: id 0 | task 245 | total time = 1409.62 ms / 122 tokens 1.21.365.192 I slot print_timing: id 0 | task 245 | graphs reused = 1 1.21.365.193 I slot print_timing: id 0 | task 245 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.365.212 I slot release: id 0 | task 245 | stop processing: n_tokens = 121, truncated = 0 1.21.365.373 I slot print_timing: id 1 | task 246 | prompt eval time = 1356.32 ms / 158 tokens ( 8.58 ms per token, 116.49 tokens per second) 1.21.365.375 I slot print_timing: id 1 | task 246 | eval time = 53.47 ms / 2 tokens ( 53.47 ms per token, 18.70 tokens per second) 1.21.365.376 I slot print_timing: id 1 | task 246 | total time = 1409.79 ms / 160 tokens 1.21.365.376 I slot print_timing: id 1 | task 246 | graphs reused = 1 1.21.365.376 I slot print_timing: id 1 | task 246 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.365.390 I slot release: id 1 | task 246 | stop processing: n_tokens = 159, truncated = 0 1.21.365.570 I slot print_timing: id 2 | task 247 | prompt eval time = 1356.51 ms / 168 tokens ( 8.07 ms per token, 123.85 tokens per second) 1.21.365.574 I slot print_timing: id 2 | task 247 | eval time = 53.47 ms / 2 tokens ( 53.47 ms per token, 18.70 tokens per second) 1.21.365.575 I slot print_timing: id 2 | task 247 | total time = 1409.98 ms / 170 tokens 1.21.365.575 I slot print_timing: id 2 | task 247 | graphs reused = 1 1.21.365.575 I slot print_timing: id 2 | task 247 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.365.592 I slot release: id 2 | task 247 | stop processing: n_tokens = 169, truncated = 0 1.21.365.767 I slot print_timing: id 3 | task 248 | prompt eval time = 1356.71 ms / 140 tokens ( 9.69 ms per token, 103.19 tokens per second) 1.21.365.769 I slot print_timing: id 3 | task 248 | eval time = 53.45 ms / 2 tokens ( 53.45 ms per token, 18.71 tokens per second) 1.21.365.769 I slot print_timing: id 3 | task 248 | total time = 1410.16 ms / 142 tokens 1.21.365.769 I slot print_timing: id 3 | task 248 | graphs reused = 1 1.21.365.770 I slot print_timing: id 3 | task 248 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.365.786 I slot release: id 3 | task 248 | stop processing: n_tokens = 141, truncated = 0 1.21.370.686 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 1.21.374.288 I slot launch_slot_: id 0 | task 252 | processing task, is_child = 0 1.21.374.313 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.401 MiB) 1.21.378.245 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.286 MiB) 1.21.381.701 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.010 MiB) 1.21.385.194 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.211 (> 0.100 thold), f_keep = 0.176 1.21.386.663 I slot launch_slot_: id 1 | task 253 | processing task, is_child = 0 1.21.386.704 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.154 (> 0.100 thold), f_keep = 0.166 1.21.386.745 I slot launch_slot_: id 2 | task 254 | processing task, is_child = 0 1.21.386.767 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.181 (> 0.100 thold), f_keep = 0.199 1.21.386.801 I slot launch_slot_: id 3 | task 255 | processing task, is_child = 0 1.22.882.639 I slot print_timing: id 0 | task 252 | prompt eval time = 1442.47 ms / 103 tokens ( 14.00 ms per token, 71.41 tokens per second) 1.22.882.642 I slot print_timing: id 0 | task 252 | eval time = 53.35 ms / 2 tokens ( 53.35 ms per token, 18.74 tokens per second) 1.22.882.642 I slot print_timing: id 0 | task 252 | total time = 1495.83 ms / 105 tokens 1.22.882.643 I slot print_timing: id 0 | task 252 | graphs reused = 1 1.22.882.643 I slot print_timing: id 0 | task 252 | graph reallocs = 0 / 0 (same size) / (changed size) 1.22.882.662 I slot release: id 0 | task 252 | stop processing: n_tokens = 104, truncated = 0 1.22.882.823 I slot print_timing: id 1 | task 253 | prompt eval time = 1442.67 ms / 133 tokens ( 10.85 ms per token, 92.19 tokens per second) 1.22.882.825 I slot print_timing: id 1 | task 253 | eval time = 53.33 ms / 2 tokens ( 53.33 ms per token, 18.75 tokens per second) 1.22.882.825 I slot print_timing: id 1 | task 253 | total time = 1496.00 ms / 135 tokens 1.22.882.826 I slot print_timing: id 1 | task 253 | graphs reused = 1 1.22.882.826 I slot print_timing: id 1 | task 253 | graph reallocs = 0 / 0 (same size) / (changed size) 1.22.882.844 I slot release: id 1 | task 253 | stop processing: n_tokens = 134, truncated = 0 1.22.883.015 I slot print_timing: id 2 | task 254 | prompt eval time = 1442.86 ms / 182 tokens ( 7.93 ms per token, 126.14 tokens per second) 1.22.883.020 I slot print_timing: id 2 | task 254 | eval time = 53.32 ms / 2 tokens ( 53.32 ms per token, 18.75 tokens per second) 1.22.883.022 I slot print_timing: id 2 | task 254 | total time = 1496.19 ms / 184 tokens 1.22.883.022 I slot print_timing: id 2 | task 254 | graphs reused = 1 1.22.883.022 I slot print_timing: id 2 | task 254 | graph reallocs = 0 / 0 (same size) / (changed size) 1.22.883.040 I slot release: id 2 | task 254 | stop processing: n_tokens = 183, truncated = 0 1.22.883.205 I slot print_timing: id 3 | task 255 | prompt eval time = 1443.07 ms / 155 tokens ( 9.31 ms per token, 107.41 tokens per second) 1.22.883.207 I slot print_timing: id 3 | task 255 | eval time = 53.29 ms / 2 tokens ( 53.29 ms per token, 18.77 tokens per second) 1.22.883.208 I slot print_timing: id 3 | task 255 | total time = 1496.36 ms / 157 tokens 1.22.883.208 I slot print_timing: id 3 | task 255 | graphs reused = 1 1.22.883.208 I slot print_timing: id 3 | task 255 | graph reallocs = 0 / 0 (same size) / (changed size) 1.22.883.220 I slot release: id 3 | task 255 | stop processing: n_tokens = 156, truncated = 0 1.22.887.826 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 1.22.891.305 I slot launch_slot_: id 0 | task 259 | processing task, is_child = 0 1.22.891.335 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.032 MiB) 1.22.896.569 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.266 MiB) 1.22.899.915 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.286 MiB) 1.22.903.231 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 1.22.903.279 I slot launch_slot_: id 1 | task 260 | processing task, is_child = 0 1.23.624.878 I slot print_timing: id 0 | task 259 | prompt eval time = 686.43 ms / 124 tokens ( 5.54 ms per token, 180.64 tokens per second) 1.23.624.880 I slot print_timing: id 0 | task 259 | eval time = 35.11 ms / 2 tokens ( 35.11 ms per token, 28.48 tokens per second) 1.23.624.881 I slot print_timing: id 0 | task 259 | total time = 721.54 ms / 126 tokens 1.23.624.881 I slot print_timing: id 0 | task 259 | graphs reused = 1 1.23.624.881 I slot print_timing: id 0 | task 259 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.624.897 I slot release: id 0 | task 259 | stop processing: n_tokens = 125, truncated = 0 1.23.625.041 I slot print_timing: id 1 | task 260 | prompt eval time = 686.58 ms / 144 tokens ( 4.77 ms per token, 209.73 tokens per second) 1.23.625.048 I slot print_timing: id 1 | task 260 | eval time = 35.12 ms / 2 tokens ( 35.12 ms per token, 28.48 tokens per second) 1.23.625.048 I slot print_timing: id 1 | task 260 | total time = 721.70 ms / 146 tokens 1.23.625.049 I slot print_timing: id 1 | task 260 | graphs reused = 1 1.23.625.049 I slot print_timing: id 1 | task 260 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.625.057 I slot release: id 1 | task 260 | stop processing: n_tokens = 145, truncated = 0 1.23.640.169 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 183, t_last = 389916473170 1.23.640.264 I slot launch_slot_: id 2 | task 264 | processing task, is_child = 0 1.23.640.286 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.755 MiB) 1.23.643.810 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.188 MiB) 1.23.647.144 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 156, t_last = 389916473350 1.23.647.183 I slot launch_slot_: id 3 | task 265 | processing task, is_child = 0 1.23.647.224 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 125, t_last = 389917215027 1.23.647.256 I slot launch_slot_: id 0 | task 266 | processing task, is_child = 0 1.23.647.274 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 145, t_last = 389917215187 1.23.647.304 I slot launch_slot_: id 1 | task 267 | processing task, is_child = 0 1.28.321.485 I slot print_timing: id 0 | task 266 | prompt processing, n_tokens = 727, progress = 0.58, t = 4.67 s / 155.54 tokens per second 1.28.392.127 I slot print_timing: id 1 | task 267 | prompt processing, n_tokens = 718, progress = 0.58, t = 4.67 s / 153.61 tokens per second 1.28.394.093 I slot print_timing: id 2 | task 264 | prompt processing, n_tokens = 714, progress = 0.58, t = 4.67 s / 152.76 tokens per second 1.28.395.979 I slot print_timing: id 3 | task 265 | prompt processing, n_tokens = 699, progress = 0.58, t = 4.67 s / 149.55 tokens per second 1.31.316.164 I slot print_timing: id 0 | task 266 | prompt processing, n_tokens = 1125, progress = 0.91, t = 7.67 s / 146.70 tokens per second 1.31.419.207 I slot print_timing: id 1 | task 267 | prompt processing, n_tokens = 1125, progress = 0.91, t = 7.67 s / 146.70 tokens per second 1.31.422.423 I slot print_timing: id 2 | task 264 | prompt processing, n_tokens = 1125, progress = 0.91, t = 7.67 s / 146.70 tokens per second 1.31.424.291 I slot print_timing: id 3 | task 265 | prompt processing, n_tokens = 1125, progress = 0.93, t = 7.67 s / 146.70 tokens per second 1.32.299.962 I slot print_timing: id 0 | task 266 | prompt processing, n_tokens = 1239, progress = 1.00, t = 8.65 s / 143.19 tokens per second 1.32.371.351 I slot print_timing: id 1 | task 267 | prompt processing, n_tokens = 1230, progress = 1.00, t = 8.65 s / 142.15 tokens per second 1.32.373.836 I slot print_timing: id 2 | task 264 | prompt processing, n_tokens = 1226, progress = 1.00, t = 8.65 s / 141.69 tokens per second 1.32.377.502 I slot print_timing: id 3 | task 265 | prompt processing, n_tokens = 1211, progress = 1.00, t = 8.65 s / 139.96 tokens per second 1.35.799.780 I slot print_timing: id 3 | task 265 | prompt eval time = 8858.16 ms / 1215 tokens ( 7.29 ms per token, 137.16 tokens per second) 1.35.799.788 I slot print_timing: id 3 | task 265 | eval time = 3294.26 ms / 63 tokens ( 53.13 ms per token, 18.82 tokens per second) 1.35.799.790 I slot print_timing: id 3 | task 265 | total time = 12152.41 ms / 1278 tokens 1.35.799.791 I slot print_timing: id 3 | task 265 | graphs reused = 63 1.35.799.792 I slot print_timing: id 3 | task 265 | graph reallocs = 0 / 0 (same size) / (changed size) 1.35.799.925 I slot release: id 3 | task 265 | stop processing: n_tokens = 1277, truncated = 0 1.35.849.891 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.897 1.35.849.953 I slot launch_slot_: id 3 | task 337 | processing task, is_child = 0 1.36.695.587 I slot print_timing: id 2 | task 264 | prompt eval time = 8857.96 ms / 1230 tokens ( 7.20 ms per token, 138.86 tokens per second) 1.36.695.593 I slot print_timing: id 2 | task 264 | eval time = 4190.28 ms / 73 tokens ( 58.20 ms per token, 17.18 tokens per second) 1.36.695.593 I slot print_timing: id 2 | task 264 | total time = 13048.25 ms / 1303 tokens 1.36.695.594 I slot print_timing: id 2 | task 264 | graphs reused = 69 1.36.695.594 I slot print_timing: id 2 | task 264 | graph reallocs = 0 / 0 (same size) / (changed size) 1.36.695.638 I slot release: id 2 | task 264 | stop processing: n_tokens = 1302, truncated = 0 1.36.752.838 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.880 1.36.752.885 I slot launch_slot_: id 2 | task 348 | processing task, is_child = 0 1.37.911.480 I slot print_timing: id 1 | task 267 | prompt eval time = 8857.77 ms / 1234 tokens ( 7.18 ms per token, 139.31 tokens per second) 1.37.911.488 I slot print_timing: id 1 | task 267 | eval time = 5406.38 ms / 88 tokens ( 62.14 ms per token, 16.09 tokens per second) 1.37.911.489 I slot print_timing: id 1 | task 267 | total time = 14264.15 ms / 1322 tokens 1.37.911.490 I slot print_timing: id 1 | task 267 | graphs reused = 80 1.37.911.491 I slot print_timing: id 1 | task 267 | graph reallocs = 0 / 0 (same size) / (changed size) 1.37.911.588 I slot release: id 1 | task 267 | stop processing: n_tokens = 1321, truncated = 0 1.37.973.027 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.868 1.37.973.100 I slot launch_slot_: id 1 | task 364 | processing task, is_child = 0 1.38.968.871 I slot print_timing: id 0 | task 266 | n_gen = 100, tg = 15.32 t/s, tg_3s = 15.47 t/s 1.41.863.124 I slot print_timing: id 3 | task 337 | prompt eval time = 478.40 ms / 132 tokens ( 3.62 ms per token, 275.92 tokens per second) 1.41.863.135 I slot print_timing: id 3 | task 337 | eval time = 5534.76 ms / 90 tokens ( 62.19 ms per token, 16.08 tokens per second) 1.41.863.137 I slot print_timing: id 3 | task 337 | total time = 6013.16 ms / 222 tokens 1.41.863.138 I slot print_timing: id 3 | task 337 | graphs reused = 143 1.41.863.139 I slot print_timing: id 3 | task 337 | graph reallocs = 0 / 0 (same size) / (changed size) 1.41.863.263 I slot release: id 3 | task 337 | stop processing: n_tokens = 1346, truncated = 0 1.41.912.767 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.851 1.41.912.821 I slot launch_slot_: id 3 | task 432 | processing task, is_child = 0 1.42.277.031 I slot print_timing: id 0 | task 266 | n_gen = 157, tg = 15.96 t/s, tg_3s = 17.23 t/s 1.43.260.963 I slot print_timing: id 2 | task 348 | n_gen = 100, tg = 16.53 t/s, tg_3s = 16.70 t/s 1.43.469.780 I slot print_timing: id 2 | task 348 | prompt eval time = 519.76 ms / 139 tokens ( 3.74 ms per token, 267.43 tokens per second) 1.43.469.786 I slot print_timing: id 2 | task 348 | eval time = 6197.13 ms / 104 tokens ( 60.17 ms per token, 16.62 tokens per second) 1.43.469.787 I slot print_timing: id 2 | task 348 | total time = 6716.89 ms / 243 tokens 1.43.469.787 I slot print_timing: id 2 | task 348 | graphs reused = 163 1.43.469.788 I slot print_timing: id 2 | task 348 | graph reallocs = 0 / 0 (same size) / (changed size) 1.43.469.833 I slot release: id 2 | task 348 | stop processing: n_tokens = 1367, truncated = 0 1.43.526.940 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.838 1.43.526.987 I slot launch_slot_: id 2 | task 457 | processing task, is_child = 0 1.44.467.735 I slot print_timing: id 1 | task 364 | n_gen = 100, tg = 16.58 t/s, tg_3s = 16.75 t/s 1.45.303.589 I slot print_timing: id 0 | task 266 | n_gen = 206, tg = 16.02 t/s, tg_3s = 16.19 t/s 1.45.878.717 I slot print_timing: id 1 | task 364 | prompt eval time = 524.84 ms / 139 tokens ( 3.78 ms per token, 264.84 tokens per second) 1.45.878.722 I slot print_timing: id 1 | task 364 | eval time = 7380.77 ms / 127 tokens ( 58.58 ms per token, 17.07 tokens per second) 1.45.878.723 I slot print_timing: id 1 | task 364 | total time = 7905.61 ms / 266 tokens 1.45.878.723 I slot print_timing: id 1 | task 364 | graphs reused = 197 1.45.878.724 I slot print_timing: id 1 | task 364 | graph reallocs = 0 / 0 (same size) / (changed size) 1.45.878.769 I slot release: id 1 | task 364 | stop processing: n_tokens = 1390, truncated = 0 1.45.936.045 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.886 (> 0.100 thold), f_keep = 0.824 1.45.936.085 I slot launch_slot_: id 1 | task 496 | processing task, is_child = 0 1.48.018.268 I slot print_timing: id 3 | task 432 | prompt eval time = 459.65 ms / 114 tokens ( 4.03 ms per token, 248.01 tokens per second) 1.48.018.271 I slot print_timing: id 3 | task 432 | eval time = 5645.79 ms / 92 tokens ( 62.04 ms per token, 16.12 tokens per second) 1.48.018.272 I slot print_timing: id 3 | task 432 | total time = 6105.44 ms / 206 tokens 1.48.018.272 I slot print_timing: id 3 | task 432 | graphs reused = 225 1.48.018.273 I slot print_timing: id 3 | task 432 | graph reallocs = 0 / 0 (same size) / (changed size) 1.48.018.321 I slot release: id 3 | task 432 | stop processing: n_tokens = 1330, truncated = 0 1.48.064.527 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.862 1.48.064.566 I slot launch_slot_: id 3 | task 529 | processing task, is_child = 0 1.48.440.878 I slot print_timing: id 0 | task 266 | n_gen = 251, tg = 15.69 t/s, tg_3s = 14.34 t/s 1.49.741.404 I slot print_timing: id 2 | task 457 | prompt eval time = 521.74 ms / 141 tokens ( 3.70 ms per token, 270.25 tokens per second) 1.49.741.410 I slot print_timing: id 2 | task 457 | eval time = 5692.67 ms / 94 tokens ( 61.21 ms per token, 16.34 tokens per second) 1.49.741.410 I slot print_timing: id 2 | task 457 | total time = 6214.41 ms / 235 tokens 1.49.741.411 I slot print_timing: id 2 | task 457 | graphs reused = 247 1.49.741.411 I slot print_timing: id 2 | task 457 | graph reallocs = 0 / 0 (same size) / (changed size) 1.49.741.458 I slot release: id 2 | task 457 | stop processing: n_tokens = 1359, truncated = 0 1.49.798.539 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.843 1.49.798.574 I slot launch_slot_: id 2 | task 556 | processing task, is_child = 0 1.51.472.901 I slot print_timing: id 0 | task 266 | n_gen = 301, tg = 15.82 t/s, tg_3s = 16.49 t/s 1.52.429.034 I slot print_timing: id 1 | task 496 | n_gen = 100, tg = 16.70 t/s, tg_3s = 16.87 t/s 1.53.227.812 I slot print_timing: id 3 | task 529 | prompt eval time = 471.55 ms / 125 tokens ( 3.77 ms per token, 265.09 tokens per second) 1.53.227.822 I slot print_timing: id 3 | task 529 | eval time = 4691.69 ms / 83 tokens ( 57.22 ms per token, 17.48 tokens per second) 1.53.227.823 I slot print_timing: id 3 | task 529 | total time = 5163.23 ms / 208 tokens 1.53.227.824 I slot print_timing: id 3 | task 529 | graphs reused = 301 1.53.227.825 I slot print_timing: id 3 | task 529 | graph reallocs = 0 / 0 (same size) / (changed size) 1.53.227.954 I slot release: id 3 | task 529 | stop processing: n_tokens = 1332, truncated = 0 1.53.277.547 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.860 1.53.277.603 I slot launch_slot_: id 3 | task 616 | processing task, is_child = 0 1.54.490.106 I slot print_timing: id 0 | task 266 | n_gen = 352, tg = 15.97 t/s, tg_3s = 16.90 t/s 1.54.910.162 I slot print_timing: id 2 | task 556 | prompt eval time = 444.88 ms / 101 tokens ( 4.40 ms per token, 227.03 tokens per second) 1.54.910.167 I slot print_timing: id 2 | task 556 | eval time = 4666.70 ms / 83 tokens ( 56.91 ms per token, 17.57 tokens per second) 1.54.910.168 I slot print_timing: id 2 | task 556 | total time = 5111.58 ms / 184 tokens 1.54.910.168 I slot print_timing: id 2 | task 556 | graphs reused = 323 1.54.910.168 I slot print_timing: id 2 | task 556 | graph reallocs = 0 / 0 (same size) / (changed size) 1.54.910.214 I slot release: id 2 | task 556 | stop processing: n_tokens = 1308, truncated = 0 1.54.967.576 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.876 1.54.967.613 I slot launch_slot_: id 2 | task 643 | processing task, is_child = 0 1.55.464.896 I slot print_timing: id 1 | task 496 | n_gen = 145, tg = 16.06 t/s, tg_3s = 14.82 t/s 1.56.487.690 I slot print_timing: id 1 | task 496 | prompt eval time = 564.60 ms / 169 tokens ( 3.34 ms per token, 299.33 tokens per second) 1.56.487.695 I slot print_timing: id 1 | task 496 | eval time = 9986.99 ms / 164 tokens ( 61.27 ms per token, 16.32 tokens per second) 1.56.487.698 I slot print_timing: id 1 | task 496 | total time = 10551.60 ms / 333 tokens 1.56.487.699 I slot print_timing: id 1 | task 496 | graphs reused = 342 1.56.487.700 I slot print_timing: id 1 | task 496 | graph reallocs = 0 / 0 (same size) / (changed size) 1.56.487.803 I slot release: id 1 | task 496 | stop processing: n_tokens = 1457, truncated = 0 1.56.549.324 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.787 1.56.549.398 I slot launch_slot_: id 1 | task 667 | processing task, is_child = 0 1.57.527.549 I slot print_timing: id 0 | task 266 | n_gen = 395, tg = 15.75 t/s, tg_3s = 14.16 t/s 1.58.380.500 I slot print_timing: id 3 | task 616 | prompt eval time = 426.70 ms / 101 tokens ( 4.22 ms per token, 236.70 tokens per second) 1.58.380.517 I slot print_timing: id 3 | task 616 | eval time = 4676.19 ms / 75 tokens ( 63.19 ms per token, 15.82 tokens per second) 1.58.380.518 I slot print_timing: id 3 | task 616 | total time = 5102.88 ms / 176 tokens 1.58.380.519 I slot print_timing: id 3 | task 616 | graphs reused = 366 1.58.380.520 I slot print_timing: id 3 | task 616 | graph reallocs = 0 / 0 (same size) / (changed size) 1.58.380.631 I slot release: id 3 | task 616 | stop processing: n_tokens = 1300, truncated = 0 1.58.430.449 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.882 1.58.430.520 I slot launch_slot_: id 3 | task 696 | processing task, is_child = 0 2.00.514.252 I slot print_timing: id 1 | task 667 | prompt eval time = 492.38 ms / 120 tokens ( 4.10 ms per token, 243.71 tokens per second) 2.00.514.261 I slot print_timing: id 1 | task 667 | eval time = 3472.44 ms / 59 tokens ( 59.87 ms per token, 16.70 tokens per second) 2.00.514.263 I slot print_timing: id 1 | task 667 | total time = 3964.83 ms / 179 tokens 2.00.514.264 I slot print_timing: id 1 | task 667 | graphs reused = 395 2.00.514.265 I slot print_timing: id 1 | task 667 | graph reallocs = 0 / 0 (same size) / (changed size) 2.00.514.376 I slot release: id 1 | task 667 | stop processing: n_tokens = 1303, truncated = 0 2.00.581.749 I slot print_timing: id 0 | task 266 | n_gen = 445, tg = 15.81 t/s, tg_3s = 16.37 t/s 2.00.582.233 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.880 2.00.582.279 I slot launch_slot_: id 1 | task 730 | processing task, is_child = 0 2.01.710.572 I slot print_timing: id 2 | task 643 | prompt eval time = 443.26 ms / 95 tokens ( 4.67 ms per token, 214.32 tokens per second) 2.01.710.581 I slot print_timing: id 2 | task 643 | eval time = 6299.67 ms / 98 tokens ( 64.95 ms per token, 15.40 tokens per second) 2.01.710.582 I slot print_timing: id 2 | task 643 | total time = 6742.94 ms / 193 tokens 2.01.710.583 I slot print_timing: id 2 | task 643 | graphs reused = 407 2.01.710.584 I slot print_timing: id 2 | task 643 | graph reallocs = 0 / 0 (same size) / (changed size) 2.01.710.688 I slot release: id 2 | task 643 | stop processing: n_tokens = 1317, truncated = 0 2.01.772.820 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.911 (> 0.100 thold), f_keep = 0.870 2.01.772.899 I slot launch_slot_: id 2 | task 747 | processing task, is_child = 0 2.03.602.051 I slot print_timing: id 0 | task 266 | n_gen = 488, tg = 15.66 t/s, tg_3s = 14.24 t/s 2.04.939.168 I slot print_timing: id 3 | task 696 | n_gen = 100, tg = 16.50 t/s, tg_3s = 16.67 t/s 2.05.631.639 I slot print_timing: id 1 | task 730 | prompt eval time = 439.41 ms / 86 tokens ( 5.11 ms per token, 195.72 tokens per second) 2.05.631.647 I slot print_timing: id 1 | task 730 | eval time = 4609.93 ms / 80 tokens ( 58.35 ms per token, 17.14 tokens per second) 2.05.631.649 I slot print_timing: id 1 | task 730 | total time = 5049.35 ms / 166 tokens 2.05.631.650 I slot print_timing: id 1 | task 730 | graphs reused = 469 2.05.631.651 I slot print_timing: id 1 | task 730 | graph reallocs = 0 / 0 (same size) / (changed size) 2.05.631.739 I slot release: id 1 | task 730 | stop processing: n_tokens = 1290, truncated = 0 2.05.693.771 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.888 2.05.693.846 I slot launch_slot_: id 1 | task 814 | processing task, is_child = 0 2.06.617.006 I slot print_timing: id 0 | task 266 | n_gen = 538, tg = 15.74 t/s, tg_3s = 16.58 t/s 2.07.405.095 I slot print_timing: id 2 | task 747 | prompt eval time = 507.25 ms / 133 tokens ( 3.81 ms per token, 262.20 tokens per second) 2.07.405.097 I slot print_timing: id 2 | task 747 | eval time = 5124.93 ms / 91 tokens ( 56.94 ms per token, 17.56 tokens per second) 2.07.405.099 I slot print_timing: id 2 | task 747 | total time = 5632.18 ms / 224 tokens 2.07.405.099 I slot print_timing: id 2 | task 747 | graphs reused = 491 2.07.405.100 I slot print_timing: id 2 | task 747 | graph reallocs = 0 / 0 (same size) / (changed size) 2.07.405.154 I slot release: id 2 | task 747 | stop processing: n_tokens = 1348, truncated = 0 2.07.462.336 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.948 (> 0.100 thold), f_keep = 0.850 2.07.462.384 I slot launch_slot_: id 2 | task 842 | processing task, is_child = 0 2.07.945.156 I slot print_timing: id 3 | task 696 | n_gen = 144, tg = 15.88 t/s, tg_3s = 14.64 t/s 2.08.917.117 I slot print_timing: id 3 | task 696 | prompt eval time = 508.68 ms / 148 tokens ( 3.44 ms per token, 290.95 tokens per second) 2.08.917.124 I slot print_timing: id 3 | task 696 | eval time = 9977.90 ms / 162 tokens ( 61.97 ms per token, 16.14 tokens per second) 2.08.917.125 I slot print_timing: id 3 | task 696 | total time = 10486.58 ms / 310 tokens 2.08.917.126 I slot print_timing: id 3 | task 696 | graphs reused = 509 2.08.917.127 I slot print_timing: id 3 | task 696 | graph reallocs = 0 / 0 (same size) / (changed size) 2.08.917.234 I slot release: id 3 | task 696 | stop processing: n_tokens = 1434, truncated = 0 2.08.967.005 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.799 2.08.967.073 I slot launch_slot_: id 3 | task 865 | processing task, is_child = 0 2.09.656.838 I slot print_timing: id 0 | task 266 | n_gen = 583, tg = 15.67 t/s, tg_3s = 14.80 t/s 2.10.390.267 I slot print_timing: id 1 | task 814 | prompt eval time = 449.07 ms / 97 tokens ( 4.63 ms per token, 216.00 tokens per second) 2.10.390.269 I slot print_timing: id 1 | task 814 | eval time = 4247.34 ms / 69 tokens ( 62.46 ms per token, 16.01 tokens per second) 2.10.390.270 I slot print_timing: id 1 | task 814 | total time = 4696.41 ms / 166 tokens 2.10.390.270 I slot print_timing: id 1 | task 814 | graphs reused = 527 2.10.390.271 I slot print_timing: id 1 | task 814 | graph reallocs = 0 / 0 (same size) / (changed size) 2.10.390.319 I slot release: id 1 | task 814 | stop processing: n_tokens = 1290, truncated = 0 2.10.448.155 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.888 2.10.448.193 I slot launch_slot_: id 1 | task 888 | processing task, is_child = 0 2.12.364.929 I slot print_timing: id 2 | task 842 | prompt eval time = 428.24 ms / 84 tokens ( 5.10 ms per token, 196.15 tokens per second) 2.12.364.936 I slot print_timing: id 2 | task 842 | eval time = 4474.29 ms / 73 tokens ( 62.14 ms per token, 16.09 tokens per second) 2.12.364.936 I slot print_timing: id 2 | task 842 | total time = 4902.54 ms / 157 tokens 2.12.364.937 I slot print_timing: id 2 | task 842 | graphs reused = 554 2.12.364.937 I slot print_timing: id 2 | task 842 | graph reallocs = 0 / 0 (same size) / (changed size) 2.12.364.982 I slot release: id 2 | task 842 | stop processing: n_tokens = 1281, truncated = 0 2.12.421.979 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.895 2.12.422.012 I slot launch_slot_: id 2 | task 920 | processing task, is_child = 0 2.12.810.888 I slot print_timing: id 0 | task 266 | n_gen = 630, tg = 15.61 t/s, tg_3s = 14.90 t/s 2.13.286.567 I slot print_timing: id 3 | task 865 | prompt eval time = 427.29 ms / 101 tokens ( 4.23 ms per token, 236.38 tokens per second) 2.13.286.571 I slot print_timing: id 3 | task 865 | eval time = 3892.20 ms / 61 tokens ( 64.87 ms per token, 15.42 tokens per second) 2.13.286.571 I slot print_timing: id 3 | task 865 | total time = 4319.48 ms / 162 tokens 2.13.286.571 I slot print_timing: id 3 | task 865 | graphs reused = 560 2.13.286.572 I slot print_timing: id 3 | task 865 | graph reallocs = 0 / 0 (same size) / (changed size) 2.13.286.617 I slot release: id 3 | task 865 | stop processing: n_tokens = 1286, truncated = 0 2.13.332.830 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.943 (> 0.100 thold), f_keep = 0.891 2.13.332.869 I slot launch_slot_: id 3 | task 931 | processing task, is_child = 0 2.14.582.507 I slot print_timing: id 1 | task 888 | prompt eval time = 449.43 ms / 95 tokens ( 4.73 ms per token, 211.38 tokens per second) 2.14.582.512 I slot print_timing: id 1 | task 888 | eval time = 3684.88 ms / 58 tokens ( 64.65 ms per token, 15.47 tokens per second) 2.14.582.512 I slot print_timing: id 1 | task 888 | total time = 4134.30 ms / 153 tokens 2.14.582.513 I slot print_timing: id 1 | task 888 | graphs reused = 575 2.14.582.513 I slot print_timing: id 1 | task 888 | graph reallocs = 0 / 0 (same size) / (changed size) 2.14.582.557 I slot release: id 1 | task 888 | stop processing: n_tokens = 1277, truncated = 0 2.14.640.316 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.897 2.14.640.354 I slot launch_slot_: id 1 | task 951 | processing task, is_child = 0 2.15.818.435 I slot print_timing: id 0 | task 266 | n_gen = 674, tg = 15.54 t/s, tg_3s = 14.63 t/s 2.18.053.378 I slot print_timing: id 3 | task 931 | prompt eval time = 409.70 ms / 90 tokens ( 4.55 ms per token, 219.67 tokens per second) 2.18.053.386 I slot print_timing: id 3 | task 931 | eval time = 4310.80 ms / 76 tokens ( 57.48 ms per token, 17.40 tokens per second) 2.18.053.387 I slot print_timing: id 3 | task 931 | total time = 4720.50 ms / 166 tokens 2.18.053.388 I slot print_timing: id 3 | task 931 | graphs reused = 630 2.18.053.389 I slot print_timing: id 3 | task 931 | graph reallocs = 0 / 0 (same size) / (changed size) 2.18.053.489 I slot release: id 3 | task 931 | stop processing: n_tokens = 1290, truncated = 0 2.18.103.039 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.888 2.18.103.096 I slot launch_slot_: id 3 | task 1011 | processing task, is_child = 0 2.18.832.194 I slot print_timing: id 0 | task 266 | n_gen = 725, tg = 15.63 t/s, tg_3s = 16.92 t/s 2.19.093.946 I slot print_timing: id 1 | task 951 | prompt eval time = 444.02 ms / 96 tokens ( 4.63 ms per token, 216.21 tokens per second) 2.19.093.951 I slot print_timing: id 1 | task 951 | eval time = 4009.56 ms / 71 tokens ( 57.28 ms per token, 17.46 tokens per second) 2.19.093.952 I slot print_timing: id 1 | task 951 | total time = 4453.58 ms / 167 tokens 2.19.093.952 I slot print_timing: id 1 | task 951 | graphs reused = 640 2.19.093.953 I slot print_timing: id 1 | task 951 | graph reallocs = 0 / 0 (same size) / (changed size) 2.19.093.999 I slot release: id 1 | task 951 | stop processing: n_tokens = 1291, truncated = 0 2.19.094.145 I slot print_timing: id 2 | task 920 | n_gen = 100, tg = 16.03 t/s, tg_3s = 16.19 t/s 2.19.150.965 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.888 2.19.151.001 I slot launch_slot_: id 1 | task 1026 | processing task, is_child = 0 2.20.037.579 I slot print_timing: id 2 | task 920 | prompt eval time = 496.44 ms / 130 tokens ( 3.82 ms per token, 261.86 tokens per second) 2.20.037.585 I slot print_timing: id 2 | task 920 | eval time = 7119.11 ms / 110 tokens ( 65.31 ms per token, 15.31 tokens per second) 2.20.037.586 I slot print_timing: id 2 | task 920 | total time = 7615.55 ms / 240 tokens 2.20.037.588 I slot print_timing: id 2 | task 920 | graphs reused = 646 2.20.037.589 I slot print_timing: id 2 | task 920 | graph reallocs = 0 / 0 (same size) / (changed size) 2.20.037.694 I slot release: id 2 | task 920 | stop processing: n_tokens = 1364, truncated = 0 2.20.100.075 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.840 2.20.100.132 I slot launch_slot_: id 2 | task 1037 | processing task, is_child = 0 2.21.841.616 I slot print_timing: id 0 | task 266 | n_gen = 766, tg = 15.51 t/s, tg_3s = 13.62 t/s 2.24.466.004 I slot print_timing: id 1 | task 1026 | prompt eval time = 500.77 ms / 131 tokens ( 3.82 ms per token, 261.60 tokens per second) 2.24.466.011 I slot print_timing: id 1 | task 1026 | eval time = 4814.22 ms / 83 tokens ( 58.71 ms per token, 17.03 tokens per second) 2.24.466.013 I slot print_timing: id 1 | task 1026 | total time = 5314.99 ms / 214 tokens 2.24.466.014 I slot print_timing: id 1 | task 1026 | graphs reused = 716 2.24.466.015 I slot print_timing: id 1 | task 1026 | graph reallocs = 0 / 0 (same size) / (changed size) 2.24.466.130 I slot release: id 1 | task 1026 | stop processing: n_tokens = 1338, truncated = 0 2.24.528.250 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.857 2.24.528.324 I slot launch_slot_: id 1 | task 1113 | processing task, is_child = 0 2.24.960.107 I slot print_timing: id 0 | task 266 | n_gen = 817, tg = 15.56 t/s, tg_3s = 16.35 t/s 2.25.069.095 I slot print_timing: id 3 | task 1011 | n_gen = 100, tg = 15.11 t/s, tg_3s = 15.26 t/s 2.25.123.645 I slot print_timing: id 3 | task 1011 | prompt eval time = 413.85 ms / 87 tokens ( 4.76 ms per token, 210.22 tokens per second) 2.25.123.650 I slot print_timing: id 3 | task 1011 | eval time = 6606.69 ms / 101 tokens ( 66.07 ms per token, 15.14 tokens per second) 2.25.123.651 I slot print_timing: id 3 | task 1011 | total time = 7020.54 ms / 188 tokens 2.25.123.651 I slot print_timing: id 3 | task 1011 | graphs reused = 716 2.25.123.651 I slot print_timing: id 3 | task 1011 | graph reallocs = 0 / 0 (same size) / (changed size) 2.25.123.701 I slot release: id 3 | task 1011 | stop processing: n_tokens = 1312, truncated = 0 2.25.169.081 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.941 (> 0.100 thold), f_keep = 0.873 2.25.169.131 I slot launch_slot_: id 3 | task 1118 | processing task, is_child = 0 2.26.635.968 I slot print_timing: id 2 | task 1037 | n_gen = 100, tg = 16.47 t/s, tg_3s = 16.64 t/s 2.27.318.704 I slot print_timing: id 2 | task 1037 | prompt eval time = 525.57 ms / 137 tokens ( 3.84 ms per token, 260.67 tokens per second) 2.27.318.709 I slot print_timing: id 2 | task 1037 | eval time = 6692.99 ms / 113 tokens ( 59.76 ms per token, 16.73 tokens per second) 2.27.318.709 I slot print_timing: id 2 | task 1037 | total time = 7218.56 ms / 250 tokens 2.27.318.710 I slot print_timing: id 2 | task 1037 | graphs reused = 748 2.27.318.710 I slot print_timing: id 2 | task 1037 | graph reallocs = 0 / 0 (same size) / (changed size) 2.27.318.762 I slot release: id 2 | task 1037 | stop processing: n_tokens = 1374, truncated = 0 2.27.376.125 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.834 2.27.376.155 I slot launch_slot_: id 2 | task 1155 | processing task, is_child = 0 2.27.965.306 I slot print_timing: id 0 | task 266 | n_gen = 861, tg = 15.51 t/s, tg_3s = 14.64 t/s 2.28.648.133 I slot print_timing: id 3 | task 1118 | prompt eval time = 414.53 ms / 93 tokens ( 4.46 ms per token, 224.35 tokens per second) 2.28.648.136 I slot print_timing: id 3 | task 1118 | eval time = 3064.46 ms / 53 tokens ( 58.93 ms per token, 16.97 tokens per second) 2.28.648.137 I slot print_timing: id 3 | task 1118 | total time = 3478.99 ms / 146 tokens 2.28.648.137 I slot print_timing: id 3 | task 1118 | graphs reused = 763 2.28.648.137 I slot print_timing: id 3 | task 1118 | graph reallocs = 0 / 0 (same size) / (changed size) 2.28.648.183 I slot release: id 3 | task 1118 | stop processing: n_tokens = 1270, truncated = 0 2.28.694.263 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.902 2.28.694.296 I slot launch_slot_: id 3 | task 1175 | processing task, is_child = 0 2.30.971.510 I slot print_timing: id 0 | task 266 | n_gen = 912, tg = 15.58 t/s, tg_3s = 16.96 t/s 2.31.190.087 I slot print_timing: id 2 | task 1155 | prompt eval time = 430.11 ms / 87 tokens ( 4.94 ms per token, 202.27 tokens per second) 2.31.190.095 I slot print_timing: id 2 | task 1155 | eval time = 3383.81 ms / 59 tokens ( 58.34 ms per token, 17.14 tokens per second) 2.31.190.096 I slot print_timing: id 2 | task 1155 | total time = 3813.92 ms / 146 tokens 2.31.190.097 I slot print_timing: id 2 | task 1155 | graphs reused = 801 2.31.190.098 I slot print_timing: id 2 | task 1155 | graph reallocs = 0 / 0 (same size) / (changed size) 2.31.190.210 I slot release: id 2 | task 1155 | stop processing: n_tokens = 1270, truncated = 0 2.31.251.751 I slot print_timing: id 1 | task 1113 | n_gen = 100, tg = 16.01 t/s, tg_3s = 16.17 t/s 2.31.252.065 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.902 2.31.252.123 I slot launch_slot_: id 2 | task 1218 | processing task, is_child = 0 2.32.970.255 I slot print_timing: id 3 | task 1175 | prompt eval time = 427.82 ms / 98 tokens ( 4.37 ms per token, 229.07 tokens per second) 2.32.970.264 I slot print_timing: id 3 | task 1175 | eval time = 3848.13 ms / 66 tokens ( 59.20 ms per token, 16.89 tokens per second) 2.32.970.265 I slot print_timing: id 3 | task 1175 | total time = 4275.95 ms / 164 tokens 2.32.970.266 I slot print_timing: id 3 | task 1175 | graphs reused = 823 2.32.970.267 I slot print_timing: id 3 | task 1175 | graph reallocs = 0 / 0 (same size) / (changed size) 2.32.970.357 I slot release: id 3 | task 1175 | stop processing: n_tokens = 1288, truncated = 0 2.33.019.820 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.890 2.33.019.869 I slot launch_slot_: id 3 | task 1245 | processing task, is_child = 0 2.34.007.324 I slot print_timing: id 0 | task 266 | n_gen = 955, tg = 15.51 t/s, tg_3s = 14.16 t/s 2.34.270.793 I slot print_timing: id 1 | task 1113 | n_gen = 143, tg = 15.43 t/s, tg_3s = 14.24 t/s 2.35.165.648 I slot print_timing: id 1 | task 1113 | prompt eval time = 540.45 ms / 153 tokens ( 3.53 ms per token, 283.10 tokens per second) 2.35.165.651 I slot print_timing: id 1 | task 1113 | eval time = 10096.87 ms / 160 tokens ( 63.50 ms per token, 15.75 tokens per second) 2.35.165.651 I slot print_timing: id 1 | task 1113 | total time = 10637.32 ms / 313 tokens 2.35.165.652 I slot print_timing: id 1 | task 1113 | graphs reused = 854 2.35.165.652 I slot print_timing: id 1 | task 1113 | graph reallocs = 0 / 0 (same size) / (changed size) 2.35.165.705 I slot release: id 1 | task 1113 | stop processing: n_tokens = 1437, truncated = 0 2.35.222.990 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.797 2.35.223.023 I slot launch_slot_: id 1 | task 1281 | processing task, is_child = 0 2.37.059.564 I slot print_timing: id 0 | task 266 | n_gen = 1005, tg = 15.55 t/s, tg_3s = 16.38 t/s 2.37.220.314 I slot print_timing: id 2 | task 1218 | prompt eval time = 475.12 ms / 105 tokens ( 4.52 ms per token, 221.00 tokens per second) 2.37.220.320 I slot print_timing: id 2 | task 1218 | eval time = 5493.06 ms / 90 tokens ( 61.72 ms per token, 16.20 tokens per second) 2.37.220.322 I slot print_timing: id 2 | task 1218 | total time = 5968.18 ms / 195 tokens 2.37.220.323 I slot print_timing: id 2 | task 1218 | graphs reused = 881 2.37.220.324 I slot print_timing: id 2 | task 1218 | graph reallocs = 0 / 0 (same size) / (changed size) 2.37.220.417 I slot release: id 2 | task 1218 | stop processing: n_tokens = 1319, truncated = 0 2.37.282.623 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.869 2.37.282.701 I slot launch_slot_: id 2 | task 1313 | processing task, is_child = 0 2.38.415.803 I slot print_timing: id 0 | task 266 | prompt eval time = 8857.59 ms / 1243 tokens ( 7.13 ms per token, 140.33 tokens per second) 2.38.415.808 I slot print_timing: id 0 | task 266 | eval time = 65910.90 ms / 1024 tokens ( 64.43 ms per token, 15.52 tokens per second) 2.38.415.809 I slot print_timing: id 0 | task 266 | total time = 74768.49 ms / 2267 tokens 2.38.415.809 I slot print_timing: id 0 | task 266 | graphs reused = 893 2.38.415.809 I slot print_timing: id 0 | task 266 | graph reallocs = 0 / 0 (same size) / (changed size) 2.38.415.858 I slot release: id 0 | task 266 | stop processing: n_tokens = 2266, truncated = 0 2.38.462.392 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.506 2.38.462.421 I slot launch_slot_: id 0 | task 1330 | processing task, is_child = 0 2.39.802.903 I slot print_timing: id 3 | task 1245 | n_gen = 100, tg = 15.66 t/s, tg_3s = 15.82 t/s 2.41.276.593 I slot print_timing: id 3 | task 1245 | prompt eval time = 460.31 ms / 113 tokens ( 4.07 ms per token, 245.48 tokens per second) 2.41.276.601 I slot print_timing: id 3 | task 1245 | eval time = 7796.39 ms / 128 tokens ( 61.39 ms per token, 16.29 tokens per second) 2.41.276.602 I slot print_timing: id 3 | task 1245 | total time = 8256.71 ms / 241 tokens 2.41.276.603 I slot print_timing: id 3 | task 1245 | graphs reused = 938 2.41.276.604 I slot print_timing: id 3 | task 1245 | graph reallocs = 0 / 0 (same size) / (changed size) 2.41.276.723 I slot release: id 3 | task 1245 | stop processing: n_tokens = 1365, truncated = 0 2.41.325.963 I slot print_timing: id 1 | task 1281 | prompt eval time = 486.68 ms / 122 tokens ( 3.99 ms per token, 250.68 tokens per second) 2.41.325.970 I slot print_timing: id 1 | task 1281 | eval time = 5616.25 ms / 94 tokens ( 60.39 ms per token, 16.56 tokens per second) 2.41.325.971 I slot print_timing: id 1 | task 1281 | total time = 6102.93 ms / 216 tokens 2.41.325.972 I slot print_timing: id 1 | task 1281 | graphs reused = 938 2.41.325.972 I slot print_timing: id 1 | task 1281 | graph reallocs = 0 / 0 (same size) / (changed size) 2.41.326.044 I slot release: id 1 | task 1281 | stop processing: n_tokens = 1340, truncated = 0 2.41.326.359 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.855 2.41.326.420 I slot launch_slot_: id 1 | task 1379 | processing task, is_child = 0 2.41.326.579 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.010 MiB) 2.41.326.584 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.166 MiB) 2.41.359.397 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.840 2.41.359.437 I slot launch_slot_: id 3 | task 1380 | processing task, is_child = 0 2.43.798.995 I slot print_timing: id 2 | task 1313 | prompt eval time = 446.27 ms / 96 tokens ( 4.65 ms per token, 215.12 tokens per second) 2.43.799.001 I slot print_timing: id 2 | task 1313 | eval time = 6070.01 ms / 94 tokens ( 65.27 ms per token, 15.32 tokens per second) 2.43.799.002 I slot print_timing: id 2 | task 1313 | total time = 6516.28 ms / 190 tokens 2.43.799.003 I slot print_timing: id 2 | task 1313 | graphs reused = 966 2.43.799.004 I slot print_timing: id 2 | task 1313 | graph reallocs = 0 / 0 (same size) / (changed size) 2.43.799.112 I slot release: id 2 | task 1313 | stop processing: n_tokens = 1314, truncated = 0 2.43.860.456 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.872 2.43.860.534 I slot launch_slot_: id 2 | task 1413 | processing task, is_child = 0 2.44.991.486 I slot print_timing: id 0 | task 1330 | prompt eval time = 450.38 ms / 113 tokens ( 3.99 ms per token, 250.90 tokens per second) 2.44.991.494 I slot print_timing: id 0 | task 1330 | eval time = 6078.67 ms / 93 tokens ( 66.07 ms per token, 15.13 tokens per second) 2.44.991.495 I slot print_timing: id 0 | task 1330 | total time = 6529.06 ms / 206 tokens 2.44.991.496 I slot print_timing: id 0 | task 1330 | graphs reused = 977 2.44.991.498 I slot print_timing: id 0 | task 1330 | graph reallocs = 0 / 0 (same size) / (changed size) 2.44.991.588 I slot release: id 0 | task 1330 | stop processing: n_tokens = 1330, truncated = 0 2.45.041.874 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.862 2.45.041.937 I slot launch_slot_: id 0 | task 1429 | processing task, is_child = 0 2.47.435.697 I slot print_timing: id 3 | task 1380 | prompt eval time = 883.43 ms / 131 tokens ( 6.74 ms per token, 148.28 tokens per second) 2.47.435.702 I slot print_timing: id 3 | task 1380 | eval time = 5188.60 ms / 85 tokens ( 61.77 ms per token, 16.19 tokens per second) 2.47.435.703 I slot print_timing: id 3 | task 1380 | total time = 6072.04 ms / 216 tokens 2.47.435.703 I slot print_timing: id 3 | task 1380 | graphs reused = 1014 2.47.435.704 I slot print_timing: id 3 | task 1380 | graph reallocs = 0 / 0 (same size) / (changed size) 2.47.435.769 I slot release: id 3 | task 1380 | stop processing: n_tokens = 1340, truncated = 0 2.47.482.744 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.855 2.47.482.799 I slot launch_slot_: id 3 | task 1470 | processing task, is_child = 0 2.48.642.814 I slot print_timing: id 1 | task 1379 | n_gen = 100, tg = 15.48 t/s, tg_3s = 15.63 t/s 2.49.125.952 I slot print_timing: id 2 | task 1413 | prompt eval time = 488.06 ms / 117 tokens ( 4.17 ms per token, 239.72 tokens per second) 2.49.125.959 I slot print_timing: id 2 | task 1413 | eval time = 4777.34 ms / 77 tokens ( 62.86 ms per token, 15.91 tokens per second) 2.49.125.960 I slot print_timing: id 2 | task 1413 | total time = 5265.40 ms / 194 tokens 2.49.125.961 I slot print_timing: id 2 | task 1413 | graphs reused = 1034 2.49.125.962 I slot print_timing: id 2 | task 1413 | graph reallocs = 0 / 0 (same size) / (changed size) 2.49.126.074 I slot release: id 2 | task 1413 | stop processing: n_tokens = 1318, truncated = 0 2.49.188.850 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.869 2.49.188.927 I slot launch_slot_: id 2 | task 1495 | processing task, is_child = 0 2.51.174.732 I slot print_timing: id 0 | task 1429 | prompt eval time = 458.27 ms / 127 tokens ( 3.61 ms per token, 277.13 tokens per second) 2.51.174.737 I slot print_timing: id 0 | task 1429 | eval time = 5674.51 ms / 94 tokens ( 61.02 ms per token, 16.39 tokens per second) 2.51.174.739 I slot print_timing: id 0 | task 1429 | total time = 6132.79 ms / 221 tokens 2.51.174.740 I slot print_timing: id 0 | task 1429 | graphs reused = 1062 2.51.174.741 I slot print_timing: id 0 | task 1429 | graph reallocs = 0 / 0 (same size) / (changed size) 2.51.174.837 I slot release: id 0 | task 1429 | stop processing: n_tokens = 1345, truncated = 0 2.51.225.318 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.852 2.51.225.383 I slot launch_slot_: id 0 | task 1528 | processing task, is_child = 0 2.51.662.544 I slot print_timing: id 1 | task 1379 | n_gen = 144, tg = 15.19 t/s, tg_3s = 14.57 t/s 2.53.229.481 I slot print_timing: id 1 | task 1379 | prompt eval time = 887.05 ms / 149 tokens ( 5.95 ms per token, 167.97 tokens per second) 2.53.229.483 I slot print_timing: id 1 | task 1379 | eval time = 10982.98 ms / 174 tokens ( 63.49 ms per token, 15.75 tokens per second) 2.53.229.483 I slot print_timing: id 1 | task 1379 | total time = 11870.03 ms / 323 tokens 2.53.229.484 I slot print_timing: id 1 | task 1379 | graphs reused = 1092 2.53.229.484 I slot print_timing: id 1 | task 1379 | graph reallocs = 0 / 0 (same size) / (changed size) 2.53.229.529 I slot release: id 1 | task 1379 | stop processing: n_tokens = 1447, truncated = 0 2.53.286.554 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.792 2.53.286.599 I slot launch_slot_: id 1 | task 1562 | processing task, is_child = 0 2.54.278.863 I slot print_timing: id 3 | task 1470 | n_gen = 100, tg = 15.75 t/s, tg_3s = 15.91 t/s 2.55.290.796 I slot print_timing: id 3 | task 1470 | prompt eval time = 509.22 ms / 137 tokens ( 3.72 ms per token, 269.04 tokens per second) 2.55.290.807 I slot print_timing: id 3 | task 1470 | eval time = 7298.76 ms / 119 tokens ( 61.85 ms per token, 16.17 tokens per second) 2.55.290.808 I slot print_timing: id 3 | task 1470 | total time = 7807.97 ms / 256 tokens 2.55.290.810 I slot print_timing: id 3 | task 1470 | graphs reused = 1120 2.55.290.811 I slot print_timing: id 3 | task 1470 | graph reallocs = 0 / 0 (same size) / (changed size) 2.55.290.930 I slot release: id 3 | task 1470 | stop processing: n_tokens = 1380, truncated = 0 2.55.340.453 I slot print_timing: id 2 | task 1495 | prompt eval time = 447.76 ms / 96 tokens ( 4.66 ms per token, 214.40 tokens per second) 2.55.340.460 I slot print_timing: id 2 | task 1495 | eval time = 5703.76 ms / 96 tokens ( 60.04 ms per token, 16.66 tokens per second) 2.55.340.462 I slot print_timing: id 2 | task 1495 | total time = 6151.51 ms / 192 tokens 2.55.340.463 I slot print_timing: id 2 | task 1495 | graphs reused = 1120 2.55.340.464 I slot print_timing: id 2 | task 1495 | graph reallocs = 0 / 0 (same size) / (changed size) 2.55.340.535 I slot release: id 2 | task 1495 | stop processing: n_tokens = 1316, truncated = 0 2.55.340.546 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.871 2.55.340.595 I slot launch_slot_: id 2 | task 1595 | processing task, is_child = 0 2.55.340.758 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.068 MiB) 2.55.340.766 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.051 MiB) 2.55.340.768 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.051 MiB) 2.55.365.331 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.830 2.55.365.362 I slot launch_slot_: id 3 | task 1596 | processing task, is_child = 0 2.56.230.291 I slot print_timing: id 0 | task 1528 | prompt eval time = 437.01 ms / 104 tokens ( 4.20 ms per token, 237.98 tokens per second) 2.56.230.296 I slot print_timing: id 0 | task 1528 | eval time = 4567.89 ms / 70 tokens ( 66.20 ms per token, 15.11 tokens per second) 2.56.230.297 I slot print_timing: id 0 | task 1528 | total time = 5004.90 ms / 174 tokens 2.56.230.297 I slot print_timing: id 0 | task 1528 | graphs reused = 1123 2.56.230.297 I slot print_timing: id 0 | task 1528 | graph reallocs = 0 / 0 (same size) / (changed size) 2.56.230.342 I slot release: id 0 | task 1528 | stop processing: n_tokens = 1298, truncated = 0 2.56.276.734 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.883 2.56.276.781 I slot launch_slot_: id 0 | task 1604 | processing task, is_child = 0 2.57.908.342 I slot print_timing: id 1 | task 1562 | prompt eval time = 456.71 ms / 98 tokens ( 4.66 ms per token, 214.58 tokens per second) 2.57.908.347 I slot print_timing: id 1 | task 1562 | eval time = 4165.02 ms / 62 tokens ( 68.28 ms per token, 14.65 tokens per second) 2.57.908.349 I slot print_timing: id 1 | task 1562 | total time = 4621.73 ms / 160 tokens 2.57.908.350 I slot print_timing: id 1 | task 1562 | graphs reused = 1144 2.57.908.351 I slot print_timing: id 1 | task 1562 | graph reallocs = 0 / 0 (same size) / (changed size) 2.57.908.450 I slot release: id 1 | task 1562 | stop processing: n_tokens = 1284, truncated = 0 2.57.970.221 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.918 (> 0.100 thold), f_keep = 0.893 2.57.970.294 I slot launch_slot_: id 1 | task 1630 | processing task, is_child = 0 2.59.205.370 I slot print_timing: id 2 | task 1595 | prompt eval time = 655.30 ms / 102 tokens ( 6.42 ms per token, 155.65 tokens per second) 2.59.205.375 I slot print_timing: id 2 | task 1595 | eval time = 3184.70 ms / 47 tokens ( 69.23 ms per token, 14.44 tokens per second) 2.59.205.376 I slot print_timing: id 2 | task 1595 | total time = 3840.00 ms / 149 tokens 2.59.205.376 I slot print_timing: id 2 | task 1595 | graphs reused = 1156 2.59.205.377 I slot print_timing: id 2 | task 1595 | graph reallocs = 0 / 0 (same size) / (changed size) 2.59.205.425 I slot release: id 2 | task 1595 | stop processing: n_tokens = 1273, truncated = 0 2.59.262.390 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.900 2.59.262.428 I slot launch_slot_: id 2 | task 1648 | processing task, is_child = 0 3.02.247.249 I slot print_timing: id 0 | task 1604 | prompt eval time = 450.82 ms / 122 tokens ( 3.70 ms per token, 270.62 tokens per second) 3.02.247.259 I slot print_timing: id 0 | task 1604 | eval time = 5519.64 ms / 90 tokens ( 62.02 ms per token, 16.12 tokens per second) 3.02.247.260 I slot print_timing: id 0 | task 1604 | total time = 5970.46 ms / 212 tokens 3.02.247.261 I slot print_timing: id 0 | task 1604 | graphs reused = 1202 3.02.247.262 I slot print_timing: id 0 | task 1604 | graph reallocs = 0 / 0 (same size) / (changed size) 3.02.247.355 I slot release: id 0 | task 1604 | stop processing: n_tokens = 1336, truncated = 0 3.02.297.909 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.858 3.02.297.976 I slot launch_slot_: id 0 | task 1699 | processing task, is_child = 0 3.02.694.943 I slot print_timing: id 3 | task 1596 | n_gen = 100, tg = 14.83 t/s, tg_3s = 14.98 t/s 3.02.905.656 I slot print_timing: id 3 | task 1596 | prompt eval time = 651.26 ms / 108 tokens ( 6.03 ms per token, 165.83 tokens per second) 3.02.905.661 I slot print_timing: id 3 | task 1596 | eval time = 6884.78 ms / 104 tokens ( 66.84 ms per token, 14.96 tokens per second) 3.02.905.662 I slot print_timing: id 3 | task 1596 | total time = 7536.04 ms / 212 tokens 3.02.905.662 I slot print_timing: id 3 | task 1596 | graphs reused = 1206 3.02.905.662 I slot print_timing: id 3 | task 1596 | graph reallocs = 0 / 0 (same size) / (changed size) 3.02.905.714 I slot release: id 3 | task 1596 | stop processing: n_tokens = 1336, truncated = 0 3.02.951.355 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.931 (> 0.100 thold), f_keep = 0.858 3.02.951.386 I slot launch_slot_: id 3 | task 1707 | processing task, is_child = 0 3.04.660.503 I slot print_timing: id 1 | task 1630 | prompt eval time = 500.61 ms / 124 tokens ( 4.04 ms per token, 247.70 tokens per second) 3.04.660.508 I slot print_timing: id 1 | task 1630 | eval time = 6189.59 ms / 99 tokens ( 63.16 ms per token, 15.83 tokens per second) 3.04.660.508 I slot print_timing: id 1 | task 1630 | total time = 6690.20 ms / 223 tokens 3.04.660.509 I slot print_timing: id 1 | task 1630 | graphs reused = 1229 3.04.660.509 I slot print_timing: id 1 | task 1630 | graph reallocs = 0 / 0 (same size) / (changed size) 3.04.660.557 I slot release: id 1 | task 1630 | stop processing: n_tokens = 1347, truncated = 0 3.04.718.428 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.851 3.04.718.477 I slot launch_slot_: id 1 | task 1735 | processing task, is_child = 0 3.05.950.524 I slot print_timing: id 2 | task 1648 | n_gen = 100, tg = 15.94 t/s, tg_3s = 16.10 t/s 3.06.218.262 I slot print_timing: id 0 | task 1699 | prompt eval time = 396.54 ms / 86 tokens ( 4.61 ms per token, 216.88 tokens per second) 3.06.218.267 I slot print_timing: id 0 | task 1699 | eval time = 3523.73 ms / 55 tokens ( 65.25 ms per token, 15.32 tokens per second) 3.06.218.268 I slot print_timing: id 0 | task 1699 | total time = 3920.27 ms / 141 tokens 3.06.218.268 I slot print_timing: id 0 | task 1699 | graphs reused = 1248 3.06.218.269 I slot print_timing: id 0 | task 1699 | graph reallocs = 0 / 0 (same size) / (changed size) 3.06.218.355 I slot release: id 0 | task 1699 | stop processing: n_tokens = 1265, truncated = 0 3.06.268.552 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.942 (> 0.100 thold), f_keep = 0.906 3.06.268.613 I slot launch_slot_: id 0 | task 1759 | processing task, is_child = 0 3.07.194.771 I slot print_timing: id 3 | task 1707 | prompt eval time = 454.24 ms / 106 tokens ( 4.29 ms per token, 233.36 tokens per second) 3.07.194.776 I slot print_timing: id 3 | task 1707 | eval time = 3789.14 ms / 61 tokens ( 63.15 ms per token, 15.83 tokens per second) 3.07.194.777 I slot print_timing: id 3 | task 1707 | total time = 4243.38 ms / 167 tokens 3.07.194.778 I slot print_timing: id 3 | task 1707 | graphs reused = 1258 3.07.194.778 I slot print_timing: id 3 | task 1707 | graph reallocs = 0 / 0 (same size) / (changed size) 3.07.194.822 I slot release: id 3 | task 1707 | stop processing: n_tokens = 1291, truncated = 0 3.07.240.160 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.888 3.07.240.193 I slot launch_slot_: id 3 | task 1773 | processing task, is_child = 0 3.08.126.869 I slot print_timing: id 2 | task 1648 | prompt eval time = 478.43 ms / 111 tokens ( 4.31 ms per token, 232.01 tokens per second) 3.08.126.872 I slot print_timing: id 2 | task 1648 | eval time = 8386.00 ms / 129 tokens ( 65.52 ms per token, 15.26 tokens per second) 3.08.126.872 I slot print_timing: id 2 | task 1648 | total time = 8864.43 ms / 240 tokens 3.08.126.873 I slot print_timing: id 2 | task 1648 | graphs reused = 1265 3.08.126.873 I slot print_timing: id 2 | task 1648 | graph reallocs = 0 / 0 (same size) / (changed size) 3.08.126.918 I slot release: id 2 | task 1648 | stop processing: n_tokens = 1364, truncated = 0 3.08.183.718 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.840 3.08.183.754 I slot launch_slot_: id 2 | task 1785 | processing task, is_child = 0 3.10.647.777 I slot print_timing: id 1 | task 1735 | prompt eval time = 445.47 ms / 98 tokens ( 4.55 ms per token, 219.99 tokens per second) 3.10.647.783 I slot print_timing: id 1 | task 1735 | eval time = 5483.82 ms / 86 tokens ( 64.52 ms per token, 15.50 tokens per second) 3.10.647.784 I slot print_timing: id 1 | task 1735 | total time = 5929.29 ms / 184 tokens 3.10.647.784 I slot print_timing: id 1 | task 1735 | graphs reused = 1301 3.10.647.784 I slot print_timing: id 1 | task 1735 | graph reallocs = 0 / 0 (same size) / (changed size) 3.10.647.830 I slot release: id 1 | task 1735 | stop processing: n_tokens = 1308, truncated = 0 3.10.705.016 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.876 3.10.705.054 I slot launch_slot_: id 1 | task 1827 | processing task, is_child = 0 3.11.669.150 I slot print_timing: id 3 | task 1773 | prompt eval time = 467.84 ms / 121 tokens ( 3.87 ms per token, 258.64 tokens per second) 3.11.669.155 I slot print_timing: id 3 | task 1773 | eval time = 3961.11 ms / 63 tokens ( 63.89 ms per token, 15.65 tokens per second) 3.11.669.156 I slot print_timing: id 3 | task 1773 | total time = 4428.95 ms / 184 tokens 3.11.669.156 I slot print_timing: id 3 | task 1773 | graphs reused = 1310 3.11.669.156 I slot print_timing: id 3 | task 1773 | graph reallocs = 0 / 0 (same size) / (changed size) 3.11.669.202 I slot release: id 3 | task 1773 | stop processing: n_tokens = 1308, truncated = 0 3.11.714.997 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.876 3.11.715.036 I slot launch_slot_: id 3 | task 1841 | processing task, is_child = 0 3.13.050.566 I slot print_timing: id 0 | task 1759 | prompt eval time = 402.01 ms / 91 tokens ( 4.42 ms per token, 226.36 tokens per second) 3.13.050.571 I slot print_timing: id 0 | task 1759 | eval time = 6379.93 ms / 95 tokens ( 67.87 ms per token, 14.73 tokens per second) 3.13.050.572 I slot print_timing: id 0 | task 1759 | total time = 6781.94 ms / 186 tokens 3.13.050.572 I slot print_timing: id 0 | task 1759 | graphs reused = 1325 3.13.050.573 I slot print_timing: id 0 | task 1759 | graph reallocs = 0 / 0 (same size) / (changed size) 3.13.050.616 I slot release: id 0 | task 1759 | stop processing: n_tokens = 1310, truncated = 0 3.13.096.993 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.875 3.13.097.028 I slot launch_slot_: id 0 | task 1861 | processing task, is_child = 0 3.13.697.387 I slot print_timing: id 2 | task 1785 | prompt eval time = 475.87 ms / 105 tokens ( 4.53 ms per token, 220.65 tokens per second) 3.13.697.393 I slot print_timing: id 2 | task 1785 | eval time = 5037.75 ms / 77 tokens ( 66.29 ms per token, 15.09 tokens per second) 3.13.697.393 I slot print_timing: id 2 | task 1785 | total time = 5513.63 ms / 182 tokens 3.13.697.394 I slot print_timing: id 2 | task 1785 | graphs reused = 1328 3.13.697.394 I slot print_timing: id 2 | task 1785 | graph reallocs = 0 / 0 (same size) / (changed size) 3.13.697.439 I slot release: id 2 | task 1785 | stop processing: n_tokens = 1306, truncated = 0 3.13.754.484 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.893 (> 0.100 thold), f_keep = 0.877 3.13.754.525 I slot launch_slot_: id 2 | task 1868 | processing task, is_child = 0 3.16.058.060 I slot print_timing: id 1 | task 1827 | prompt eval time = 441.97 ms / 95 tokens ( 4.65 ms per token, 214.94 tokens per second) 3.16.058.068 I slot print_timing: id 1 | task 1827 | eval time = 4911.02 ms / 72 tokens ( 69.17 ms per token, 14.46 tokens per second) 3.16.058.069 I slot print_timing: id 1 | task 1827 | total time = 5353.00 ms / 167 tokens 3.16.058.070 I slot print_timing: id 1 | task 1827 | graphs reused = 1360 3.16.058.071 I slot print_timing: id 1 | task 1827 | graph reallocs = 0 / 0 (same size) / (changed size) 3.16.058.161 I slot release: id 1 | task 1827 | stop processing: n_tokens = 1291, truncated = 0 3.16.120.230 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.924 (> 0.100 thold), f_keep = 0.888 3.16.120.313 I slot launch_slot_: id 1 | task 1905 | processing task, is_child = 0 3.17.837.186 I slot print_timing: id 0 | task 1861 | prompt eval time = 441.43 ms / 110 tokens ( 4.01 ms per token, 249.19 tokens per second) 3.17.837.194 I slot print_timing: id 0 | task 1861 | eval time = 4298.71 ms / 66 tokens ( 66.13 ms per token, 15.12 tokens per second) 3.17.837.196 I slot print_timing: id 0 | task 1861 | total time = 4740.15 ms / 176 tokens 3.17.837.197 I slot print_timing: id 0 | task 1861 | graphs reused = 1382 3.17.837.198 I slot print_timing: id 0 | task 1861 | graph reallocs = 0 / 0 (same size) / (changed size) 3.17.837.287 I slot release: id 0 | task 1861 | stop processing: n_tokens = 1300, truncated = 0 3.17.887.945 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.882 3.17.887.997 I slot launch_slot_: id 0 | task 1932 | processing task, is_child = 0 3.18.353.956 I slot print_timing: id 3 | task 1841 | prompt eval time = 497.93 ms / 144 tokens ( 3.46 ms per token, 289.20 tokens per second) 3.18.353.962 I slot print_timing: id 3 | task 1841 | eval time = 6140.99 ms / 88 tokens ( 70.59 ms per token, 14.17 tokens per second) 3.18.353.963 I slot print_timing: id 3 | task 1841 | total time = 6638.91 ms / 232 tokens 3.18.353.963 I slot print_timing: id 3 | task 1841 | graphs reused = 1383 3.18.353.964 I slot print_timing: id 3 | task 1841 | graph reallocs = 0 / 0 (same size) / (changed size) 3.18.354.010 I slot release: id 3 | task 1841 | stop processing: n_tokens = 1356, truncated = 0 3.18.399.685 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.950 (> 0.100 thold), f_keep = 0.845 3.18.399.717 I slot launch_slot_: id 3 | task 1936 | processing task, is_child = 0 3.20.589.390 I slot print_timing: id 2 | task 1868 | n_gen = 100, tg = 15.71 t/s, tg_3s = 15.87 t/s 3.20.748.239 I slot print_timing: id 1 | task 1905 | prompt eval time = 485.63 ms / 115 tokens ( 4.22 ms per token, 236.81 tokens per second) 3.20.748.244 I slot print_timing: id 1 | task 1905 | eval time = 4142.28 ms / 67 tokens ( 62.76 ms per token, 15.93 tokens per second) 3.20.748.245 I slot print_timing: id 1 | task 1905 | total time = 4627.91 ms / 182 tokens 3.20.748.246 I slot print_timing: id 1 | task 1905 | graphs reused = 1419 3.20.748.247 I slot print_timing: id 1 | task 1905 | graph reallocs = 0 / 0 (same size) / (changed size) 3.20.748.335 I slot release: id 1 | task 1905 | stop processing: n_tokens = 1306, truncated = 0 3.20.809.891 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.877 3.20.809.982 I slot launch_slot_: id 1 | task 1977 | processing task, is_child = 0 3.22.143.423 I slot print_timing: id 3 | task 1936 | prompt eval time = 400.94 ms / 81 tokens ( 4.95 ms per token, 202.03 tokens per second) 3.22.143.432 I slot print_timing: id 3 | task 1936 | eval time = 3342.75 ms / 57 tokens ( 59.69 ms per token, 16.75 tokens per second) 3.22.143.434 I slot print_timing: id 3 | task 1936 | total time = 3743.69 ms / 138 tokens 3.22.143.435 I slot print_timing: id 3 | task 1936 | graphs reused = 1434 3.22.143.436 I slot print_timing: id 3 | task 1936 | graph reallocs = 0 / 0 (same size) / (changed size) 3.22.143.584 I slot release: id 3 | task 1936 | stop processing: n_tokens = 1262, truncated = 0 3.22.193.393 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.908 3.22.193.449 I slot launch_slot_: id 3 | task 1997 | processing task, is_child = 0 3.23.348.639 I slot print_timing: id 2 | task 1868 | prompt eval time = 534.55 ms / 158 tokens ( 3.38 ms per token, 295.58 tokens per second) 3.23.348.646 I slot print_timing: id 2 | task 1868 | eval time = 9059.56 ms / 138 tokens ( 66.13 ms per token, 15.12 tokens per second) 3.23.348.648 I slot print_timing: id 2 | task 1868 | total time = 9594.10 ms / 296 tokens 3.23.348.649 I slot print_timing: id 2 | task 1868 | graphs reused = 1446 3.23.348.650 I slot print_timing: id 2 | task 1868 | graph reallocs = 0 / 0 (same size) / (changed size) 3.23.348.763 I slot release: id 2 | task 1868 | stop processing: n_tokens = 1420, truncated = 0 3.23.412.282 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.807 3.23.412.401 I slot launch_slot_: id 2 | task 2014 | processing task, is_child = 0 3.24.982.291 I slot print_timing: id 0 | task 1932 | n_gen = 100, tg = 14.93 t/s, tg_3s = 15.09 t/s 3.26.154.222 I slot print_timing: id 1 | task 1977 | prompt eval time = 475.10 ms / 104 tokens ( 4.57 ms per token, 218.90 tokens per second) 3.26.154.231 I slot print_timing: id 1 | task 1977 | eval time = 4869.12 ms / 79 tokens ( 62.42 ms per token, 16.02 tokens per second) 3.26.154.232 I slot print_timing: id 1 | task 1977 | total time = 5344.22 ms / 183 tokens 3.26.154.233 I slot print_timing: id 1 | task 1977 | graphs reused = 1488 3.26.154.234 I slot print_timing: id 1 | task 1977 | graph reallocs = 0 / 0 (same size) / (changed size) 3.26.154.334 I slot release: id 1 | task 1977 | stop processing: n_tokens = 1307, truncated = 0 3.26.216.404 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.916 (> 0.100 thold), f_keep = 0.877 3.26.216.477 I slot launch_slot_: id 1 | task 2061 | processing task, is_child = 0 3.26.718.166 I slot print_timing: id 3 | task 1997 | prompt eval time = 474.08 ms / 125 tokens ( 3.79 ms per token, 263.67 tokens per second) 3.26.718.171 I slot print_timing: id 3 | task 1997 | eval time = 4050.63 ms / 63 tokens ( 65.33 ms per token, 15.31 tokens per second) 3.26.718.171 I slot print_timing: id 3 | task 1997 | total time = 4524.71 ms / 188 tokens 3.26.718.172 I slot print_timing: id 3 | task 1997 | graphs reused = 1488 3.26.718.172 I slot print_timing: id 3 | task 1997 | graph reallocs = 0 / 0 (same size) / (changed size) 3.26.718.226 I slot release: id 3 | task 1997 | stop processing: n_tokens = 1312, truncated = 0 3.26.763.861 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.873 3.26.763.893 I slot launch_slot_: id 3 | task 2065 | processing task, is_child = 0 3.28.015.155 I slot print_timing: id 0 | task 1932 | n_gen = 143, tg = 14.70 t/s, tg_3s = 14.18 t/s 3.29.194.735 I slot print_timing: id 0 | task 1932 | prompt eval time = 465.54 ms / 128 tokens ( 3.64 ms per token, 274.95 tokens per second) 3.29.194.741 I slot print_timing: id 0 | task 1932 | eval time = 10841.19 ms / 165 tokens ( 66.10 ms per token, 15.13 tokens per second) 3.29.194.742 I slot print_timing: id 0 | task 1932 | total time = 11306.73 ms / 293 tokens 3.29.194.743 I slot print_timing: id 0 | task 1932 | graphs reused = 1524 3.29.194.744 I slot print_timing: id 0 | task 1932 | graph reallocs = 0 / 0 (same size) / (changed size) 3.29.194.843 I slot release: id 0 | task 1932 | stop processing: n_tokens = 1417, truncated = 0 3.29.244.693 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.811 3.29.244.751 I slot launch_slot_: id 0 | task 2106 | processing task, is_child = 0 3.30.208.551 I slot print_timing: id 2 | task 2014 | n_gen = 100, tg = 15.65 t/s, tg_3s = 15.81 t/s 3.30.580.851 I slot print_timing: id 2 | task 2014 | prompt eval time = 472.10 ms / 103 tokens ( 4.58 ms per token, 218.18 tokens per second) 3.30.580.867 I slot print_timing: id 2 | task 2014 | eval time = 6696.34 ms / 107 tokens ( 63.17 ms per token, 15.83 tokens per second) 3.30.580.868 I slot print_timing: id 2 | task 2014 | total time = 7168.43 ms / 210 tokens 3.30.580.870 I slot print_timing: id 2 | task 2014 | graphs reused = 1541 3.30.580.876 I slot print_timing: id 2 | task 2014 | graph reallocs = 0 / 0 (same size) / (changed size) 3.30.580.967 I slot release: id 2 | task 2014 | stop processing: n_tokens = 1334, truncated = 0 3.30.642.919 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.859 3.30.642.998 I slot launch_slot_: id 2 | task 2127 | processing task, is_child = 0 3.31.615.576 I slot print_timing: id 1 | task 2061 | prompt eval time = 501.38 ms / 126 tokens ( 3.98 ms per token, 251.31 tokens per second) 3.31.615.581 I slot print_timing: id 1 | task 2061 | eval time = 4897.71 ms / 74 tokens ( 67.09 ms per token, 14.90 tokens per second) 3.31.615.582 I slot print_timing: id 1 | task 2061 | total time = 5399.09 ms / 200 tokens 3.31.615.582 I slot print_timing: id 1 | task 2061 | graphs reused = 1550 3.31.615.583 I slot print_timing: id 1 | task 2061 | graph reallocs = 0 / 0 (same size) / (changed size) 3.31.615.632 I slot release: id 1 | task 2061 | stop processing: n_tokens = 1324, truncated = 0 3.31.672.685 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.866 3.31.672.720 I slot launch_slot_: id 1 | task 2141 | processing task, is_child = 0 3.33.628.172 I slot print_timing: id 3 | task 2065 | n_gen = 100, tg = 15.47 t/s, tg_3s = 15.63 t/s 3.35.011.586 I slot print_timing: id 2 | task 2127 | prompt eval time = 449.20 ms / 100 tokens ( 4.49 ms per token, 222.62 tokens per second) 3.35.011.593 I slot print_timing: id 2 | task 2127 | eval time = 3919.37 ms / 66 tokens ( 60.30 ms per token, 16.58 tokens per second) 3.35.011.594 I slot print_timing: id 2 | task 2127 | total time = 4368.57 ms / 166 tokens 3.35.011.595 I slot print_timing: id 2 | task 2127 | graphs reused = 1601 3.35.011.596 I slot print_timing: id 2 | task 2127 | graph reallocs = 0 / 0 (same size) / (changed size) 3.35.011.707 I slot release: id 2 | task 2127 | stop processing: n_tokens = 1290, truncated = 0 3.35.074.237 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.944 (> 0.100 thold), f_keep = 0.888 3.35.074.313 I slot launch_slot_: id 2 | task 2197 | processing task, is_child = 0 3.35.617.588 I slot print_timing: id 0 | task 2106 | prompt eval time = 435.32 ms / 108 tokens ( 4.03 ms per token, 248.09 tokens per second) 3.35.617.594 I slot print_timing: id 0 | task 2106 | eval time = 5937.51 ms / 91 tokens ( 65.97 ms per token, 15.16 tokens per second) 3.35.617.594 I slot print_timing: id 0 | task 2106 | total time = 6372.83 ms / 199 tokens 3.35.617.595 I slot print_timing: id 0 | task 2106 | graphs reused = 1602 3.35.617.595 I slot print_timing: id 0 | task 2106 | graph reallocs = 0 / 0 (same size) / (changed size) 3.35.617.640 I slot release: id 0 | task 2106 | stop processing: n_tokens = 1323, truncated = 0 3.35.664.145 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.949 (> 0.100 thold), f_keep = 0.866 3.35.664.181 I slot launch_slot_: id 0 | task 2203 | processing task, is_child = 0 3.36.265.168 I slot print_timing: id 1 | task 2141 | prompt eval time = 567.85 ms / 171 tokens ( 3.32 ms per token, 301.14 tokens per second) 3.36.265.173 I slot print_timing: id 1 | task 2141 | eval time = 4024.59 ms / 65 tokens ( 62.88 ms per token, 15.90 tokens per second) 3.36.265.174 I slot print_timing: id 1 | task 2141 | total time = 4592.44 ms / 236 tokens 3.36.265.174 I slot print_timing: id 1 | task 2141 | graphs reused = 1606 3.36.265.175 I slot print_timing: id 1 | task 2141 | graph reallocs = 0 / 0 (same size) / (changed size) 3.36.265.222 I slot release: id 1 | task 2141 | stop processing: n_tokens = 1360, truncated = 0 3.36.322.356 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.843 3.36.322.397 I slot launch_slot_: id 1 | task 2211 | processing task, is_child = 0 3.36.695.563 I slot print_timing: id 3 | task 2065 | n_gen = 140, tg = 14.69 t/s, tg_3s = 13.04 t/s 3.37.349.246 I slot print_timing: id 3 | task 2065 | prompt eval time = 466.47 ms / 125 tokens ( 3.73 ms per token, 267.97 tokens per second) 3.37.349.257 I slot print_timing: id 3 | task 2065 | eval time = 10118.88 ms / 151 tokens ( 67.46 ms per token, 14.82 tokens per second) 3.37.349.258 I slot print_timing: id 3 | task 2065 | total time = 10585.34 ms / 276 tokens 3.37.349.260 I slot print_timing: id 3 | task 2065 | graphs reused = 1615 3.37.349.261 I slot print_timing: id 3 | task 2065 | graph reallocs = 0 / 0 (same size) / (changed size) 3.37.349.373 I slot release: id 3 | task 2065 | stop processing: n_tokens = 1400, truncated = 0 3.37.398.861 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.819 3.37.398.929 I slot launch_slot_: id 3 | task 2225 | processing task, is_child = 0 3.39.651.287 I slot print_timing: id 1 | task 2211 | prompt eval time = 480.57 ms / 114 tokens ( 4.22 ms per token, 237.22 tokens per second) 3.39.651.289 I slot print_timing: id 1 | task 2211 | eval time = 2848.30 ms / 49 tokens ( 59.34 ms per token, 16.85 tokens per second) 3.39.651.290 I slot print_timing: id 1 | task 2211 | total time = 3328.88 ms / 163 tokens 3.39.651.290 I slot print_timing: id 1 | task 2211 | graphs reused = 1648 3.39.651.291 I slot print_timing: id 1 | task 2211 | graph reallocs = 0 / 0 (same size) / (changed size) 3.39.651.337 I slot release: id 1 | task 2211 | stop processing: n_tokens = 1287, truncated = 0 3.39.707.940 I slot print_timing: id 0 | task 2203 | prompt eval time = 390.49 ms / 82 tokens ( 4.76 ms per token, 209.99 tokens per second) 3.39.707.942 I slot print_timing: id 0 | task 2203 | eval time = 3653.26 ms / 57 tokens ( 65.24 ms per token, 15.33 tokens per second) 3.39.707.943 I slot print_timing: id 0 | task 2203 | total time = 4043.75 ms / 139 tokens 3.39.707.943 I slot print_timing: id 0 | task 2203 | graphs reused = 1648 3.39.707.944 I slot print_timing: id 0 | task 2203 | graph reallocs = 0 / 0 (same size) / (changed size) 3.39.707.986 I slot release: id 0 | task 2203 | stop processing: n_tokens = 1263, truncated = 0 3.39.708.301 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.907 3.39.708.334 I slot launch_slot_: id 0 | task 2264 | processing task, is_child = 0 3.39.708.402 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.130 MiB) 3.39.708.406 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.188 MiB) 3.39.708.408 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.149 MiB) 3.39.730.996 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.890 3.39.731.035 I slot launch_slot_: id 1 | task 2265 | processing task, is_child = 0 3.41.360.554 I slot print_timing: id 3 | task 2225 | prompt eval time = 424.80 ms / 98 tokens ( 4.33 ms per token, 230.70 tokens per second) 3.41.360.559 I slot print_timing: id 3 | task 2225 | eval time = 3536.82 ms / 58 tokens ( 62.05 ms per token, 16.12 tokens per second) 3.41.360.560 I slot print_timing: id 3 | task 2225 | total time = 3961.62 ms / 156 tokens 3.41.360.561 I slot print_timing: id 3 | task 2225 | graphs reused = 1666 3.41.360.561 I slot print_timing: id 3 | task 2225 | graph reallocs = 0 / 0 (same size) / (changed size) 3.41.360.606 I slot release: id 3 | task 2225 | stop processing: n_tokens = 1280, truncated = 0 3.41.406.251 I slot print_timing: id 2 | task 2197 | prompt eval time = 437.02 ms / 89 tokens ( 4.91 ms per token, 203.65 tokens per second) 3.41.406.257 I slot print_timing: id 2 | task 2197 | eval time = 5894.91 ms / 84 tokens ( 71.02 ms per token, 14.08 tokens per second) 3.41.406.257 I slot print_timing: id 2 | task 2197 | total time = 6331.93 ms / 173 tokens 3.41.406.258 I slot print_timing: id 2 | task 2197 | graphs reused = 1666 3.41.406.258 I slot print_timing: id 2 | task 2197 | graph reallocs = 0 / 0 (same size) / (changed size) 3.41.406.299 I slot release: id 2 | task 2197 | stop processing: n_tokens = 1297, truncated = 0 3.41.406.307 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.884 3.41.406.335 I slot launch_slot_: id 2 | task 2288 | processing task, is_child = 0 3.41.406.403 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.403 MiB) 3.41.406.409 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.051 MiB) 3.41.424.650 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.895 3.41.424.679 I slot launch_slot_: id 3 | task 2289 | processing task, is_child = 0 3.44.442.662 I slot print_timing: id 1 | task 2265 | prompt eval time = 631.57 ms / 97 tokens ( 6.51 ms per token, 153.59 tokens per second) 3.44.442.671 I slot print_timing: id 1 | task 2265 | eval time = 4076.80 ms / 67 tokens ( 61.77 ms per token, 16.19 tokens per second) 3.44.442.674 I slot print_timing: id 1 | task 2265 | total time = 4708.36 ms / 164 tokens 3.44.442.675 I slot print_timing: id 1 | task 2265 | graphs reused = 1708 3.44.442.676 I slot print_timing: id 1 | task 2265 | graph reallocs = 0 / 0 (same size) / (changed size) 3.44.442.781 I slot release: id 1 | task 2265 | stop processing: n_tokens = 1288, truncated = 0 3.44.504.204 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.890 3.44.504.279 I slot launch_slot_: id 1 | task 2337 | processing task, is_child = 0 3.46.387.849 I slot print_timing: id 2 | task 2288 | prompt eval time = 671.12 ms / 113 tokens ( 5.94 ms per token, 168.38 tokens per second) 3.46.387.855 I slot print_timing: id 2 | task 2288 | eval time = 4292.04 ms / 74 tokens ( 58.80 ms per token, 17.01 tokens per second) 3.46.387.855 I slot print_timing: id 2 | task 2288 | total time = 4963.16 ms / 187 tokens 3.46.387.856 I slot print_timing: id 2 | task 2288 | graphs reused = 1733 3.46.387.856 I slot print_timing: id 2 | task 2288 | graph reallocs = 0 / 0 (same size) / (changed size) 3.46.387.905 I slot release: id 2 | task 2288 | stop processing: n_tokens = 1311, truncated = 0 3.46.445.014 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.874 3.46.445.050 I slot launch_slot_: id 2 | task 2367 | processing task, is_child = 0 3.46.978.151 I slot print_timing: id 0 | task 2264 | n_gen = 100, tg = 14.97 t/s, tg_3s = 15.12 t/s 3.47.395.329 I slot print_timing: id 3 | task 2289 | prompt eval time = 668.09 ms / 119 tokens ( 5.61 ms per token, 178.12 tokens per second) 3.47.395.335 I slot print_timing: id 3 | task 2289 | eval time = 5299.31 ms / 86 tokens ( 62.34 ms per token, 16.04 tokens per second) 3.47.395.336 I slot print_timing: id 3 | task 2289 | total time = 5967.40 ms / 205 tokens 3.47.395.336 I slot print_timing: id 3 | task 2289 | graphs reused = 1741 3.47.395.337 I slot print_timing: id 3 | task 2289 | graph reallocs = 0 / 0 (same size) / (changed size) 3.47.395.384 I slot release: id 3 | task 2289 | stop processing: n_tokens = 1329, truncated = 0 3.47.441.455 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.863 3.47.441.484 I slot launch_slot_: id 3 | task 2380 | processing task, is_child = 0 3.49.879.066 I slot print_timing: id 0 | task 2264 | prompt eval time = 634.66 ms / 109 tokens ( 5.82 ms per token, 171.75 tokens per second) 3.49.879.072 I slot print_timing: id 0 | task 2264 | eval time = 9513.37 ms / 149 tokens ( 64.28 ms per token, 15.56 tokens per second) 3.49.879.072 I slot print_timing: id 0 | task 2264 | total time = 10148.02 ms / 258 tokens 3.49.879.073 I slot print_timing: id 0 | task 2264 | graphs reused = 1778 3.49.879.073 I slot print_timing: id 0 | task 2264 | graph reallocs = 0 / 0 (same size) / (changed size) 3.49.879.116 I slot release: id 0 | task 2264 | stop processing: n_tokens = 1382, truncated = 0 3.49.926.042 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.829 3.49.926.073 I slot launch_slot_: id 0 | task 2422 | processing task, is_child = 0 3.51.223.712 I slot print_timing: id 1 | task 2337 | n_gen = 100, tg = 15.99 t/s, tg_3s = 16.15 t/s 3.51.541.472 I slot print_timing: id 3 | task 2380 | prompt eval time = 450.37 ms / 109 tokens ( 4.13 ms per token, 242.02 tokens per second) 3.51.541.478 I slot print_timing: id 3 | task 2380 | eval time = 3649.60 ms / 65 tokens ( 57.03 ms per token, 17.54 tokens per second) 3.51.541.479 I slot print_timing: id 3 | task 2380 | total time = 4099.97 ms / 174 tokens 3.51.541.480 I slot print_timing: id 3 | task 2380 | graphs reused = 1801 3.51.541.481 I slot print_timing: id 3 | task 2380 | graph reallocs = 0 / 0 (same size) / (changed size) 3.51.541.596 I slot release: id 3 | task 2380 | stop processing: n_tokens = 1298, truncated = 0 3.51.591.157 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.883 3.51.591.224 I slot launch_slot_: id 3 | task 2449 | processing task, is_child = 0 3.53.064.256 I slot print_timing: id 2 | task 2367 | n_gen = 100, tg = 16.12 t/s, tg_3s = 16.29 t/s 3.53.169.517 I slot print_timing: id 1 | task 2337 | prompt eval time = 527.02 ms / 134 tokens ( 3.93 ms per token, 254.26 tokens per second) 3.53.169.527 I slot print_timing: id 1 | task 2337 | eval time = 8138.21 ms / 131 tokens ( 62.60 ms per token, 15.97 tokens per second) 3.53.169.528 I slot print_timing: id 1 | task 2337 | total time = 8665.22 ms / 265 tokens 3.53.169.529 I slot print_timing: id 1 | task 2337 | graphs reused = 1822 3.53.169.530 I slot print_timing: id 1 | task 2337 | graph reallocs = 0 / 0 (same size) / (changed size) 3.53.169.636 I slot release: id 1 | task 2337 | stop processing: n_tokens = 1389, truncated = 0 3.53.236.962 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.825 3.53.237.022 I slot launch_slot_: id 1 | task 2475 | processing task, is_child = 0 3.54.205.387 I slot print_timing: id 2 | task 2367 | prompt eval time = 479.20 ms / 112 tokens ( 4.28 ms per token, 233.72 tokens per second) 3.54.205.392 I slot print_timing: id 2 | task 2367 | eval time = 7281.12 ms / 114 tokens ( 64.43 ms per token, 15.52 tokens per second) 3.54.205.392 I slot print_timing: id 2 | task 2367 | total time = 7760.33 ms / 226 tokens 3.54.205.393 I slot print_timing: id 2 | task 2367 | graphs reused = 1830 3.54.205.393 I slot print_timing: id 2 | task 2367 | graph reallocs = 0 / 0 (same size) / (changed size) 3.54.205.438 I slot release: id 2 | task 2367 | stop processing: n_tokens = 1350, truncated = 0 3.54.262.293 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.849 3.54.262.333 I slot launch_slot_: id 2 | task 2488 | processing task, is_child = 0 3.55.688.443 I slot print_timing: id 3 | task 2449 | prompt eval time = 424.65 ms / 96 tokens ( 4.42 ms per token, 226.07 tokens per second) 3.55.688.453 I slot print_timing: id 3 | task 2449 | eval time = 3672.55 ms / 54 tokens ( 69.29 ms per token, 14.43 tokens per second) 3.55.688.454 I slot print_timing: id 3 | task 2449 | total time = 4097.20 ms / 150 tokens 3.55.688.455 I slot print_timing: id 3 | task 2449 | graphs reused = 1845 3.55.688.456 I slot print_timing: id 3 | task 2449 | graph reallocs = 0 / 0 (same size) / (changed size) 3.55.688.580 I slot release: id 3 | task 2449 | stop processing: n_tokens = 1274, truncated = 0 3.55.738.668 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.900 3.55.738.730 I slot launch_slot_: id 3 | task 2508 | processing task, is_child = 0 3.56.779.414 I slot print_timing: id 0 | task 2422 | prompt eval time = 406.96 ms / 95 tokens ( 4.28 ms per token, 233.44 tokens per second) 3.56.779.417 I slot print_timing: id 0 | task 2422 | eval time = 6446.38 ms / 94 tokens ( 69.32 ms per token, 14.43 tokens per second) 3.56.779.417 I slot print_timing: id 0 | task 2422 | total time = 6853.33 ms / 189 tokens 3.56.779.418 I slot print_timing: id 0 | task 2422 | graphs reused = 1855 3.56.779.418 I slot print_timing: id 0 | task 2422 | graph reallocs = 0 / 0 (same size) / (changed size) 3.56.779.468 I slot release: id 0 | task 2422 | stop processing: n_tokens = 1313, truncated = 0 3.56.825.737 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.873 3.56.825.774 I slot launch_slot_: id 0 | task 2523 | processing task, is_child = 0 4.00.120.637 I slot print_timing: id 1 | task 2475 | n_gen = 100, tg = 15.50 t/s, tg_3s = 15.65 t/s 4.00.383.555 I slot print_timing: id 1 | task 2475 | prompt eval time = 495.68 ms / 122 tokens ( 4.06 ms per token, 246.12 tokens per second) 4.00.383.560 I slot print_timing: id 1 | task 2475 | eval time = 6650.83 ms / 105 tokens ( 63.95 ms per token, 15.64 tokens per second) 4.00.383.561 I slot print_timing: id 1 | task 2475 | total time = 7146.52 ms / 227 tokens 4.00.383.562 I slot print_timing: id 1 | task 2475 | graphs reused = 1914 4.00.383.563 I slot print_timing: id 1 | task 2475 | graph reallocs = 0 / 0 (same size) / (changed size) 4.00.383.638 I slot release: id 1 | task 2475 | stop processing: n_tokens = 1351, truncated = 0 4.00.443.645 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.848 4.00.443.711 I slot launch_slot_: id 1 | task 2586 | processing task, is_child = 0 4.01.135.464 I slot print_timing: id 2 | task 2488 | n_gen = 100, tg = 15.70 t/s, tg_3s = 15.86 t/s 4.02.128.108 I slot print_timing: id 3 | task 2508 | n_gen = 100, tg = 16.71 t/s, tg_3s = 16.88 t/s 4.02.396.415 I slot print_timing: id 0 | task 2523 | prompt eval time = 434.62 ms / 104 tokens ( 4.18 ms per token, 239.29 tokens per second) 4.02.396.420 I slot print_timing: id 0 | task 2523 | eval time = 5136.01 ms / 91 tokens ( 57.07 ms per token, 17.52 tokens per second) 4.02.396.422 I slot print_timing: id 0 | task 2523 | total time = 5570.63 ms / 195 tokens 4.02.396.423 I slot print_timing: id 0 | task 2523 | graphs reused = 1941 4.02.396.424 I slot print_timing: id 0 | task 2523 | graph reallocs = 0 / 0 (same size) / (changed size) 4.02.396.514 I slot release: id 0 | task 2523 | stop processing: n_tokens = 1319, truncated = 0 4.02.447.593 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.911 (> 0.100 thold), f_keep = 0.869 4.02.447.661 I slot launch_slot_: id 0 | task 2618 | processing task, is_child = 0 4.03.565.970 I slot print_timing: id 3 | task 2508 | prompt eval time = 464.63 ms / 117 tokens ( 3.97 ms per token, 251.81 tokens per second) 4.03.565.977 I slot print_timing: id 3 | task 2508 | eval time = 7362.59 ms / 120 tokens ( 61.87 ms per token, 16.16 tokens per second) 4.03.565.979 I slot print_timing: id 3 | task 2508 | total time = 7827.22 ms / 237 tokens 4.03.565.980 I slot print_timing: id 3 | task 2508 | graphs reused = 1953 4.03.565.981 I slot print_timing: id 3 | task 2508 | graph reallocs = 0 / 0 (same size) / (changed size) 4.03.566.083 I slot release: id 3 | task 2508 | stop processing: n_tokens = 1361, truncated = 0 4.03.615.428 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.842 4.03.615.491 I slot launch_slot_: id 3 | task 2634 | processing task, is_child = 0 4.04.177.989 I slot print_timing: id 2 | task 2488 | n_gen = 144, tg = 15.30 t/s, tg_3s = 14.46 t/s 4.04.861.954 I slot print_timing: id 2 | task 2488 | prompt eval time = 568.87 ms / 166 tokens ( 3.43 ms per token, 291.81 tokens per second) 4.04.861.966 I slot print_timing: id 2 | task 2488 | eval time = 10030.74 ms / 157 tokens ( 64.30 ms per token, 15.55 tokens per second) 4.04.861.967 I slot print_timing: id 2 | task 2488 | total time = 10599.61 ms / 323 tokens 4.04.861.968 I slot print_timing: id 2 | task 2488 | graphs reused = 1967 4.04.861.969 I slot print_timing: id 2 | task 2488 | graph reallocs = 0 / 0 (same size) / (changed size) 4.04.862.080 I slot release: id 2 | task 2488 | stop processing: n_tokens = 1447, truncated = 0 4.04.924.407 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.792 4.04.924.492 I slot launch_slot_: id 2 | task 2653 | processing task, is_child = 0 4.07.246.079 I slot print_timing: id 1 | task 2586 | n_gen = 100, tg = 15.66 t/s, tg_3s = 15.82 t/s 4.07.674.521 I slot print_timing: id 3 | task 2634 | prompt eval time = 456.14 ms / 112 tokens ( 4.07 ms per token, 245.54 tokens per second) 4.07.674.527 I slot print_timing: id 3 | task 2634 | eval time = 3602.87 ms / 62 tokens ( 59.06 ms per token, 16.93 tokens per second) 4.07.674.528 I slot print_timing: id 3 | task 2634 | total time = 4059.02 ms / 174 tokens 4.07.674.529 I slot print_timing: id 3 | task 2634 | graphs reused = 2009 4.07.674.530 I slot print_timing: id 3 | task 2634 | graph reallocs = 0 / 0 (same size) / (changed size) 4.07.674.631 I slot release: id 3 | task 2634 | stop processing: n_tokens = 1298, truncated = 0 4.07.723.732 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.883 4.07.723.797 I slot launch_slot_: id 3 | task 2700 | processing task, is_child = 0 4.08.873.941 I slot print_timing: id 1 | task 2586 | prompt eval time = 481.23 ms / 108 tokens ( 4.46 ms per token, 224.42 tokens per second) 4.08.873.946 I slot print_timing: id 1 | task 2586 | eval time = 7948.98 ms / 124 tokens ( 64.63 ms per token, 15.47 tokens per second) 4.08.873.947 I slot print_timing: id 1 | task 2586 | total time = 8430.21 ms / 232 tokens 4.08.873.947 I slot print_timing: id 1 | task 2586 | graphs reused = 2021 4.08.873.947 I slot print_timing: id 1 | task 2586 | graph reallocs = 0 / 0 (same size) / (changed size) 4.08.873.994 I slot release: id 1 | task 2586 | stop processing: n_tokens = 1356, truncated = 0 4.08.931.365 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.845 4.08.931.421 I slot launch_slot_: id 1 | task 2717 | processing task, is_child = 0 4.09.630.705 I slot print_timing: id 0 | task 2618 | n_gen = 100, tg = 14.78 t/s, tg_3s = 14.92 t/s 4.10.745.820 I slot print_timing: id 2 | task 2653 | prompt eval time = 486.41 ms / 116 tokens ( 4.19 ms per token, 238.48 tokens per second) 4.10.745.831 I slot print_timing: id 2 | task 2653 | eval time = 5334.90 ms / 88 tokens ( 61.32 ms per token, 16.31 tokens per second) 4.10.745.833 I slot print_timing: id 2 | task 2653 | total time = 5821.31 ms / 204 tokens 4.10.745.834 I slot print_timing: id 2 | task 2653 | graphs reused = 2045 4.10.745.835 I slot print_timing: id 2 | task 2653 | graph reallocs = 0 / 0 (same size) / (changed size) 4.10.745.972 I slot release: id 2 | task 2653 | stop processing: n_tokens = 1328, truncated = 0 4.10.808.274 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.863 4.10.808.344 I slot launch_slot_: id 2 | task 2746 | processing task, is_child = 0 4.12.121.651 I slot print_timing: id 0 | task 2618 | prompt eval time = 482.55 ms / 133 tokens ( 3.63 ms per token, 275.62 tokens per second) 4.12.121.656 I slot print_timing: id 0 | task 2618 | eval time = 9191.43 ms / 140 tokens ( 66.13 ms per token, 15.12 tokens per second) 4.12.121.657 I slot print_timing: id 0 | task 2618 | total time = 9673.98 ms / 273 tokens 4.12.121.657 I slot print_timing: id 0 | task 2618 | graphs reused = 2060 4.12.121.658 I slot print_timing: id 0 | task 2618 | graph reallocs = 0 / 0 (same size) / (changed size) 4.12.121.706 I slot release: id 0 | task 2618 | stop processing: n_tokens = 1397, truncated = 0 4.12.167.805 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.820 4.12.167.839 I slot launch_slot_: id 0 | task 2766 | processing task, is_child = 0 4.14.504.232 I slot print_timing: id 3 | task 2700 | n_gen = 100, tg = 15.69 t/s, tg_3s = 15.85 t/s 4.15.288.614 I slot print_timing: id 1 | task 2717 | prompt eval time = 488.14 ms / 119 tokens ( 4.10 ms per token, 243.78 tokens per second) 4.15.288.620 I slot print_timing: id 1 | task 2717 | eval time = 5869.04 ms / 99 tokens ( 59.89 ms per token, 16.70 tokens per second) 4.15.288.620 I slot print_timing: id 1 | task 2717 | total time = 6357.18 ms / 218 tokens 4.15.288.621 I slot print_timing: id 1 | task 2717 | graphs reused = 2111 4.15.288.621 I slot print_timing: id 1 | task 2717 | graph reallocs = 0 / 0 (same size) / (changed size) 4.15.288.686 I slot release: id 1 | task 2717 | stop processing: n_tokens = 1342, truncated = 0 4.15.346.110 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.854 4.15.346.147 I slot launch_slot_: id 1 | task 2821 | processing task, is_child = 0 4.16.622.454 I slot print_timing: id 2 | task 2746 | prompt eval time = 476.86 ms / 103 tokens ( 4.63 ms per token, 216.00 tokens per second) 4.16.622.462 I slot print_timing: id 2 | task 2746 | eval time = 5337.23 ms / 89 tokens ( 60.65 ms per token, 16.49 tokens per second) 4.16.622.465 I slot print_timing: id 2 | task 2746 | total time = 5814.10 ms / 192 tokens 4.16.622.466 I slot print_timing: id 2 | task 2746 | graphs reused = 2125 4.16.622.467 I slot print_timing: id 2 | task 2746 | graph reallocs = 0 / 0 (same size) / (changed size) 4.16.622.585 I slot release: id 2 | task 2746 | stop processing: n_tokens = 1316, truncated = 0 4.16.685.003 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.871 4.16.685.071 I slot launch_slot_: id 2 | task 2840 | processing task, is_child = 0 4.17.523.487 I slot print_timing: id 3 | task 2700 | n_gen = 143, tg = 15.22 t/s, tg_3s = 14.24 t/s 4.18.163.924 I slot print_timing: id 3 | task 2700 | prompt eval time = 469.64 ms / 119 tokens ( 3.95 ms per token, 253.39 tokens per second) 4.18.163.935 I slot print_timing: id 3 | task 2700 | eval time = 9970.48 ms / 155 tokens ( 64.74 ms per token, 15.45 tokens per second) 4.18.163.936 I slot print_timing: id 3 | task 2700 | total time = 10440.11 ms / 274 tokens 4.18.163.938 I slot print_timing: id 3 | task 2700 | graphs reused = 2143 4.18.163.939 I slot print_timing: id 3 | task 2700 | graph reallocs = 0 / 0 (same size) / (changed size) 4.18.164.069 I slot release: id 3 | task 2700 | stop processing: n_tokens = 1398, truncated = 0 4.18.212.787 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.820 4.18.212.847 I slot launch_slot_: id 3 | task 2863 | processing task, is_child = 0 4.18.901.867 I slot print_timing: id 0 | task 2766 | n_gen = 100, tg = 15.76 t/s, tg_3s = 15.92 t/s 4.19.537.983 I slot print_timing: id 0 | task 2766 | prompt eval time = 452.79 ms / 120 tokens ( 3.77 ms per token, 265.02 tokens per second) 4.19.537.991 I slot print_timing: id 0 | task 2766 | eval time = 6917.34 ms / 112 tokens ( 62.32 ms per token, 16.05 tokens per second) 4.19.537.993 I slot print_timing: id 0 | task 2766 | total time = 7370.13 ms / 232 tokens 4.19.537.994 I slot print_timing: id 0 | task 2766 | graphs reused = 2159 4.19.537.995 I slot print_timing: id 0 | task 2766 | graph reallocs = 0 / 0 (same size) / (changed size) 4.19.538.088 I slot release: id 0 | task 2766 | stop processing: n_tokens = 1356, truncated = 0 4.19.589.122 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.846 4.19.589.181 I slot launch_slot_: id 0 | task 2884 | processing task, is_child = 0 4.21.587.473 I slot print_timing: id 2 | task 2840 | prompt eval time = 460.96 ms / 97 tokens ( 4.75 ms per token, 210.43 tokens per second) 4.21.587.479 I slot print_timing: id 2 | task 2840 | eval time = 4441.43 ms / 71 tokens ( 63.45 ms per token, 15.76 tokens per second) 4.21.587.479 I slot print_timing: id 2 | task 2840 | total time = 4902.39 ms / 168 tokens 4.21.587.480 I slot print_timing: id 2 | task 2840 | graphs reused = 2187 4.21.587.480 I slot print_timing: id 2 | task 2840 | graph reallocs = 0 / 0 (same size) / (changed size) 4.21.587.535 I slot release: id 2 | task 2840 | stop processing: n_tokens = 1292, truncated = 0 4.21.647.165 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.887 4.21.647.283 I slot launch_slot_: id 2 | task 2916 | processing task, is_child = 0 4.22.559.309 I slot print_timing: id 1 | task 2821 | n_gen = 100, tg = 14.70 t/s, tg_3s = 14.85 t/s 4.22.664.374 I slot print_timing: id 1 | task 2821 | prompt eval time = 480.59 ms / 108 tokens ( 4.45 ms per token, 224.73 tokens per second) 4.22.664.380 I slot print_timing: id 1 | task 2821 | eval time = 6837.64 ms / 102 tokens ( 67.70 ms per token, 14.77 tokens per second) 4.22.664.381 I slot print_timing: id 1 | task 2821 | total time = 7318.22 ms / 210 tokens 4.22.664.381 I slot print_timing: id 1 | task 2821 | graphs reused = 2196 4.22.664.382 I slot print_timing: id 1 | task 2821 | graph reallocs = 0 / 0 (same size) / (changed size) 4.22.664.435 I slot release: id 1 | task 2821 | stop processing: n_tokens = 1334, truncated = 0 4.22.721.423 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.859 4.22.721.460 I slot launch_slot_: id 1 | task 2930 | processing task, is_child = 0 4.23.679.782 I slot print_timing: id 3 | task 2863 | prompt eval time = 426.45 ms / 100 tokens ( 4.26 ms per token, 234.49 tokens per second) 4.23.679.787 I slot print_timing: id 3 | task 2863 | eval time = 5040.47 ms / 74 tokens ( 69.05 ms per token, 14.48 tokens per second) 4.23.679.788 I slot print_timing: id 3 | task 2863 | total time = 5466.93 ms / 174 tokens 4.23.679.788 I slot print_timing: id 3 | task 2863 | graphs reused = 2204 4.23.679.789 I slot print_timing: id 3 | task 2863 | graph reallocs = 0 / 0 (same size) / (changed size) 4.23.679.838 I slot release: id 3 | task 2863 | stop processing: n_tokens = 1298, truncated = 0 4.23.725.476 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.883 4.23.725.511 I slot launch_slot_: id 3 | task 2943 | processing task, is_child = 0 4.26.051.761 I slot print_timing: id 1 | task 2930 | prompt eval time = 487.23 ms / 114 tokens ( 4.27 ms per token, 233.98 tokens per second) 4.26.051.766 I slot print_timing: id 1 | task 2930 | eval time = 2843.07 ms / 49 tokens ( 59.23 ms per token, 16.88 tokens per second) 4.26.051.767 I slot print_timing: id 1 | task 2930 | total time = 3330.30 ms / 163 tokens 4.26.051.768 I slot print_timing: id 1 | task 2930 | graphs reused = 2239 4.26.051.768 I slot print_timing: id 1 | task 2930 | graph reallocs = 0 / 0 (same size) / (changed size) 4.26.051.823 I slot release: id 1 | task 2930 | stop processing: n_tokens = 1287, truncated = 0 4.26.109.144 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.890 4.26.109.174 I slot launch_slot_: id 1 | task 2983 | processing task, is_child = 0 4.26.803.274 I slot print_timing: id 0 | task 2884 | n_gen = 100, tg = 14.82 t/s, tg_3s = 14.97 t/s 4.27.482.309 I slot print_timing: id 2 | task 2916 | prompt eval time = 492.74 ms / 119 tokens ( 4.14 ms per token, 241.51 tokens per second) 4.27.482.311 I slot print_timing: id 2 | task 2916 | eval time = 5342.27 ms / 82 tokens ( 65.95 ms per token, 15.16 tokens per second) 4.27.482.312 I slot print_timing: id 2 | task 2916 | total time = 5835.01 ms / 201 tokens 4.27.482.312 I slot print_timing: id 2 | task 2916 | graphs reused = 2255 4.27.482.313 I slot print_timing: id 2 | task 2916 | graph reallocs = 0 / 0 (same size) / (changed size) 4.27.482.366 I slot release: id 2 | task 2916 | stop processing: n_tokens = 1325, truncated = 0 4.27.539.514 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.945 (> 0.100 thold), f_keep = 0.865 4.27.539.550 I slot launch_slot_: id 2 | task 3004 | processing task, is_child = 0 4.28.495.334 I slot print_timing: id 0 | task 2884 | prompt eval time = 532.41 ms / 172 tokens ( 3.10 ms per token, 323.06 tokens per second) 4.28.495.337 I slot print_timing: id 0 | task 2884 | eval time = 8373.73 ms / 126 tokens ( 66.99 ms per token, 14.93 tokens per second) 4.28.495.337 I slot print_timing: id 0 | task 2884 | total time = 8906.14 ms / 298 tokens 4.28.495.338 I slot print_timing: id 0 | task 2884 | graphs reused = 2264 4.28.495.338 I slot print_timing: id 0 | task 2884 | graph reallocs = 0 / 0 (same size) / (changed size) 4.28.495.386 I slot release: id 0 | task 2884 | stop processing: n_tokens = 1422, truncated = 0 4.28.542.141 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.806 4.28.542.182 I slot launch_slot_: id 0 | task 3018 | processing task, is_child = 0 4.29.160.568 I slot print_timing: id 3 | task 2943 | prompt eval time = 445.00 ms / 104 tokens ( 4.28 ms per token, 233.71 tokens per second) 4.29.160.571 I slot print_timing: id 3 | task 2943 | eval time = 4990.04 ms / 76 tokens ( 66.53 ms per token, 15.03 tokens per second) 4.29.160.571 I slot print_timing: id 3 | task 2943 | total time = 5435.05 ms / 180 tokens 4.29.160.572 I slot print_timing: id 3 | task 2943 | graphs reused = 2267 4.29.160.572 I slot print_timing: id 3 | task 2943 | graph reallocs = 0 / 0 (same size) / (changed size) 4.29.160.616 I slot release: id 3 | task 2943 | stop processing: n_tokens = 1304, truncated = 0 4.29.206.398 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.879 4.29.206.433 I slot launch_slot_: id 3 | task 3025 | processing task, is_child = 0 4.31.463.963 I slot print_timing: id 1 | task 2983 | prompt eval time = 483.62 ms / 117 tokens ( 4.13 ms per token, 241.93 tokens per second) 4.31.463.972 I slot print_timing: id 1 | task 2983 | eval time = 4871.16 ms / 75 tokens ( 65.83 ms per token, 15.19 tokens per second) 4.31.463.974 I slot print_timing: id 1 | task 2983 | total time = 5354.78 ms / 192 tokens 4.31.463.975 I slot print_timing: id 1 | task 2983 | graphs reused = 2301 4.31.463.976 I slot print_timing: id 1 | task 2983 | graph reallocs = 0 / 0 (same size) / (changed size) 4.31.464.066 I slot release: id 1 | task 2983 | stop processing: n_tokens = 1316, truncated = 0 4.31.525.320 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.871 4.31.525.392 I slot launch_slot_: id 1 | task 3064 | processing task, is_child = 0 4.33.239.897 I slot print_timing: id 2 | task 3004 | prompt eval time = 433.74 ms / 88 tokens ( 4.93 ms per token, 202.89 tokens per second) 4.33.239.906 I slot print_timing: id 2 | task 3004 | eval time = 5266.60 ms / 80 tokens ( 66.67 ms per token, 15.00 tokens per second) 4.33.239.907 I slot print_timing: id 2 | task 3004 | total time = 5700.34 ms / 168 tokens 4.33.239.908 I slot print_timing: id 2 | task 3004 | graphs reused = 2322 4.33.239.909 I slot print_timing: id 2 | task 3004 | graph reallocs = 0 / 0 (same size) / (changed size) 4.33.240.027 I slot release: id 2 | task 3004 | stop processing: n_tokens = 1292, truncated = 0 4.33.302.194 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.887 4.33.302.271 I slot launch_slot_: id 2 | task 3090 | processing task, is_child = 0 4.33.896.387 I slot print_timing: id 3 | task 3025 | prompt eval time = 412.64 ms / 87 tokens ( 4.74 ms per token, 210.83 tokens per second) 4.33.896.393 I slot print_timing: id 3 | task 3025 | eval time = 4277.30 ms / 66 tokens ( 65.80 ms per token, 15.20 tokens per second) 4.33.896.393 I slot print_timing: id 3 | task 3025 | total time = 4689.95 ms / 153 tokens 4.33.896.394 I slot print_timing: id 3 | task 3025 | graphs reused = 2323 4.33.896.399 I slot print_timing: id 3 | task 3025 | graph reallocs = 0 / 0 (same size) / (changed size) 4.33.896.453 I slot release: id 3 | task 3025 | stop processing: n_tokens = 1277, truncated = 0 4.33.942.256 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.897 4.33.942.285 I slot launch_slot_: id 3 | task 3096 | processing task, is_child = 0 4.35.700.835 I slot print_timing: id 0 | task 3018 | n_gen = 100, tg = 14.78 t/s, tg_3s = 14.93 t/s 4.36.276.413 I slot print_timing: id 0 | task 3018 | prompt eval time = 459.54 ms / 129 tokens ( 3.56 ms per token, 280.72 tokens per second) 4.36.276.419 I slot print_timing: id 0 | task 3018 | eval time = 7274.68 ms / 111 tokens ( 66.13 ms per token, 15.12 tokens per second) 4.36.276.420 I slot print_timing: id 0 | task 3018 | total time = 7734.22 ms / 240 tokens 4.36.276.420 I slot print_timing: id 0 | task 3018 | graphs reused = 2358 4.36.276.421 I slot print_timing: id 0 | task 3018 | graph reallocs = 0 / 0 (same size) / (changed size) 4.36.276.474 I slot release: id 0 | task 3018 | stop processing: n_tokens = 1364, truncated = 0 4.36.323.547 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.840 4.36.323.581 I slot launch_slot_: id 0 | task 3136 | processing task, is_child = 0 4.38.143.865 I slot print_timing: id 1 | task 3064 | prompt eval time = 539.78 ms / 152 tokens ( 3.55 ms per token, 281.60 tokens per second) 4.38.143.877 I slot print_timing: id 1 | task 3064 | eval time = 6078.68 ms / 95 tokens ( 64.67 ms per token, 15.46 tokens per second) 4.38.143.878 I slot print_timing: id 1 | task 3064 | total time = 6618.46 ms / 247 tokens 4.38.143.879 I slot print_timing: id 1 | task 3064 | graphs reused = 2383 4.38.143.880 I slot print_timing: id 1 | task 3064 | graph reallocs = 0 / 0 (same size) / (changed size) 4.38.143.976 I slot release: id 1 | task 3064 | stop processing: n_tokens = 1371, truncated = 0 4.38.205.396 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.942 (> 0.100 thold), f_keep = 0.836 4.38.205.463 I slot launch_slot_: id 1 | task 3165 | processing task, is_child = 0 4.38.860.117 I slot print_timing: id 2 | task 3090 | prompt eval time = 487.88 ms / 118 tokens ( 4.13 ms per token, 241.86 tokens per second) 4.38.860.123 I slot print_timing: id 2 | task 3090 | eval time = 5069.95 ms / 77 tokens ( 66.71 ms per token, 14.99 tokens per second) 4.38.860.123 I slot print_timing: id 2 | task 3090 | total time = 5557.83 ms / 195 tokens 4.38.860.124 I slot print_timing: id 2 | task 3090 | graphs reused = 2386 4.38.860.124 I slot print_timing: id 2 | task 3090 | graph reallocs = 0 / 0 (same size) / (changed size) 4.38.860.173 I slot release: id 2 | task 3090 | stop processing: n_tokens = 1319, truncated = 0 4.38.917.240 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.869 4.38.917.277 I slot launch_slot_: id 2 | task 3173 | processing task, is_child = 0 4.40.711.708 I slot print_timing: id 3 | task 3096 | n_gen = 100, tg = 15.67 t/s, tg_3s = 15.83 t/s 4.41.712.542 I slot print_timing: id 3 | task 3096 | prompt eval time = 451.15 ms / 110 tokens ( 4.10 ms per token, 243.82 tokens per second) 4.41.712.552 I slot print_timing: id 3 | task 3096 | eval time = 7319.10 ms / 119 tokens ( 62.03 ms per token, 16.12 tokens per second) 4.41.712.553 I slot print_timing: id 3 | task 3096 | total time = 7770.25 ms / 229 tokens 4.41.712.554 I slot print_timing: id 3 | task 3096 | graphs reused = 2429 4.41.712.555 I slot print_timing: id 3 | task 3096 | graph reallocs = 0 / 0 (same size) / (changed size) 4.41.712.662 I slot release: id 3 | task 3096 | stop processing: n_tokens = 1353, truncated = 0 4.41.762.209 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.847 4.41.762.272 I slot launch_slot_: id 3 | task 3221 | processing task, is_child = 0 4.42.711.351 I slot print_timing: id 0 | task 3136 | prompt eval time = 482.91 ms / 135 tokens ( 3.58 ms per token, 279.56 tokens per second) 4.42.711.356 I slot print_timing: id 0 | task 3136 | eval time = 5904.86 ms / 92 tokens ( 64.89 ms per token, 15.41 tokens per second) 4.42.711.357 I slot print_timing: id 0 | task 3136 | total time = 6387.76 ms / 227 tokens 4.42.711.357 I slot print_timing: id 0 | task 3136 | graphs reused = 2437 4.42.711.358 I slot print_timing: id 0 | task 3136 | graph reallocs = 0 / 0 (same size) / (changed size) 4.42.711.404 I slot release: id 0 | task 3136 | stop processing: n_tokens = 1351, truncated = 0 4.42.757.952 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.848 4.42.757.984 I slot launch_slot_: id 0 | task 3234 | processing task, is_child = 0 4.43.476.495 I slot print_timing: id 1 | task 3165 | prompt eval time = 443.55 ms / 92 tokens ( 4.82 ms per token, 207.42 tokens per second) 4.43.476.503 I slot print_timing: id 1 | task 3165 | eval time = 4827.48 ms / 73 tokens ( 67.05 ms per token, 14.91 tokens per second) 4.43.476.504 I slot print_timing: id 1 | task 3165 | total time = 5271.02 ms / 165 tokens 4.43.476.505 I slot print_timing: id 1 | task 3165 | graphs reused = 2443 4.43.476.505 I slot print_timing: id 1 | task 3165 | graph reallocs = 0 / 0 (same size) / (changed size) 4.43.476.573 I slot release: id 1 | task 3165 | stop processing: n_tokens = 1289, truncated = 0 4.43.536.008 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.889 4.43.536.060 I slot launch_slot_: id 1 | task 3244 | processing task, is_child = 0 4.45.322.907 I slot print_timing: id 2 | task 3173 | prompt eval time = 486.45 ms / 120 tokens ( 4.05 ms per token, 246.68 tokens per second) 4.45.322.916 I slot print_timing: id 2 | task 3173 | eval time = 5919.16 ms / 94 tokens ( 63.65 ms per token, 15.71 tokens per second) 4.45.322.917 I slot print_timing: id 2 | task 3173 | total time = 6405.62 ms / 214 tokens 4.45.322.918 I slot print_timing: id 2 | task 3173 | graphs reused = 2467 4.45.322.919 I slot print_timing: id 2 | task 3173 | graph reallocs = 0 / 0 (same size) / (changed size) 4.45.323.037 I slot release: id 2 | task 3173 | stop processing: n_tokens = 1338, truncated = 0 4.45.385.680 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.857 4.45.385.745 I slot launch_slot_: id 2 | task 3273 | processing task, is_child = 0 4.48.505.895 I slot print_timing: id 3 | task 3221 | n_gen = 100, tg = 15.80 t/s, tg_3s = 15.96 t/s 4.48.558.583 I slot print_timing: id 2 | task 3273 | prompt eval time = 488.81 ms / 116 tokens ( 4.21 ms per token, 237.31 tokens per second) 4.48.558.589 I slot print_timing: id 2 | task 3273 | eval time = 2684.01 ms / 52 tokens ( 52.63 ms per token, 19.00 tokens per second) 4.48.558.590 I slot print_timing: id 2 | task 3273 | total time = 3172.82 ms / 168 tokens 4.48.558.591 I slot print_timing: id 2 | task 3273 | graphs reused = 2517 4.48.558.592 I slot print_timing: id 2 | task 3273 | graph reallocs = 0 / 0 (same size) / (changed size) 4.48.558.704 I slot release: id 2 | task 3273 | stop processing: n_tokens = 1292, truncated = 0 4.48.620.743 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.887 4.48.620.832 I slot launch_slot_: id 2 | task 3328 | processing task, is_child = 0 4.49.542.569 I slot print_timing: id 0 | task 3234 | n_gen = 100, tg = 15.51 t/s, tg_3s = 15.67 t/s 4.49.975.947 I slot print_timing: id 1 | task 3244 | prompt eval time = 450.73 ms / 98 tokens ( 4.60 ms per token, 217.42 tokens per second) 4.49.975.952 I slot print_timing: id 1 | task 3244 | eval time = 5989.14 ms / 99 tokens ( 61.11 ms per token, 16.36 tokens per second) 4.49.975.954 I slot print_timing: id 1 | task 3244 | total time = 6439.88 ms / 197 tokens 4.49.975.955 I slot print_timing: id 1 | task 3244 | graphs reused = 2532 4.49.975.956 I slot print_timing: id 1 | task 3244 | graph reallocs = 0 / 0 (same size) / (changed size) 4.49.976.048 I slot release: id 1 | task 3244 | stop processing: n_tokens = 1321, truncated = 0 4.50.037.787 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.868 4.50.037.866 I slot launch_slot_: id 1 | task 3348 | processing task, is_child = 0 4.50.775.625 I slot print_timing: id 0 | task 3234 | prompt eval time = 403.01 ms / 95 tokens ( 4.24 ms per token, 235.72 tokens per second) 4.50.775.627 I slot print_timing: id 0 | task 3234 | eval time = 7614.62 ms / 116 tokens ( 66.21 ms per token, 15.10 tokens per second) 4.50.775.628 I slot print_timing: id 0 | task 3234 | total time = 8017.63 ms / 211 tokens 4.50.775.628 I slot print_timing: id 0 | task 3234 | graphs reused = 2536 4.50.775.629 I slot print_timing: id 0 | task 3234 | graph reallocs = 0 / 0 (same size) / (changed size) 4.50.775.673 I slot release: id 0 | task 3234 | stop processing: n_tokens = 1335, truncated = 0 4.50.821.992 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.858 4.50.822.029 I slot launch_slot_: id 0 | task 3357 | processing task, is_child = 0 4.51.534.844 I slot print_timing: id 3 | task 3221 | n_gen = 136, tg = 14.53 t/s, tg_3s = 11.89 t/s 4.52.057.619 I slot print_timing: id 3 | task 3221 | prompt eval time = 478.67 ms / 131 tokens ( 3.65 ms per token, 273.68 tokens per second) 4.52.057.625 I slot print_timing: id 3 | task 3221 | eval time = 9816.67 ms / 146 tokens ( 67.70 ms per token, 14.77 tokens per second) 4.52.057.625 I slot print_timing: id 3 | task 3221 | total time = 10295.34 ms / 277 tokens 4.52.057.626 I slot print_timing: id 3 | task 3221 | graphs reused = 2551 4.52.057.626 I slot print_timing: id 3 | task 3221 | graph reallocs = 0 / 0 (same size) / (changed size) 4.52.057.673 I slot release: id 3 | task 3221 | stop processing: n_tokens = 1401, truncated = 0 4.52.104.150 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.911 (> 0.100 thold), f_keep = 0.818 4.52.104.191 I slot launch_slot_: id 3 | task 3376 | processing task, is_child = 0 4.55.336.891 I slot print_timing: id 2 | task 3328 | prompt eval time = 502.88 ms / 130 tokens ( 3.87 ms per token, 258.51 tokens per second) 4.55.336.901 I slot print_timing: id 2 | task 3328 | eval time = 6213.15 ms / 98 tokens ( 64.05 ms per token, 15.61 tokens per second) 4.55.336.902 I slot print_timing: id 2 | task 3328 | total time = 6716.03 ms / 228 tokens 4.55.336.903 I slot print_timing: id 2 | task 3328 | graphs reused = 2602 4.55.336.904 I slot print_timing: id 2 | task 3328 | graph reallocs = 0 / 0 (same size) / (changed size) 4.55.337.018 I slot release: id 2 | task 3328 | stop processing: n_tokens = 1352, truncated = 0 4.55.399.608 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.918 (> 0.100 thold), f_keep = 0.848 4.55.399.678 I slot launch_slot_: id 2 | task 3432 | processing task, is_child = 0 4.56.855.741 I slot print_timing: id 1 | task 3348 | n_gen = 100, tg = 15.61 t/s, tg_3s = 15.77 t/s 4.57.280.290 I slot print_timing: id 0 | task 3357 | n_gen = 100, tg = 16.48 t/s, tg_3s = 16.64 t/s 4.58.030.899 I slot print_timing: id 1 | task 3348 | prompt eval time = 474.98 ms / 103 tokens ( 4.61 ms per token, 216.85 tokens per second) 4.58.030.906 I slot print_timing: id 1 | task 3348 | eval time = 7518.04 ms / 122 tokens ( 62.13 ms per token, 16.09 tokens per second) 4.58.030.907 I slot print_timing: id 1 | task 3348 | total time = 7993.02 ms / 225 tokens 4.58.030.908 I slot print_timing: id 1 | task 3348 | graphs reused = 2641 4.58.030.909 I slot print_timing: id 1 | task 3348 | graph reallocs = 0 / 0 (same size) / (changed size) 4.58.031.009 I slot release: id 1 | task 3348 | stop processing: n_tokens = 1349, truncated = 0 4.58.092.706 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.850 4.58.092.777 I slot launch_slot_: id 1 | task 3476 | processing task, is_child = 0 4.58.639.074 I slot print_timing: id 3 | task 3376 | n_gen = 100, tg = 16.33 t/s, tg_3s = 16.50 t/s 5.00.206.117 I slot print_timing: id 0 | task 3357 | prompt eval time = 450.15 ms / 122 tokens ( 3.69 ms per token, 271.02 tokens per second) 5.00.206.123 I slot print_timing: id 0 | task 3357 | eval time = 8933.93 ms / 148 tokens ( 60.78 ms per token, 16.45 tokens per second) 5.00.206.123 I slot print_timing: id 0 | task 3357 | total time = 9384.08 ms / 270 tokens 5.00.206.124 I slot print_timing: id 0 | task 3357 | graphs reused = 2671 5.00.206.124 I slot print_timing: id 0 | task 3357 | graph reallocs = 0 / 0 (same size) / (changed size) 5.00.206.169 I slot release: id 0 | task 3357 | stop processing: n_tokens = 1394, truncated = 0 5.00.252.074 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.822 5.00.252.107 I slot launch_slot_: id 0 | task 3511 | processing task, is_child = 0 5.01.680.254 I slot print_timing: id 3 | task 3376 | n_gen = 152, tg = 16.59 t/s, tg_3s = 17.10 t/s 5.01.840.533 I slot print_timing: id 2 | task 3432 | n_gen = 100, tg = 16.63 t/s, tg_3s = 16.80 t/s 5.02.106.486 I slot print_timing: id 2 | task 3432 | prompt eval time = 489.35 ms / 123 tokens ( 3.98 ms per token, 251.35 tokens per second) 5.02.106.494 I slot print_timing: id 2 | task 3432 | eval time = 6217.44 ms / 105 tokens ( 59.78 ms per token, 16.73 tokens per second) 5.02.106.495 I slot print_timing: id 2 | task 3432 | total time = 6706.79 ms / 228 tokens 5.02.106.496 I slot print_timing: id 2 | task 3432 | graphs reused = 2698 5.02.106.497 I slot print_timing: id 2 | task 3432 | graph reallocs = 0 / 0 (same size) / (changed size) 5.02.106.593 I slot release: id 2 | task 3432 | stop processing: n_tokens = 1352, truncated = 0 5.02.168.512 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.848 5.02.168.594 I slot launch_slot_: id 2 | task 3542 | processing task, is_child = 0 5.04.444.734 I slot print_timing: id 1 | task 3476 | n_gen = 100, tg = 16.89 t/s, tg_3s = 17.06 t/s 5.04.549.331 I slot print_timing: id 3 | task 3376 | prompt eval time = 472.89 ms / 133 tokens ( 3.56 ms per token, 281.25 tokens per second) 5.04.549.333 I slot print_timing: id 3 | task 3376 | eval time = 11972.24 ms / 200 tokens ( 60.16 ms per token, 16.62 tokens per second) 5.04.549.334 I slot print_timing: id 3 | task 3376 | total time = 12445.13 ms / 333 tokens 5.04.549.334 I slot print_timing: id 3 | task 3376 | graphs reused = 2734 5.04.549.335 I slot print_timing: id 3 | task 3376 | graph reallocs = 0 / 0 (same size) / (changed size) 5.04.549.384 I slot release: id 3 | task 3376 | stop processing: n_tokens = 1457, truncated = 0 5.04.595.161 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.787 5.04.595.190 I slot launch_slot_: id 3 | task 3583 | processing task, is_child = 0 5.06.615.663 I slot print_timing: id 0 | task 3511 | n_gen = 100, tg = 16.67 t/s, tg_3s = 16.84 t/s 5.07.303.159 I slot print_timing: id 0 | task 3511 | prompt eval time = 426.19 ms / 101 tokens ( 4.22 ms per token, 236.98 tokens per second) 5.07.303.164 I slot print_timing: id 0 | task 3511 | eval time = 6624.85 ms / 113 tokens ( 59.15 ms per token, 16.91 tokens per second) 5.07.303.165 I slot print_timing: id 0 | task 3511 | total time = 7051.04 ms / 214 tokens 5.07.303.166 I slot print_timing: id 0 | task 3511 | graphs reused = 2775 5.07.303.167 I slot print_timing: id 0 | task 3511 | graph reallocs = 0 / 0 (same size) / (changed size) 5.07.303.253 I slot release: id 0 | task 3511 | stop processing: n_tokens = 1338, truncated = 0 5.07.354.516 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.944 (> 0.100 thold), f_keep = 0.857 5.07.354.586 I slot launch_slot_: id 0 | task 3629 | processing task, is_child = 0 5.07.661.933 I slot print_timing: id 1 | task 3476 | n_gen = 149, tg = 16.30 t/s, tg_3s = 15.23 t/s 5.07.808.314 I slot print_timing: id 2 | task 3542 | prompt eval time = 446.82 ms / 95 tokens ( 4.70 ms per token, 212.61 tokens per second) 5.07.808.320 I slot print_timing: id 2 | task 3542 | eval time = 5192.89 ms / 87 tokens ( 60.38 ms per token, 16.56 tokens per second) 5.07.808.320 I slot print_timing: id 2 | task 3542 | total time = 5639.71 ms / 182 tokens 5.07.808.321 I slot print_timing: id 2 | task 3542 | graphs reused = 2776 5.07.808.321 I slot print_timing: id 2 | task 3542 | graph reallocs = 0 / 0 (same size) / (changed size) 5.07.808.370 I slot release: id 2 | task 3542 | stop processing: n_tokens = 1306, truncated = 0 5.07.865.240 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.877 5.07.865.277 I slot launch_slot_: id 2 | task 3634 | processing task, is_child = 0 5.08.908.674 I slot print_timing: id 1 | task 3476 | prompt eval time = 491.62 ms / 118 tokens ( 4.17 ms per token, 240.02 tokens per second) 5.08.908.682 I slot print_timing: id 1 | task 3476 | eval time = 10324.26 ms / 165 tokens ( 62.95 ms per token, 15.88 tokens per second) 5.08.908.683 I slot print_timing: id 1 | task 3476 | total time = 10815.88 ms / 283 tokens 5.08.908.684 I slot print_timing: id 1 | task 3476 | graphs reused = 2786 5.08.908.685 I slot print_timing: id 1 | task 3476 | graph reallocs = 0 / 0 (same size) / (changed size) 5.08.908.791 I slot release: id 1 | task 3476 | stop processing: n_tokens = 1407, truncated = 0 5.08.970.234 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.942 (> 0.100 thold), f_keep = 0.814 5.08.970.304 I slot launch_slot_: id 1 | task 3649 | processing task, is_child = 0 5.11.343.279 I slot print_timing: id 3 | task 3583 | n_gen = 100, tg = 15.86 t/s, tg_3s = 16.02 t/s 5.11.873.060 I slot print_timing: id 0 | task 3629 | prompt eval time = 399.28 ms / 89 tokens ( 4.49 ms per token, 222.90 tokens per second) 5.11.873.071 I slot print_timing: id 0 | task 3629 | eval time = 4119.19 ms / 65 tokens ( 64.36 ms per token, 15.54 tokens per second) 5.11.873.072 I slot print_timing: id 0 | task 3629 | total time = 4518.46 ms / 154 tokens 5.11.873.073 I slot print_timing: id 0 | task 3629 | graphs reused = 2831 5.11.873.074 I slot print_timing: id 0 | task 3629 | graph reallocs = 0 / 0 (same size) / (changed size) 5.11.873.165 I slot release: id 0 | task 3629 | stop processing: n_tokens = 1278, truncated = 0 5.11.923.659 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.897 5.11.923.719 I slot launch_slot_: id 0 | task 3699 | processing task, is_child = 0 5.12.474.426 I slot print_timing: id 2 | task 3634 | prompt eval time = 449.27 ms / 99 tokens ( 4.54 ms per token, 220.36 tokens per second) 5.12.474.432 I slot print_timing: id 2 | task 3634 | eval time = 4159.86 ms / 66 tokens ( 64.00 ms per token, 15.63 tokens per second) 5.12.474.432 I slot print_timing: id 2 | task 3634 | total time = 4609.14 ms / 165 tokens 5.12.474.433 I slot print_timing: id 2 | task 3634 | graphs reused = 2833 5.12.474.433 I slot print_timing: id 2 | task 3634 | graph reallocs = 0 / 0 (same size) / (changed size) 5.12.474.478 I slot release: id 2 | task 3634 | stop processing: n_tokens = 1289, truncated = 0 5.12.531.625 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.889 5.12.531.662 I slot launch_slot_: id 2 | task 3705 | processing task, is_child = 0 5.13.282.419 I slot print_timing: id 1 | task 3649 | prompt eval time = 447.41 ms / 92 tokens ( 4.86 ms per token, 205.63 tokens per second) 5.13.282.422 I slot print_timing: id 1 | task 3649 | eval time = 3864.69 ms / 60 tokens ( 65.50 ms per token, 15.27 tokens per second) 5.13.282.423 I slot print_timing: id 1 | task 3649 | total time = 4312.10 ms / 152 tokens 5.13.282.423 I slot print_timing: id 1 | task 3649 | graphs reused = 2837 5.13.282.424 I slot print_timing: id 1 | task 3649 | graph reallocs = 0 / 0 (same size) / (changed size) 5.13.282.472 I slot release: id 1 | task 3649 | stop processing: n_tokens = 1276, truncated = 0 5.13.339.441 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.943 (> 0.100 thold), f_keep = 0.898 5.13.339.481 I slot launch_slot_: id 1 | task 3714 | processing task, is_child = 0 5.14.375.281 I slot print_timing: id 3 | task 3583 | n_gen = 137, tg = 14.66 t/s, tg_3s = 12.20 t/s 5.16.828.180 I slot print_timing: id 3 | task 3583 | prompt eval time = 505.65 ms / 152 tokens ( 3.33 ms per token, 300.60 tokens per second) 5.16.828.188 I slot print_timing: id 3 | task 3583 | eval time = 11727.32 ms / 183 tokens ( 64.44 ms per token, 15.52 tokens per second) 5.16.828.189 I slot print_timing: id 3 | task 3583 | total time = 12232.97 ms / 335 tokens 5.16.828.190 I slot print_timing: id 3 | task 3583 | graphs reused = 2893 5.16.828.191 I slot print_timing: id 3 | task 3583 | graph reallocs = 0 / 0 (same size) / (changed size) 5.16.828.333 I slot release: id 3 | task 3583 | stop processing: n_tokens = 1459, truncated = 0 5.16.878.287 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.885 (> 0.100 thold), f_keep = 0.785 5.16.878.345 I slot launch_slot_: id 3 | task 3775 | processing task, is_child = 0 5.17.997.228 I slot print_timing: id 1 | task 3714 | prompt eval time = 440.92 ms / 90 tokens ( 4.90 ms per token, 204.12 tokens per second) 5.17.997.235 I slot print_timing: id 1 | task 3714 | eval time = 4216.82 ms / 72 tokens ( 59.39 ms per token, 16.84 tokens per second) 5.17.997.235 I slot print_timing: id 1 | task 3714 | total time = 4657.74 ms / 162 tokens 5.17.997.236 I slot print_timing: id 1 | task 3714 | graphs reused = 2903 5.17.997.236 I slot print_timing: id 1 | task 3714 | graph reallocs = 0 / 0 (same size) / (changed size) 5.17.997.283 I slot release: id 1 | task 3714 | stop processing: n_tokens = 1286, truncated = 0 5.18.054.796 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.891 5.18.054.836 I slot launch_slot_: id 1 | task 3790 | processing task, is_child = 0 5.18.424.997 I slot print_timing: id 0 | task 3699 | prompt eval time = 444.59 ms / 113 tokens ( 3.93 ms per token, 254.17 tokens per second) 5.18.425.002 I slot print_timing: id 0 | task 3699 | eval time = 6056.68 ms / 87 tokens ( 70.43 ms per token, 14.20 tokens per second) 5.18.425.003 I slot print_timing: id 0 | task 3699 | total time = 6501.27 ms / 200 tokens 5.18.425.003 I slot print_timing: id 0 | task 3699 | graphs reused = 2903 5.18.425.004 I slot print_timing: id 0 | task 3699 | graph reallocs = 0 / 0 (same size) / (changed size) 5.18.425.046 I slot release: id 0 | task 3699 | stop processing: n_tokens = 1324, truncated = 0 5.18.506.771 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.901 (> 0.100 thold), f_keep = 0.866 5.18.506.808 I slot launch_slot_: id 0 | task 3793 | processing task, is_child = 0 5.19.782.031 I slot print_timing: id 2 | task 3705 | n_gen = 100, tg = 14.64 t/s, tg_3s = 14.79 t/s 5.21.581.304 I slot print_timing: id 2 | task 3705 | prompt eval time = 487.72 ms / 118 tokens ( 4.13 ms per token, 241.94 tokens per second) 5.21.581.312 I slot print_timing: id 2 | task 3705 | eval time = 8561.91 ms / 134 tokens ( 64.38 ms per token, 15.53 tokens per second) 5.21.581.313 I slot print_timing: id 2 | task 3705 | total time = 9049.63 ms / 252 tokens 5.21.581.314 I slot print_timing: id 2 | task 3705 | graphs reused = 2951 5.21.581.315 I slot print_timing: id 2 | task 3705 | graph reallocs = 0 / 0 (same size) / (changed size) 5.21.581.417 I slot release: id 2 | task 3705 | stop processing: n_tokens = 1376, truncated = 0 5.21.643.225 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.833 5.21.643.296 I slot launch_slot_: id 2 | task 3846 | processing task, is_child = 0 5.23.403.455 I slot print_timing: id 1 | task 3790 | prompt eval time = 451.63 ms / 107 tokens ( 4.22 ms per token, 236.92 tokens per second) 5.23.403.465 I slot print_timing: id 1 | task 3790 | eval time = 4896.98 ms / 79 tokens ( 62.78 ms per token, 15.93 tokens per second) 5.23.403.466 I slot print_timing: id 1 | task 3790 | total time = 5348.61 ms / 186 tokens 5.23.403.467 I slot print_timing: id 1 | task 3790 | graphs reused = 2974 5.23.403.468 I slot print_timing: id 1 | task 3790 | graph reallocs = 0 / 0 (same size) / (changed size) 5.23.403.569 I slot release: id 1 | task 3790 | stop processing: n_tokens = 1310, truncated = 0 5.23.464.994 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.875 5.23.465.071 I slot launch_slot_: id 1 | task 3874 | processing task, is_child = 0 5.24.204.198 I slot print_timing: id 3 | task 3775 | n_gen = 100, tg = 14.59 t/s, tg_3s = 14.74 t/s 5.24.256.397 I slot print_timing: id 0 | task 3793 | prompt eval time = 489.93 ms / 147 tokens ( 3.33 ms per token, 300.04 tokens per second) 5.24.256.401 I slot print_timing: id 0 | task 3793 | eval time = 5259.65 ms / 85 tokens ( 62.61 ms per token, 15.97 tokens per second) 5.24.256.402 I slot print_timing: id 0 | task 3793 | total time = 5749.58 ms / 232 tokens 5.24.256.402 I slot print_timing: id 0 | task 3793 | graphs reused = 2978 5.24.256.403 I slot print_timing: id 0 | task 3793 | graph reallocs = 0 / 0 (same size) / (changed size) 5.24.256.453 I slot release: id 0 | task 3793 | stop processing: n_tokens = 1356, truncated = 0 5.24.302.717 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.845 5.24.302.755 I slot launch_slot_: id 0 | task 3883 | processing task, is_child = 0 5.26.693.131 I slot print_timing: id 2 | task 3846 | prompt eval time = 483.13 ms / 109 tokens ( 4.43 ms per token, 225.61 tokens per second) 5.26.693.139 I slot print_timing: id 2 | task 3846 | eval time = 4566.69 ms / 73 tokens ( 63.43 ms per token, 15.77 tokens per second) 5.26.693.141 I slot print_timing: id 2 | task 3846 | total time = 5049.82 ms / 182 tokens 5.26.693.142 I slot print_timing: id 2 | task 3846 | graphs reused = 3015 5.26.693.143 I slot print_timing: id 2 | task 3846 | graph reallocs = 0 / 0 (same size) / (changed size) 5.26.693.246 I slot release: id 2 | task 3846 | stop processing: n_tokens = 1306, truncated = 0 5.26.755.500 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.877 5.26.755.582 I slot launch_slot_: id 2 | task 3924 | processing task, is_child = 0 5.27.283.159 I slot print_timing: id 3 | task 3775 | n_gen = 144, tg = 14.50 t/s, tg_3s = 14.29 t/s 5.29.979.633 I slot print_timing: id 1 | task 3874 | n_gen = 100, tg = 16.54 t/s, tg_3s = 16.70 t/s 5.30.299.664 I slot print_timing: id 3 | task 3775 | n_gen = 201, tg = 15.53 t/s, tg_3s = 18.90 t/s 5.30.404.546 I slot print_timing: id 0 | task 3883 | n_gen = 100, tg = 17.49 t/s, tg_3s = 17.67 t/s 5.31.577.883 I slot print_timing: id 0 | task 3883 | prompt eval time = 442.22 ms / 110 tokens ( 4.02 ms per token, 248.74 tokens per second) 5.31.577.890 I slot print_timing: id 0 | task 3883 | eval time = 6832.90 ms / 122 tokens ( 56.47 ms per token, 17.71 tokens per second) 5.31.577.891 I slot print_timing: id 0 | task 3883 | total time = 7275.12 ms / 232 tokens 5.31.577.892 I slot print_timing: id 0 | task 3883 | graphs reused = 3095 5.31.577.894 I slot print_timing: id 0 | task 3883 | graph reallocs = 0 / 0 (same size) / (changed size) 5.31.577.985 I slot release: id 0 | task 3883 | stop processing: n_tokens = 1356, truncated = 0 5.31.628.253 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.845 5.31.628.315 I slot launch_slot_: id 0 | task 4009 | processing task, is_child = 0 5.32.891.856 I slot print_timing: id 2 | task 3924 | n_gen = 100, tg = 17.65 t/s, tg_3s = 17.83 t/s 5.32.997.837 I slot print_timing: id 1 | task 3874 | n_gen = 150, tg = 16.55 t/s, tg_3s = 16.57 t/s 5.33.317.801 I slot print_timing: id 3 | task 3775 | n_gen = 251, tg = 15.73 t/s, tg_3s = 16.57 t/s 5.33.796.039 I slot print_timing: id 2 | task 3924 | prompt eval time = 527.42 ms / 134 tokens ( 3.94 ms per token, 254.07 tokens per second) 5.33.796.048 I slot print_timing: id 2 | task 3924 | eval time = 6513.03 ms / 117 tokens ( 56.15 ms per token, 17.81 tokens per second) 5.33.796.050 I slot print_timing: id 2 | task 3924 | total time = 7040.44 ms / 251 tokens 5.33.796.051 I slot print_timing: id 2 | task 3924 | graphs reused = 3126 5.33.796.053 I slot print_timing: id 2 | task 3924 | graph reallocs = 0 / 0 (same size) / (changed size) 5.33.796.157 I slot release: id 2 | task 3924 | stop processing: n_tokens = 1375, truncated = 0 5.33.858.069 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.833 5.33.858.153 I slot launch_slot_: id 2 | task 4045 | processing task, is_child = 0 5.36.049.798 I slot print_timing: id 1 | task 3874 | n_gen = 201, tg = 16.59 t/s, tg_3s = 16.71 t/s 5.36.263.499 I slot print_timing: id 1 | task 3874 | prompt eval time = 527.98 ms / 139 tokens ( 3.80 ms per token, 263.27 tokens per second) 5.36.263.505 I slot print_timing: id 1 | task 3874 | eval time = 12270.44 ms / 205 tokens ( 60.15 ms per token, 16.63 tokens per second) 5.36.263.506 I slot print_timing: id 1 | task 3874 | total time = 12798.41 ms / 344 tokens 5.36.263.507 I slot print_timing: id 1 | task 3874 | graphs reused = 3162 5.36.263.508 I slot print_timing: id 1 | task 3874 | graph reallocs = 0 / 0 (same size) / (changed size) 5.36.263.600 I slot release: id 1 | task 3874 | stop processing: n_tokens = 1468, truncated = 0 5.36.324.980 I slot print_timing: id 3 | task 3775 | n_gen = 301, tg = 15.87 t/s, tg_3s = 16.63 t/s 5.36.324.991 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.781 5.36.325.063 I slot launch_slot_: id 1 | task 4086 | processing task, is_child = 0 5.38.092.142 I slot print_timing: id 0 | task 4009 | n_gen = 100, tg = 16.47 t/s, tg_3s = 16.64 t/s 5.39.321.435 I slot print_timing: id 0 | task 4009 | prompt eval time = 452.47 ms / 122 tokens ( 3.71 ms per token, 269.63 tokens per second) 5.39.321.444 I slot print_timing: id 0 | task 4009 | eval time = 7240.64 ms / 123 tokens ( 59.35 ms per token, 16.85 tokens per second) 5.39.321.445 I slot print_timing: id 0 | task 4009 | total time = 7693.11 ms / 245 tokens 5.39.321.446 I slot print_timing: id 0 | task 4009 | graphs reused = 3208 5.39.321.447 I slot print_timing: id 0 | task 4009 | graph reallocs = 0 / 0 (same size) / (changed size) 5.39.321.539 I slot release: id 0 | task 4009 | stop processing: n_tokens = 1369, truncated = 0 5.39.372.621 I slot print_timing: id 3 | task 3775 | n_gen = 351, tg = 15.94 t/s, tg_3s = 16.41 t/s 5.39.372.632 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.837 5.39.372.695 I slot launch_slot_: id 0 | task 4137 | processing task, is_child = 0 5.39.708.493 I slot print_timing: id 2 | task 4045 | prompt eval time = 451.28 ms / 96 tokens ( 4.70 ms per token, 212.73 tokens per second) 5.39.708.498 I slot print_timing: id 2 | task 4045 | eval time = 5399.05 ms / 90 tokens ( 60.66 ms per token, 16.48 tokens per second) 5.39.708.498 I slot print_timing: id 2 | task 4045 | total time = 5850.33 ms / 186 tokens 5.39.708.499 I slot print_timing: id 2 | task 4045 | graphs reused = 3209 5.39.708.499 I slot print_timing: id 2 | task 4045 | graph reallocs = 0 / 0 (same size) / (changed size) 5.39.708.551 I slot release: id 2 | task 4045 | stop processing: n_tokens = 1310, truncated = 0 5.39.799.629 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.875 5.39.799.665 I slot launch_slot_: id 2 | task 4140 | processing task, is_child = 0 5.42.407.948 I slot print_timing: id 1 | task 4086 | prompt eval time = 486.38 ms / 111 tokens ( 4.38 ms per token, 228.22 tokens per second) 5.42.407.957 I slot print_timing: id 1 | task 4086 | eval time = 5596.50 ms / 93 tokens ( 60.83 ms per token, 16.44 tokens per second) 5.42.407.958 I slot print_timing: id 1 | task 4086 | total time = 6082.87 ms / 204 tokens 5.42.407.959 I slot print_timing: id 1 | task 4086 | graphs reused = 3248 5.42.407.960 I slot print_timing: id 1 | task 4086 | graph reallocs = 0 / 0 (same size) / (changed size) 5.42.408.068 I slot release: id 1 | task 4086 | stop processing: n_tokens = 1328, truncated = 0 5.42.408.882 I slot print_timing: id 3 | task 3775 | n_gen = 395, tg = 15.77 t/s, tg_3s = 14.49 t/s 5.42.470.226 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.863 5.42.470.330 I slot launch_slot_: id 1 | task 4184 | processing task, is_child = 0 5.44.695.914 I slot print_timing: id 0 | task 4137 | prompt eval time = 426.58 ms / 101 tokens ( 4.22 ms per token, 236.77 tokens per second) 5.44.695.922 I slot print_timing: id 0 | task 4137 | eval time = 4896.62 ms / 77 tokens ( 64.43 ms per token, 15.52 tokens per second) 5.44.695.923 I slot print_timing: id 0 | task 4137 | total time = 5323.21 ms / 178 tokens 5.44.695.924 I slot print_timing: id 0 | task 4137 | graphs reused = 3278 5.44.695.925 I slot print_timing: id 0 | task 4137 | graph reallocs = 0 / 0 (same size) / (changed size) 5.44.696.015 I slot release: id 0 | task 4137 | stop processing: n_tokens = 1302, truncated = 0 5.44.746.358 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.880 5.44.746.426 I slot launch_slot_: id 0 | task 4219 | processing task, is_child = 0 5.45.451.511 I slot print_timing: id 3 | task 3775 | n_gen = 437, tg = 15.55 t/s, tg_3s = 13.80 t/s 5.46.340.369 I slot print_timing: id 2 | task 4140 | n_gen = 100, tg = 16.31 t/s, tg_3s = 16.48 t/s 5.47.922.482 I slot print_timing: id 2 | task 4140 | prompt eval time = 472.30 ms / 108 tokens ( 4.37 ms per token, 228.67 tokens per second) 5.47.922.488 I slot print_timing: id 2 | task 4140 | eval time = 7650.50 ms / 130 tokens ( 59.31 ms per token, 16.86 tokens per second) 5.47.922.489 I slot print_timing: id 2 | task 4140 | total time = 8122.80 ms / 238 tokens 5.47.922.490 I slot print_timing: id 2 | task 4140 | graphs reused = 3330 5.47.922.491 I slot print_timing: id 2 | task 4140 | graph reallocs = 0 / 0 (same size) / (changed size) 5.47.922.588 I slot release: id 2 | task 4140 | stop processing: n_tokens = 1362, truncated = 0 5.47.985.125 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.841 5.47.985.178 I slot launch_slot_: id 2 | task 4275 | processing task, is_child = 0 5.48.485.935 I slot print_timing: id 3 | task 3775 | n_gen = 487, tg = 15.64 t/s, tg_3s = 16.48 t/s 5.49.011.410 I slot print_timing: id 1 | task 4184 | n_gen = 100, tg = 16.59 t/s, tg_3s = 16.75 t/s 5.50.325.760 I slot print_timing: id 1 | task 4184 | prompt eval time = 572.05 ms / 166 tokens ( 3.45 ms per token, 290.19 tokens per second) 5.50.325.765 I slot print_timing: id 1 | task 4184 | eval time = 7283.37 ms / 125 tokens ( 58.74 ms per token, 17.03 tokens per second) 5.50.325.766 I slot print_timing: id 1 | task 4184 | total time = 7855.42 ms / 291 tokens 5.50.325.766 I slot print_timing: id 1 | task 4184 | graphs reused = 3363 5.50.325.767 I slot print_timing: id 1 | task 4184 | graph reallocs = 0 / 0 (same size) / (changed size) 5.50.325.814 I slot release: id 1 | task 4184 | stop processing: n_tokens = 1415, truncated = 0 5.50.383.674 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.810 5.50.383.704 I slot launch_slot_: id 1 | task 4314 | processing task, is_child = 0 5.51.149.790 I slot print_timing: id 0 | task 4219 | n_gen = 100, tg = 16.60 t/s, tg_3s = 16.77 t/s 5.51.515.803 I slot print_timing: id 3 | task 3775 | n_gen = 538, tg = 15.75 t/s, tg_3s = 16.83 t/s 5.51.619.969 I slot print_timing: id 0 | task 4219 | prompt eval time = 441.06 ms / 110 tokens ( 4.01 ms per token, 249.40 tokens per second) 5.51.619.975 I slot print_timing: id 0 | task 4219 | eval time = 6432.47 ms / 109 tokens ( 59.56 ms per token, 16.79 tokens per second) 5.51.619.975 I slot print_timing: id 0 | task 4219 | total time = 6873.53 ms / 219 tokens 5.51.619.976 I slot print_timing: id 0 | task 4219 | graphs reused = 3377 5.51.619.976 I slot print_timing: id 0 | task 4219 | graph reallocs = 0 / 0 (same size) / (changed size) 5.51.620.027 I slot release: id 0 | task 4219 | stop processing: n_tokens = 1343, truncated = 0 5.51.666.781 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.904 (> 0.100 thold), f_keep = 0.853 5.51.666.821 I slot launch_slot_: id 0 | task 4333 | processing task, is_child = 0 5.52.059.375 I slot print_timing: id 2 | task 4275 | prompt eval time = 500.58 ms / 128 tokens ( 3.91 ms per token, 255.70 tokens per second) 5.52.059.380 I slot print_timing: id 2 | task 4275 | eval time = 3573.61 ms / 56 tokens ( 64.97 ms per token, 15.39 tokens per second) 5.52.059.380 I slot print_timing: id 2 | task 4275 | total time = 4074.19 ms / 184 tokens 5.52.059.381 I slot print_timing: id 2 | task 4275 | graphs reused = 3378 5.52.059.381 I slot print_timing: id 2 | task 4275 | graph reallocs = 0 / 0 (same size) / (changed size) 5.52.059.428 I slot release: id 2 | task 4275 | stop processing: n_tokens = 1308, truncated = 0 5.52.149.207 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.876 5.52.149.243 I slot launch_slot_: id 2 | task 4336 | processing task, is_child = 0 5.54.528.060 I slot print_timing: id 3 | task 3775 | n_gen = 581, tg = 15.63 t/s, tg_3s = 14.28 t/s 5.55.328.122 I slot print_timing: id 1 | task 4314 | prompt eval time = 450.30 ms / 95 tokens ( 4.74 ms per token, 210.97 tokens per second) 5.55.328.132 I slot print_timing: id 1 | task 4314 | eval time = 4494.11 ms / 72 tokens ( 63.30 ms per token, 15.80 tokens per second) 5.55.328.133 I slot print_timing: id 1 | task 4314 | total time = 4944.41 ms / 167 tokens 5.55.328.134 I slot print_timing: id 1 | task 4314 | graphs reused = 3428 5.55.328.135 I slot print_timing: id 1 | task 4314 | graph reallocs = 0 / 0 (same size) / (changed size) 5.55.328.240 I slot release: id 1 | task 4314 | stop processing: n_tokens = 1291, truncated = 0 5.57.005.397 I slot print_timing: id 2 | task 4336 | prompt eval time = 441.02 ms / 96 tokens ( 4.59 ms per token, 217.68 tokens per second) 5.57.005.403 I slot print_timing: id 2 | task 4336 | eval time = 4415.12 ms / 79 tokens ( 56.60 ms per token, 17.67 tokens per second) 5.57.005.414 I slot print_timing: id 2 | task 4336 | total time = 4856.14 ms / 175 tokens 5.57.005.419 I slot print_timing: id 2 | task 4336 | graphs reused = 3428 5.57.005.420 I slot print_timing: id 2 | task 4336 | graph reallocs = 0 / 0 (same size) / (changed size) 5.57.005.517 I slot release: id 2 | task 4336 | stop processing: n_tokens = 1299, truncated = 0 5.57.574.042 I slot print_timing: id 3 | task 3775 | n_gen = 635, tg = 15.79 t/s, tg_3s = 17.73 t/s 5.57.905.764 I slot print_timing: id 0 | task 4333 | prompt eval time = 482.01 ms / 142 tokens ( 3.39 ms per token, 294.60 tokens per second) 5.57.905.770 I slot print_timing: id 0 | task 4333 | eval time = 5756.92 ms / 100 tokens ( 58.15 ms per token, 17.20 tokens per second) 5.57.905.771 I slot print_timing: id 0 | task 4333 | total time = 6238.93 ms / 242 tokens 5.57.905.772 I slot print_timing: id 0 | task 4333 | graphs reused = 3428 5.57.905.773 I slot print_timing: id 0 | task 4333 | graph reallocs = 0 / 0 (same size) / (changed size) 5.57.905.857 I slot release: id 0 | task 4333 | stop processing: n_tokens = 1366, truncated = 0 6.00.577.197 I slot print_timing: id 3 | task 3775 | n_gen = 770, tg = 17.82 t/s, tg_3s = 44.95 t/s 6.02.742.114 I slot print_timing: id 3 | task 3775 | prompt eval time = 541.81 ms / 170 tokens ( 3.19 ms per token, 313.77 tokens per second) 6.02.742.122 I slot print_timing: id 3 | task 3775 | eval time = 45321.96 ms / 874 tokens ( 51.92 ms per token, 19.26 tokens per second) 6.02.742.122 I slot print_timing: id 3 | task 3775 | total time = 45863.76 ms / 1044 tokens 6.02.742.123 I slot print_timing: id 3 | task 3775 | graphs reused = 3659 6.02.742.123 I slot print_timing: id 3 | task 3775 | graph reallocs = 0 / 0 (same size) / (changed size) 6.02.742.179 I slot release: id 3 | task 3775 | stop processing: n_tokens = 2168, truncated = 0 6.02.760.616 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1291, t_last = 390188918370 6.02.760.702 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.169 MiB) 6.02.760.711 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.794 MiB) 6.02.760.712 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.658 MiB) 6.02.783.176 I slot launch_slot_: id 1 | task 4668 | processing task, is_child = 0 6.02.783.252 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.403 MiB) 6.02.783.254 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.853 MiB) 6.02.783.256 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.797 MiB) 6.02.806.063 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.325 MiB) 6.02.806.069 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.540 MiB) 6.02.825.883 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.836 MiB) 6.02.825.886 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.051 MiB) 6.02.825.888 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.188 MiB) 6.02.847.620 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1299, t_last = 390190595647 6.02.847.744 I slot launch_slot_: id 2 | task 4669 | processing task, is_child = 0 6.02.847.887 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1366, t_last = 390191495987 6.02.847.969 I slot launch_slot_: id 0 | task 4670 | processing task, is_child = 0 6.02.848.053 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 2168, t_last = 390196332309 6.02.848.164 I slot launch_slot_: id 3 | task 4671 | processing task, is_child = 0 6.06.604.075 I slot print_timing: id 0 | task 4670 | prompt processing, n_tokens = 471, progress = 0.48, t = 3.76 s / 125.40 tokens per second 6.06.919.829 I slot print_timing: id 1 | task 4668 | prompt processing, n_tokens = 656, progress = 0.84, t = 3.76 s / 174.66 tokens per second 6.06.923.603 I slot print_timing: id 2 | task 4669 | prompt processing, n_tokens = 290, progress = 0.36, t = 3.76 s / 77.22 tokens per second 6.06.925.483 I slot print_timing: id 3 | task 4671 | prompt processing, n_tokens = 436, progress = 0.46, t = 3.76 s / 116.09 tokens per second 6.09.050.831 I slot print_timing: id 0 | task 4670 | prompt processing, n_tokens = 877, progress = 0.89, t = 6.20 s / 141.39 tokens per second 6.09.242.152 I slot print_timing: id 1 | task 4668 | prompt processing, n_tokens = 775, progress = 0.99, t = 6.20 s / 124.95 tokens per second 6.09.245.503 I slot print_timing: id 2 | task 4669 | prompt processing, n_tokens = 642, progress = 0.80, t = 6.20 s / 103.51 tokens per second 6.09.247.659 I slot print_timing: id 3 | task 4671 | prompt processing, n_tokens = 835, progress = 0.88, t = 6.20 s / 134.63 tokens per second 6.10.312.664 I slot print_timing: id 0 | task 4670 | prompt processing, n_tokens = 983, progress = 1.00, t = 7.46 s / 131.69 tokens per second 6.10.316.052 I slot print_timing: id 2 | task 4669 | prompt processing, n_tokens = 802, progress = 1.00, t = 7.46 s / 107.45 tokens per second 6.10.319.408 I slot print_timing: id 3 | task 4671 | prompt processing, n_tokens = 948, progress = 1.00, t = 7.46 s / 127.01 tokens per second 6.10.463.827 I slot print_timing: id 1 | task 4668 | prompt eval time = 7464.39 ms / 779 tokens ( 9.58 ms per token, 104.36 tokens per second) 6.10.463.829 I slot print_timing: id 1 | task 4668 | eval time = 151.17 ms / 2 tokens ( 151.17 ms per token, 6.62 tokens per second) 6.10.463.830 I slot print_timing: id 1 | task 4668 | total time = 7615.55 ms / 781 tokens 6.10.463.831 I slot print_timing: id 1 | task 4668 | graphs reused = 3659 6.10.463.831 I slot print_timing: id 1 | task 4668 | graph reallocs = 0 / 0 (same size) / (changed size) 6.10.463.864 I slot release: id 1 | task 4668 | stop processing: n_tokens = 780, truncated = 0 6.10.520.114 I slot print_timing: id 0 | task 4670 | prompt eval time = 7615.49 ms / 987 tokens ( 7.72 ms per token, 129.60 tokens per second) 6.10.520.118 I slot print_timing: id 0 | task 4670 | eval time = 56.45 ms / 2 tokens ( 56.45 ms per token, 17.71 tokens per second) 6.10.520.118 I slot print_timing: id 0 | task 4670 | total time = 7671.94 ms / 989 tokens 6.10.520.119 I slot print_timing: id 0 | task 4670 | graphs reused = 3659 6.10.520.119 I slot print_timing: id 0 | task 4670 | graph reallocs = 0 / 0 (same size) / (changed size) 6.10.520.157 I slot release: id 0 | task 4670 | stop processing: n_tokens = 988, truncated = 0 6.10.520.368 I slot print_timing: id 2 | task 4669 | prompt eval time = 7615.73 ms / 806 tokens ( 9.45 ms per token, 105.83 tokens per second) 6.10.520.373 I slot print_timing: id 2 | task 4669 | eval time = 56.29 ms / 2 tokens ( 56.29 ms per token, 17.77 tokens per second) 6.10.520.373 I slot print_timing: id 2 | task 4669 | total time = 7672.02 ms / 808 tokens 6.10.520.374 I slot print_timing: id 2 | task 4669 | graphs reused = 3659 6.10.520.374 I slot print_timing: id 2 | task 4669 | graph reallocs = 0 / 0 (same size) / (changed size) 6.10.520.400 I slot release: id 2 | task 4669 | stop processing: n_tokens = 807, truncated = 0 6.10.520.564 I slot print_timing: id 3 | task 4671 | prompt eval time = 7615.86 ms / 952 tokens ( 8.00 ms per token, 125.00 tokens per second) 6.10.520.565 I slot print_timing: id 3 | task 4671 | eval time = 56.28 ms / 2 tokens ( 56.28 ms per token, 17.77 tokens per second) 6.10.520.566 I slot print_timing: id 3 | task 4671 | total time = 7672.14 ms / 954 tokens 6.10.520.566 I slot print_timing: id 3 | task 4671 | graphs reused = 3659 6.10.520.566 I slot print_timing: id 3 | task 4671 | graph reallocs = 0 / 0 (same size) / (changed size) 6.10.520.595 I slot release: id 3 | task 4671 | stop processing: n_tokens = 953, truncated = 0 6.10.520.600 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 780, t_last = 390204053994 6.10.520.650 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.618 MiB) 6.10.520.654 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.716 MiB) 6.10.520.655 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.149 MiB) 6.10.539.264 I slot launch_slot_: id 1 | task 4679 | processing task, is_child = 0 6.10.539.316 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.892 MiB) 6.10.539.321 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.875 MiB) 6.10.560.334 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.758 MiB) 6.10.560.340 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.403 MiB) 6.10.560.341 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.638 MiB) 6.10.578.431 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.146 MiB) 6.10.578.435 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.915 MiB) 6.10.598.008 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 988, t_last = 390204110287 6.10.598.140 I slot launch_slot_: id 0 | task 4680 | processing task, is_child = 0 6.10.598.223 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 807, t_last = 390204110530 6.10.598.292 I slot launch_slot_: id 2 | task 4681 | processing task, is_child = 0 6.10.598.337 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 953, t_last = 390204110726 6.10.598.404 I slot launch_slot_: id 3 | task 4682 | processing task, is_child = 0 6.15.420.680 I slot print_timing: id 0 | task 4680 | prompt processing, n_tokens = 696, progress = 0.87, t = 4.82 s / 144.33 tokens per second 6.15.490.710 I slot print_timing: id 1 | task 4679 | prompt processing, n_tokens = 696, progress = 0.87, t = 4.82 s / 144.33 tokens per second 6.15.493.162 I slot print_timing: id 2 | task 4681 | prompt processing, n_tokens = 696, progress = 0.81, t = 4.82 s / 144.34 tokens per second 6.15.495.376 I slot print_timing: id 3 | task 4682 | prompt processing, n_tokens = 696, progress = 0.82, t = 4.82 s / 144.34 tokens per second 6.16.503.022 I slot print_timing: id 0 | task 4680 | prompt processing, n_tokens = 800, progress = 1.00, t = 5.90 s / 135.49 tokens per second 6.16.573.232 I slot print_timing: id 1 | task 4679 | prompt processing, n_tokens = 797, progress = 1.00, t = 5.90 s / 134.98 tokens per second 6.16.577.244 I slot print_timing: id 2 | task 4681 | prompt processing, n_tokens = 851, progress = 1.00, t = 5.90 s / 144.13 tokens per second 6.16.579.167 I slot print_timing: id 3 | task 4682 | prompt processing, n_tokens = 842, progress = 1.00, t = 5.90 s / 142.61 tokens per second 6.16.759.503 I slot print_timing: id 0 | task 4680 | prompt eval time = 6107.44 ms / 804 tokens ( 7.60 ms per token, 131.64 tokens per second) 6.16.759.507 I slot print_timing: id 0 | task 4680 | eval time = 53.65 ms / 2 tokens ( 53.65 ms per token, 18.64 tokens per second) 6.16.759.508 I slot print_timing: id 0 | task 4680 | total time = 6161.09 ms / 806 tokens 6.16.759.508 I slot print_timing: id 0 | task 4680 | graphs reused = 3659 6.16.759.509 I slot print_timing: id 0 | task 4680 | graph reallocs = 0 / 0 (same size) / (changed size) 6.16.759.546 I slot release: id 0 | task 4680 | stop processing: n_tokens = 805, truncated = 0 6.16.759.697 I slot print_timing: id 1 | task 4679 | prompt eval time = 6107.53 ms / 801 tokens ( 7.62 ms per token, 131.15 tokens per second) 6.16.759.701 I slot print_timing: id 1 | task 4679 | eval time = 53.66 ms / 2 tokens ( 53.66 ms per token, 18.64 tokens per second) 6.16.759.701 I slot print_timing: id 1 | task 4679 | total time = 6161.19 ms / 803 tokens 6.16.759.702 I slot print_timing: id 1 | task 4679 | graphs reused = 3659 6.16.759.702 I slot print_timing: id 1 | task 4679 | graph reallocs = 0 / 0 (same size) / (changed size) 6.16.759.725 I slot release: id 1 | task 4679 | stop processing: n_tokens = 802, truncated = 0 6.16.759.900 I slot print_timing: id 2 | task 4681 | prompt eval time = 6107.69 ms / 855 tokens ( 7.14 ms per token, 139.99 tokens per second) 6.16.759.902 I slot print_timing: id 2 | task 4681 | eval time = 53.66 ms / 2 tokens ( 53.66 ms per token, 18.63 tokens per second) 6.16.759.902 I slot print_timing: id 2 | task 4681 | total time = 6161.35 ms / 857 tokens 6.16.759.903 I slot print_timing: id 2 | task 4681 | graphs reused = 3659 6.16.759.903 I slot print_timing: id 2 | task 4681 | graph reallocs = 0 / 0 (same size) / (changed size) 6.16.759.922 I slot release: id 2 | task 4681 | stop processing: n_tokens = 856, truncated = 0 6.16.760.093 I slot print_timing: id 3 | task 4682 | prompt eval time = 6107.86 ms / 846 tokens ( 7.22 ms per token, 138.51 tokens per second) 6.16.760.098 I slot print_timing: id 3 | task 4682 | eval time = 53.63 ms / 2 tokens ( 53.63 ms per token, 18.65 tokens per second) 6.16.760.098 I slot print_timing: id 3 | task 4682 | total time = 6161.49 ms / 848 tokens 6.16.760.098 I slot print_timing: id 3 | task 4682 | graphs reused = 3659 6.16.760.099 I slot print_timing: id 3 | task 4682 | graph reallocs = 0 / 0 (same size) / (changed size) 6.16.760.119 I slot release: id 3 | task 4682 | stop processing: n_tokens = 847, truncated = 0 6.16.767.639 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 805, t_last = 390210349676 6.16.767.743 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.266 MiB) 6.16.767.747 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.286 MiB) 6.16.767.748 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.736 MiB) 6.16.785.306 I slot launch_slot_: id 0 | task 4690 | processing task, is_child = 0 6.16.785.352 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.032 MiB) 6.16.785.355 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.934 MiB) 6.16.804.385 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.716 MiB) 6.16.804.390 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.560 MiB) 6.16.804.391 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.560 MiB) 6.16.822.365 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.677 MiB) 6.16.822.372 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.775 MiB) 6.16.822.374 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.658 MiB) 6.16.840.688 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.878 (> 0.100 thold), f_keep = 0.903 6.16.840.744 I slot launch_slot_: id 1 | task 4691 | processing task, is_child = 0 6.16.840.834 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 856, t_last = 390210350052 6.16.840.898 I slot launch_slot_: id 2 | task 4692 | processing task, is_child = 0 6.16.840.948 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 847, t_last = 390210350249 6.16.841.012 I slot launch_slot_: id 3 | task 4693 | processing task, is_child = 0 6.19.788.705 I slot print_timing: id 1 | task 4691 | prompt eval time = 2348.71 ms / 129 tokens ( 18.21 ms per token, 54.92 tokens per second) 6.19.788.708 I slot print_timing: id 1 | task 4691 | eval time = 598.90 ms / 2 tokens ( 598.90 ms per token, 1.67 tokens per second) 6.19.788.708 I slot print_timing: id 1 | task 4691 | total time = 2947.62 ms / 131 tokens 6.19.788.709 I slot print_timing: id 1 | task 4691 | graphs reused = 3659 6.19.788.709 I slot print_timing: id 1 | task 4691 | graph reallocs = 0 / 0 (same size) / (changed size) 6.19.788.744 I slot release: id 1 | task 4691 | stop processing: n_tokens = 826, truncated = 0 6.21.721.723 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 826, t_last = 390213378874 6.21.721.787 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.875 MiB) 6.21.721.790 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.641 MiB) 6.21.832.936 I slot launch_slot_: id 1 | task 4698 | processing task, is_child = 0 6.21.832.950 I slot print_timing: id 0 | task 4690 | prompt processing, n_tokens = 831, progress = 0.86, t = 4.88 s / 170.26 tokens per second 6.21.834.888 I slot print_timing: id 2 | task 4692 | prompt processing, n_tokens = 754, progress = 0.84, t = 4.88 s / 154.60 tokens per second 6.21.836.793 I slot print_timing: id 3 | task 4693 | prompt processing, n_tokens = 754, progress = 0.86, t = 4.88 s / 154.60 tokens per second 6.22.950.543 I slot print_timing: id 0 | task 4690 | prompt processing, n_tokens = 959, progress = 1.00, t = 6.11 s / 156.97 tokens per second 6.23.131.716 I slot print_timing: id 2 | task 4692 | prompt processing, n_tokens = 892, progress = 1.00, t = 6.11 s / 146.09 tokens per second 6.23.133.705 I slot print_timing: id 3 | task 4693 | prompt processing, n_tokens = 876, progress = 1.00, t = 6.11 s / 143.47 tokens per second 6.23.996.625 I slot print_timing: id 0 | task 4690 | prompt eval time = 6859.02 ms / 963 tokens ( 7.12 ms per token, 140.40 tokens per second) 6.23.996.628 I slot print_timing: id 0 | task 4690 | eval time = 296.59 ms / 2 tokens ( 296.59 ms per token, 3.37 tokens per second) 6.23.996.629 I slot print_timing: id 0 | task 4690 | total time = 7155.61 ms / 965 tokens 6.23.996.630 I slot print_timing: id 0 | task 4690 | graphs reused = 3659 6.23.996.630 I slot print_timing: id 0 | task 4690 | graph reallocs = 0 / 0 (same size) / (changed size) 6.23.996.678 I slot release: id 0 | task 4690 | stop processing: n_tokens = 964, truncated = 0 6.23.996.833 I slot print_timing: id 2 | task 4692 | prompt eval time = 6855.72 ms / 896 tokens ( 7.65 ms per token, 130.69 tokens per second) 6.23.996.836 I slot print_timing: id 2 | task 4692 | eval time = 296.56 ms / 2 tokens ( 296.56 ms per token, 3.37 tokens per second) 6.23.996.836 I slot print_timing: id 2 | task 4692 | total time = 7152.28 ms / 898 tokens 6.23.996.836 I slot print_timing: id 2 | task 4692 | graphs reused = 3659 6.23.996.837 I slot print_timing: id 2 | task 4692 | graph reallocs = 0 / 0 (same size) / (changed size) 6.23.996.874 I slot release: id 2 | task 4692 | stop processing: n_tokens = 897, truncated = 0 6.23.997.040 I slot print_timing: id 3 | task 4693 | prompt eval time = 6855.89 ms / 880 tokens ( 7.79 ms per token, 128.36 tokens per second) 6.23.997.042 I slot print_timing: id 3 | task 4693 | eval time = 296.55 ms / 2 tokens ( 296.55 ms per token, 3.37 tokens per second) 6.23.997.042 I slot print_timing: id 3 | task 4693 | total time = 7152.43 ms / 882 tokens 6.23.997.043 I slot print_timing: id 3 | task 4693 | graphs reused = 3659 6.23.997.043 I slot print_timing: id 3 | task 4693 | graph reallocs = 0 / 0 (same size) / (changed size) 6.23.997.072 I slot release: id 3 | task 4693 | stop processing: n_tokens = 881, truncated = 0 6.24.698.675 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 964, t_last = 390217586808 6.24.698.730 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.264 MiB) 6.24.698.732 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.110 MiB) 6.24.698.735 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.032 MiB) 6.25.004.165 I slot launch_slot_: id 0 | task 4704 | processing task, is_child = 0 6.25.004.217 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.797 MiB) 6.25.004.220 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.853 MiB) 6.25.020.997 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.091 MiB) 6.25.021.001 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.032 MiB) 6.25.021.002 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.325 MiB) 6.25.035.822 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 897, t_last = 390217587005 6.25.035.931 I slot launch_slot_: id 2 | task 4705 | processing task, is_child = 0 6.25.035.976 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 881, t_last = 390217587202 6.25.036.047 I slot launch_slot_: id 3 | task 4706 | processing task, is_child = 0 6.27.019.140 I slot print_timing: id 1 | task 4698 | prompt eval time = 4152.89 ms / 987 tokens ( 4.21 ms per token, 237.67 tokens per second) 6.27.019.142 I slot print_timing: id 1 | task 4698 | eval time = 1031.41 ms / 2 tokens ( 1031.41 ms per token, 0.97 tokens per second) 6.27.019.143 I slot print_timing: id 1 | task 4698 | total time = 5184.30 ms / 989 tokens 6.27.019.144 I slot print_timing: id 1 | task 4698 | graphs reused = 3659 6.27.019.144 I slot print_timing: id 1 | task 4698 | graph reallocs = 0 / 0 (same size) / (changed size) 6.27.019.189 I slot release: id 1 | task 4698 | stop processing: n_tokens = 988, truncated = 0 6.27.759.977 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 988, t_last = 390220609319 6.27.760.040 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.345 MiB) 6.27.760.043 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.993 MiB) 6.27.760.046 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.736 MiB) 6.28.378.708 I slot launch_slot_: id 1 | task 4710 | processing task, is_child = 0 6.30.500.692 I slot print_timing: id 0 | task 4704 | prompt processing, n_tokens = 872, progress = 0.85, t = 5.46 s / 159.57 tokens per second 6.30.888.900 I slot print_timing: id 2 | task 4705 | prompt processing, n_tokens = 753, progress = 0.81, t = 5.46 s / 137.85 tokens per second 6.30.890.779 I slot print_timing: id 3 | task 4706 | prompt processing, n_tokens = 1264, progress = 0.71, t = 5.46 s / 231.40 tokens per second 6.32.369.415 I slot print_timing: id 0 | task 4704 | prompt processing, n_tokens = 1018, progress = 1.00, t = 7.33 s / 138.82 tokens per second 6.33.003.384 I slot print_timing: id 1 | task 4710 | prompt processing, n_tokens = 283, progress = 0.30, t = 3.99 s / 70.95 tokens per second 6.33.003.399 I slot print_timing: id 2 | task 4705 | prompt processing, n_tokens = 920, progress = 1.00, t = 7.33 s / 125.49 tokens per second 6.33.006.595 I slot print_timing: id 3 | task 4706 | prompt processing, n_tokens = 1776, progress = 1.00, t = 7.33 s / 242.25 tokens per second 6.33.468.727 I slot print_timing: id 1 | task 4710 | prompt processing, n_tokens = 421, progress = 0.45, t = 5.09 s / 82.76 tokens per second 6.34.143.126 I slot print_timing: id 0 | task 4704 | prompt eval time = 8432.22 ms / 1022 tokens ( 8.25 ms per token, 121.20 tokens per second) 6.34.143.128 I slot print_timing: id 0 | task 4704 | eval time = 674.85 ms / 2 tokens ( 674.85 ms per token, 1.48 tokens per second) 6.34.143.128 I slot print_timing: id 0 | task 4704 | total time = 9107.07 ms / 1024 tokens 6.34.143.129 I slot print_timing: id 0 | task 4704 | graphs reused = 3659 6.34.143.129 I slot print_timing: id 0 | task 4704 | graph reallocs = 0 / 0 (same size) / (changed size) 6.34.143.173 I slot release: id 0 | task 4704 | stop processing: n_tokens = 1023, truncated = 0 6.34.143.326 I slot print_timing: id 2 | task 4705 | prompt eval time = 8430.31 ms / 924 tokens ( 9.12 ms per token, 109.60 tokens per second) 6.34.143.328 I slot print_timing: id 2 | task 4705 | eval time = 674.84 ms / 2 tokens ( 674.84 ms per token, 1.48 tokens per second) 6.34.143.329 I slot print_timing: id 2 | task 4705 | total time = 9105.16 ms / 926 tokens 6.34.143.329 I slot print_timing: id 2 | task 4705 | graphs reused = 3659 6.34.143.329 I slot print_timing: id 2 | task 4705 | graph reallocs = 0 / 0 (same size) / (changed size) 6.34.143.367 I slot release: id 2 | task 4705 | stop processing: n_tokens = 925, truncated = 0 6.34.143.538 I slot print_timing: id 3 | task 4706 | prompt eval time = 8430.49 ms / 1780 tokens ( 4.74 ms per token, 211.14 tokens per second) 6.34.143.539 I slot print_timing: id 3 | task 4706 | eval time = 674.82 ms / 2 tokens ( 674.82 ms per token, 1.48 tokens per second) 6.34.143.540 I slot print_timing: id 3 | task 4706 | total time = 9105.31 ms / 1782 tokens 6.34.143.540 I slot print_timing: id 3 | task 4706 | graphs reused = 3659 6.34.143.540 I slot print_timing: id 3 | task 4706 | graph reallocs = 0 / 0 (same size) / (changed size) 6.34.143.602 I slot release: id 3 | task 4706 | stop processing: n_tokens = 1781, truncated = 0 6.34.143.613 I slot print_timing: id 1 | task 4710 | prompt processing, n_tokens = 753, progress = 0.80, t = 5.76 s / 130.68 tokens per second 6.34.151.785 I slot print_timing: id 1 | task 4710 | prompt processing, n_tokens = 933, progress = 1.00, t = 5.77 s / 161.67 tokens per second 6.34.603.330 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1023, t_last = 390227733303 6.34.603.389 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.931 MiB) 6.34.603.393 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.384 MiB) 6.34.622.492 I slot launch_slot_: id 0 | task 4718 | processing task, is_child = 0 6.34.622.550 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.660 MiB) 6.34.622.552 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.247 MiB) 6.34.622.556 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.205 MiB) 6.34.637.130 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.677 MiB) 6.34.637.134 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.071 MiB) 6.34.653.612 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 925, t_last = 390227733497 6.34.653.719 I slot launch_slot_: id 2 | task 4717 | processing task, is_child = 0 6.34.653.791 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1781, t_last = 390227733733 6.34.653.878 I slot launch_slot_: id 3 | task 4719 | processing task, is_child = 0 6.35.612.280 I slot print_timing: id 1 | task 4710 | prompt eval time = 6222.45 ms / 937 tokens ( 6.64 ms per token, 150.58 tokens per second) 6.35.612.283 I slot print_timing: id 1 | task 4710 | eval time = 1008.95 ms / 2 tokens ( 1008.95 ms per token, 0.99 tokens per second) 6.35.612.285 I slot print_timing: id 1 | task 4710 | total time = 7231.40 ms / 939 tokens 6.35.612.285 I slot print_timing: id 1 | task 4710 | graphs reused = 3659 6.35.612.285 I slot print_timing: id 1 | task 4710 | graph reallocs = 0 / 0 (same size) / (changed size) 6.35.612.334 I slot release: id 1 | task 4710 | stop processing: n_tokens = 938, truncated = 0 6.36.272.226 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 938, t_last = 390229202464 6.36.272.286 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.462 MiB) 6.36.272.292 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 340.758 MiB) 6.36.465.335 I slot launch_slot_: id 1 | task 4722 | processing task, is_child = 0 6.37.872.254 I slot print_timing: id 0 | task 4718 | prompt processing, n_tokens = 603, progress = 0.81, t = 3.22 s / 187.36 tokens per second 6.38.404.592 I slot print_timing: id 2 | task 4717 | prompt processing, n_tokens = 603, progress = 0.85, t = 3.22 s / 187.37 tokens per second 6.38.406.481 I slot print_timing: id 3 | task 4719 | prompt processing, n_tokens = 364, progress = 0.41, t = 3.22 s / 113.11 tokens per second 6.39.407.048 I slot print_timing: id 0 | task 4718 | prompt processing, n_tokens = 737, progress = 0.99, t = 4.75 s / 155.05 tokens per second 6.39.975.911 I slot print_timing: id 2 | task 4717 | prompt processing, n_tokens = 709, progress = 0.99, t = 4.75 s / 149.17 tokens per second 6.39.977.878 I slot print_timing: id 3 | task 4719 | prompt processing, n_tokens = 769, progress = 0.87, t = 4.75 s / 161.79 tokens per second 6.41.082.733 I slot print_timing: id 1 | task 4722 | prompt processing, n_tokens = 603, progress = 0.84, t = 4.61 s / 130.69 tokens per second 6.41.085.563 I slot print_timing: id 3 | task 4719 | prompt processing, n_tokens = 876, progress = 1.00, t = 6.43 s / 136.27 tokens per second 6.41.483.022 I slot print_timing: id 0 | task 4718 | prompt eval time = 6428.61 ms / 741 tokens ( 8.68 ms per token, 115.27 tokens per second) 6.41.483.027 I slot print_timing: id 0 | task 4718 | eval time = 400.53 ms / 2 tokens ( 400.53 ms per token, 2.50 tokens per second) 6.41.483.028 I slot print_timing: id 0 | task 4718 | total time = 6829.13 ms / 743 tokens 6.41.483.028 I slot print_timing: id 0 | task 4718 | graphs reused = 3659 6.41.483.028 I slot print_timing: id 0 | task 4718 | graph reallocs = 0 / 0 (same size) / (changed size) 6.41.483.065 I slot release: id 0 | task 4718 | stop processing: n_tokens = 742, truncated = 0 6.41.483.298 I slot print_timing: id 2 | task 4717 | prompt eval time = 6428.76 ms / 713 tokens ( 9.02 ms per token, 110.91 tokens per second) 6.41.483.301 I slot print_timing: id 2 | task 4717 | eval time = 400.57 ms / 2 tokens ( 400.57 ms per token, 2.50 tokens per second) 6.41.483.302 I slot print_timing: id 2 | task 4717 | total time = 6829.34 ms / 715 tokens 6.41.483.302 I slot print_timing: id 2 | task 4717 | graphs reused = 3659 6.41.483.302 I slot print_timing: id 2 | task 4717 | graph reallocs = 0 / 0 (same size) / (changed size) 6.41.483.324 I slot release: id 2 | task 4717 | stop processing: n_tokens = 714, truncated = 0 6.41.483.582 I slot print_timing: id 1 | task 4722 | prompt processing, n_tokens = 712, progress = 0.99, t = 5.01 s / 141.99 tokens per second 6.41.553.036 I slot print_timing: id 3 | task 4719 | prompt eval time = 6829.56 ms / 880 tokens ( 7.76 ms per token, 128.85 tokens per second) 6.41.553.038 I slot print_timing: id 3 | task 4719 | eval time = 69.46 ms / 2 tokens ( 69.46 ms per token, 14.40 tokens per second) 6.41.553.039 I slot print_timing: id 3 | task 4719 | total time = 6899.02 ms / 882 tokens 6.41.553.039 I slot print_timing: id 3 | task 4719 | graphs reused = 3659 6.41.553.040 I slot print_timing: id 3 | task 4719 | graph reallocs = 0 / 0 (same size) / (changed size) 6.41.553.078 I slot release: id 3 | task 4719 | stop processing: n_tokens = 881, truncated = 0 6.41.553.085 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.878 (> 0.100 thold), f_keep = 0.850 6.41.553.124 I slot launch_slot_: id 0 | task 4728 | processing task, is_child = 0 6.41.553.175 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 341.051 MiB) 6.41.560.885 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 339.233 MiB) 6.41.569.661 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 6.41.569.715 I slot launch_slot_: id 2 | task 4729 | processing task, is_child = 0 6.41.569.762 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 881, t_last = 390235143208 6.41.569.847 I slot launch_slot_: id 3 | task 4730 | processing task, is_child = 0 6.42.505.044 I slot print_timing: id 1 | task 4722 | prompt eval time = 5084.58 ms / 716 tokens ( 7.10 ms per token, 140.82 tokens per second) 6.42.505.047 I slot print_timing: id 1 | task 4722 | eval time = 952.15 ms / 2 tokens ( 952.15 ms per token, 1.05 tokens per second) 6.42.505.047 I slot print_timing: id 1 | task 4722 | total time = 6036.73 ms / 718 tokens 6.42.505.048 I slot print_timing: id 1 | task 4722 | graphs reused = 3659 6.42.505.048 I slot print_timing: id 1 | task 4722 | graph reallocs = 0 / 0 (same size) / (changed size) 6.42.505.088 I slot release: id 1 | task 4722 | stop processing: n_tokens = 717, truncated = 0 6.42.959.936 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 717, t_last = 390236095218 6.42.959.987 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 339.096 MiB) 6.42.969.860 I slot launch_slot_: id 1 | task 4733 | processing task, is_child = 0 6.43.614.112 I slot print_timing: id 0 | task 4728 | prompt eval time = 1389.84 ms / 116 tokens ( 11.98 ms per token, 83.46 tokens per second) 6.43.614.114 I slot print_timing: id 0 | task 4728 | eval time = 654.42 ms / 2 tokens ( 654.42 ms per token, 1.53 tokens per second) 6.43.614.114 I slot print_timing: id 0 | task 4728 | total time = 2044.25 ms / 118 tokens 6.43.614.115 I slot print_timing: id 0 | task 4728 | graphs reused = 3659 6.43.614.115 I slot print_timing: id 0 | task 4728 | graph reallocs = 0 / 0 (same size) / (changed size) 6.43.614.154 I slot release: id 0 | task 4728 | stop processing: n_tokens = 720, truncated = 0 6.43.614.402 I slot print_timing: id 2 | task 4729 | prompt eval time = 1386.55 ms / 122 tokens ( 11.37 ms per token, 87.99 tokens per second) 6.43.614.405 I slot print_timing: id 2 | task 4729 | eval time = 654.47 ms / 2 tokens ( 654.47 ms per token, 1.53 tokens per second) 6.43.614.405 I slot print_timing: id 2 | task 4729 | total time = 2041.02 ms / 124 tokens 6.43.614.406 I slot print_timing: id 2 | task 4729 | graphs reused = 3659 6.43.614.406 I slot print_timing: id 2 | task 4729 | graph reallocs = 0 / 0 (same size) / (changed size) 6.43.614.437 I slot release: id 2 | task 4729 | stop processing: n_tokens = 726, truncated = 0 6.44.048.978 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 720, t_last = 390237204284 6.44.049.027 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 339.311 MiB) 6.44.734.917 I slot launch_slot_: id 0 | task 4736 | processing task, is_child = 0 6.44.734.967 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 340.777 MiB) 6.44.742.539 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 726, t_last = 390237204567 6.44.742.614 I slot launch_slot_: id 2 | task 4737 | processing task, is_child = 0 6.45.877.508 I slot print_timing: id 3 | task 4730 | prompt processing, n_tokens = 872, progress = 1.00, t = 4.22 s / 206.87 tokens per second 6.47.452.089 I slot print_timing: id 1 | task 4733 | prompt processing, n_tokens = 861, progress = 0.87, t = 4.48 s / 192.10 tokens per second 6.48.456.291 I slot print_timing: id 3 | task 4730 | prompt eval time = 5875.33 ms / 876 tokens ( 6.71 ms per token, 149.10 tokens per second) 6.48.456.294 I slot print_timing: id 3 | task 4730 | eval time = 1004.23 ms / 2 tokens ( 1004.23 ms per token, 1.00 tokens per second) 6.48.456.295 I slot print_timing: id 3 | task 4730 | total time = 6879.55 ms / 878 tokens 6.48.456.295 I slot print_timing: id 3 | task 4730 | graphs reused = 3659 6.48.456.296 I slot print_timing: id 3 | task 4730 | graph reallocs = 0 / 0 (same size) / (changed size) 6.48.456.334 I slot release: id 3 | task 4730 | stop processing: n_tokens = 877, truncated = 0 6.48.456.344 I slot print_timing: id 0 | task 4736 | prompt processing, n_tokens = 490, progress = 0.49, t = 3.71 s / 131.95 tokens per second 6.48.459.646 I slot print_timing: id 1 | task 4733 | prompt processing, n_tokens = 988, progress = 1.00, t = 5.49 s / 180.09 tokens per second 6.48.461.659 I slot print_timing: id 2 | task 4737 | prompt processing, n_tokens = 518, progress = 0.50, t = 3.71 s / 139.49 tokens per second 6.49.801.812 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 877, t_last = 390242046464 6.49.801.869 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 339.467 MiB) 6.49.810.480 I slot launch_slot_: id 3 | task 4742 | processing task, is_child = 0 6.49.810.492 I slot print_timing: id 0 | task 4736 | prompt processing, n_tokens = 861, progress = 0.86, t = 5.06 s / 170.19 tokens per second 6.49.812.357 I slot print_timing: id 2 | task 4737 | prompt processing, n_tokens = 861, progress = 0.83, t = 5.06 s / 170.19 tokens per second 6.50.908.386 I slot print_timing: id 1 | task 4733 | prompt eval time = 6831.94 ms / 992 tokens ( 6.89 ms per token, 145.20 tokens per second) 6.50.908.389 I slot print_timing: id 1 | task 4733 | eval time = 1106.57 ms / 2 tokens ( 1106.57 ms per token, 0.90 tokens per second) 6.50.908.390 I slot print_timing: id 1 | task 4733 | total time = 7938.51 ms / 994 tokens 6.50.908.390 I slot print_timing: id 1 | task 4733 | graphs reused = 3659 6.50.908.391 I slot print_timing: id 1 | task 4733 | graph reallocs = 0 / 0 (same size) / (changed size) 6.50.908.432 I slot release: id 1 | task 4733 | stop processing: n_tokens = 993, truncated = 0 6.50.908.443 I slot print_timing: id 0 | task 4736 | prompt processing, n_tokens = 1002, progress = 1.00, t = 6.17 s / 162.52 tokens per second 6.50.911.174 I slot print_timing: id 2 | task 4737 | prompt processing, n_tokens = 1030, progress = 1.00, t = 6.17 s / 167.06 tokens per second 6.51.450.607 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.895 (> 0.100 thold), f_keep = 0.895 6.51.450.670 I slot launch_slot_: id 1 | task 4745 | processing task, is_child = 0 6.52.168.949 I slot print_timing: id 0 | task 4736 | prompt eval time = 6707.80 ms / 1006 tokens ( 6.67 ms per token, 149.97 tokens per second) 6.52.168.951 I slot print_timing: id 0 | task 4736 | eval time = 718.52 ms / 2 tokens ( 718.52 ms per token, 1.39 tokens per second) 6.52.168.952 I slot print_timing: id 0 | task 4736 | total time = 7426.32 ms / 1008 tokens 6.52.168.952 I slot print_timing: id 0 | task 4736 | graphs reused = 3659 6.52.168.952 I slot print_timing: id 0 | task 4736 | graph reallocs = 0 / 0 (same size) / (changed size) 6.52.168.994 I slot release: id 0 | task 4736 | stop processing: n_tokens = 1007, truncated = 0 6.52.169.225 I slot print_timing: id 2 | task 4737 | prompt eval time = 6707.91 ms / 1034 tokens ( 6.49 ms per token, 154.15 tokens per second) 6.52.169.227 I slot print_timing: id 2 | task 4737 | eval time = 718.62 ms / 2 tokens ( 718.62 ms per token, 1.39 tokens per second) 6.52.169.227 I slot print_timing: id 2 | task 4737 | total time = 7426.53 ms / 1036 tokens 6.52.169.227 I slot print_timing: id 2 | task 4737 | graphs reused = 3659 6.52.169.228 I slot print_timing: id 2 | task 4737 | graph reallocs = 0 / 0 (same size) / (changed size) 6.52.169.265 I slot release: id 2 | task 4737 | stop processing: n_tokens = 1035, truncated = 0 6.52.869.360 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1007, t_last = 390245759125 6.52.869.419 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 356.460 MiB) 6.52.878.013 I slot launch_slot_: id 0 | task 4748 | processing task, is_child = 0 6.52.878.068 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 329.319 MiB) 6.52.894.675 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1035, t_last = 390245759395 6.52.894.766 I slot launch_slot_: id 2 | task 4749 | processing task, is_child = 0 6.52.894.921 I slot print_timing: id 3 | task 4742 | prompt processing, n_tokens = 861, progress = 0.86, t = 3.05 s / 281.84 tokens per second 6.53.971.792 I slot print_timing: id 1 | task 4745 | prompt eval time = 1418.67 ms / 132 tokens ( 10.75 ms per token, 93.04 tokens per second) 6.53.971.795 I slot print_timing: id 1 | task 4745 | eval time = 1102.43 ms / 2 tokens ( 1102.43 ms per token, 0.91 tokens per second) 6.53.971.795 I slot print_timing: id 1 | task 4745 | total time = 2521.11 ms / 134 tokens 6.53.971.796 I slot print_timing: id 1 | task 4745 | graphs reused = 3659 6.53.971.796 I slot print_timing: id 1 | task 4745 | graph reallocs = 0 / 0 (same size) / (changed size) 6.53.971.834 I slot release: id 1 | task 4745 | stop processing: n_tokens = 994, truncated = 0 6.53.977.176 I slot print_timing: id 3 | task 4742 | prompt processing, n_tokens = 995, progress = 1.00, t = 4.16 s / 239.34 tokens per second 6.54.768.291 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 994, t_last = 390247561964 6.54.768.357 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 333.386 MiB) 6.54.790.050 I slot launch_slot_: id 1 | task 4752 | processing task, is_child = 0 6.55.717.290 I slot print_timing: id 3 | task 4742 | prompt eval time = 4954.05 ms / 999 tokens ( 4.96 ms per token, 201.65 tokens per second) 6.55.717.296 I slot print_timing: id 3 | task 4742 | eval time = 949.00 ms / 2 tokens ( 949.00 ms per token, 1.05 tokens per second) 6.55.717.296 I slot print_timing: id 3 | task 4742 | total time = 5903.05 ms / 1001 tokens 6.55.717.297 I slot print_timing: id 3 | task 4742 | graphs reused = 3659 6.55.717.297 I slot print_timing: id 3 | task 4742 | graph reallocs = 0 / 0 (same size) / (changed size) 6.55.717.341 I slot release: id 3 | task 4742 | stop processing: n_tokens = 1000, truncated = 0 6.57.130.902 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1000, t_last = 390249307471 6.57.130.975 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 329.847 MiB) 6.57.394.440 I slot launch_slot_: id 3 | task 4755 | processing task, is_child = 0 6.57.394.456 I slot print_timing: id 0 | task 4748 | prompt processing, n_tokens = 730, progress = 0.83, t = 4.24 s / 172.33 tokens per second 6.57.396.306 I slot print_timing: id 2 | task 4749 | prompt processing, n_tokens = 773, progress = 0.76, t = 4.24 s / 182.48 tokens per second 6.58.448.210 I slot print_timing: id 0 | task 4748 | prompt processing, n_tokens = 875, progress = 1.00, t = 5.55 s / 157.56 tokens per second 6.58.771.014 I slot print_timing: id 1 | task 4752 | prompt processing, n_tokens = 380, progress = 0.42, t = 3.66 s / 103.88 tokens per second 6.58.773.160 I slot print_timing: id 2 | task 4749 | prompt processing, n_tokens = 1014, progress = 1.00, t = 5.55 s / 182.59 tokens per second 6.59.962.378 I slot print_timing: id 1 | task 4752 | prompt processing, n_tokens = 773, progress = 0.86, t = 5.17 s / 149.46 tokens per second 7.00.768.475 I slot print_timing: id 0 | task 4748 | prompt eval time = 7067.36 ms / 879 tokens ( 8.04 ms per token, 124.37 tokens per second) 7.00.768.481 I slot print_timing: id 0 | task 4748 | eval time = 806.33 ms / 2 tokens ( 806.33 ms per token, 1.24 tokens per second) 7.00.768.482 I slot print_timing: id 0 | task 4748 | total time = 7873.69 ms / 881 tokens 7.00.768.482 I slot print_timing: id 0 | task 4748 | graphs reused = 3659 7.00.768.483 I slot print_timing: id 0 | task 4748 | graph reallocs = 0 / 0 (same size) / (changed size) 7.00.768.522 I slot release: id 0 | task 4748 | stop processing: n_tokens = 880, truncated = 0 7.00.768.754 I slot print_timing: id 2 | task 4749 | prompt eval time = 7067.51 ms / 1018 tokens ( 6.94 ms per token, 144.04 tokens per second) 7.00.768.759 I slot print_timing: id 2 | task 4749 | eval time = 806.39 ms / 2 tokens ( 806.39 ms per token, 1.24 tokens per second) 7.00.768.759 I slot print_timing: id 2 | task 4749 | total time = 7873.90 ms / 1020 tokens 7.00.768.759 I slot print_timing: id 2 | task 4749 | graphs reused = 3659 7.00.768.760 I slot print_timing: id 2 | task 4749 | graph reallocs = 0 / 0 (same size) / (changed size) 7.00.768.797 I slot release: id 2 | task 4749 | stop processing: n_tokens = 1019, truncated = 0 7.00.768.804 I slot print_timing: id 1 | task 4752 | prompt processing, n_tokens = 892, progress = 1.00, t = 5.98 s / 149.21 tokens per second 7.00.771.334 I slot print_timing: id 3 | task 4755 | prompt processing, n_tokens = 493, progress = 0.49, t = 3.37 s / 146.29 tokens per second 7.01.340.848 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.813 (> 0.100 thold), f_keep = 0.786 7.01.340.892 I slot launch_slot_: id 2 | task 4760 | processing task, is_child = 0 7.01.340.952 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 332.701 MiB) 7.01.350.121 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 880, t_last = 390254358652 7.01.350.197 I slot launch_slot_: id 0 | task 4761 | processing task, is_child = 0 7.01.353.499 I slot print_timing: id 3 | task 4755 | prompt processing, n_tokens = 773, progress = 0.77, t = 3.94 s / 196.07 tokens per second 7.02.568.943 I slot print_timing: id 1 | task 4752 | prompt eval time = 6550.78 ms / 896 tokens ( 7.31 ms per token, 136.78 tokens per second) 7.02.568.948 I slot print_timing: id 1 | task 4752 | eval time = 1228.10 ms / 2 tokens ( 1228.10 ms per token, 0.81 tokens per second) 7.02.568.948 I slot print_timing: id 1 | task 4752 | total time = 7778.87 ms / 898 tokens 7.02.568.949 I slot print_timing: id 1 | task 4752 | graphs reused = 3659 7.02.568.949 I slot print_timing: id 1 | task 4752 | graph reallocs = 0 / 0 (same size) / (changed size) 7.02.568.993 I slot release: id 1 | task 4752 | stop processing: n_tokens = 897, truncated = 0 7.02.575.027 I slot print_timing: id 3 | task 4755 | prompt processing, n_tokens = 1005, progress = 1.00, t = 5.17 s / 194.37 tokens per second 7.03.036.664 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 7.03.036.737 I slot launch_slot_: id 1 | task 4764 | processing task, is_child = 0 7.03.570.885 I slot print_timing: id 2 | task 4760 | prompt eval time = 1686.20 ms / 212 tokens ( 7.95 ms per token, 125.73 tokens per second) 7.03.570.890 I slot print_timing: id 2 | task 4760 | eval time = 534.40 ms / 2 tokens ( 534.40 ms per token, 1.87 tokens per second) 7.03.570.890 I slot print_timing: id 2 | task 4760 | total time = 2220.60 ms / 214 tokens 7.03.570.891 I slot print_timing: id 2 | task 4760 | graphs reused = 3659 7.03.570.891 I slot print_timing: id 2 | task 4760 | graph reallocs = 0 / 0 (same size) / (changed size) 7.03.570.940 I slot release: id 2 | task 4760 | stop processing: n_tokens = 986, truncated = 0 7.03.571.100 I slot print_timing: id 3 | task 4755 | prompt eval time = 5638.43 ms / 1009 tokens ( 5.59 ms per token, 178.95 tokens per second) 7.03.571.103 I slot print_timing: id 3 | task 4755 | eval time = 534.45 ms / 2 tokens ( 534.45 ms per token, 1.87 tokens per second) 7.03.571.103 I slot print_timing: id 3 | task 4755 | total time = 6172.87 ms / 1011 tokens 7.03.571.104 I slot print_timing: id 3 | task 4755 | graphs reused = 3659 7.03.571.104 I slot print_timing: id 3 | task 4755 | graph reallocs = 0 / 0 (same size) / (changed size) 7.03.571.138 I slot release: id 3 | task 4755 | stop processing: n_tokens = 1010, truncated = 0 7.04.298.194 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 986, t_last = 390257161070 7.04.298.268 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 329.807 MiB) 7.04.307.119 I slot launch_slot_: id 2 | task 4767 | processing task, is_child = 0 7.04.307.172 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 329.749 MiB) 7.04.324.140 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1010, t_last = 390257161268 7.04.324.236 I slot launch_slot_: id 3 | task 4768 | processing task, is_child = 0 7.05.118.628 I slot print_timing: id 1 | task 4764 | prompt eval time = 1261.43 ms / 108 tokens ( 11.68 ms per token, 85.62 tokens per second) 7.05.118.630 I slot print_timing: id 1 | task 4764 | eval time = 820.43 ms / 2 tokens ( 820.43 ms per token, 1.22 tokens per second) 7.05.118.631 I slot print_timing: id 1 | task 4764 | total time = 2081.87 ms / 110 tokens 7.05.118.631 I slot print_timing: id 1 | task 4764 | graphs reused = 3659 7.05.118.632 I slot print_timing: id 1 | task 4764 | graph reallocs = 0 / 0 (same size) / (changed size) 7.05.118.677 I slot release: id 1 | task 4764 | stop processing: n_tokens = 882, truncated = 0 7.05.118.692 I slot print_timing: id 0 | task 4761 | prompt processing, n_tokens = 898, progress = 1.00, t = 3.77 s / 238.31 tokens per second 7.05.613.786 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 882, t_last = 390258708807 7.05.613.844 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 330.805 MiB) 7.05.632.678 I slot launch_slot_: id 1 | task 4771 | processing task, is_child = 0 7.06.671.040 I slot print_timing: id 0 | task 4761 | prompt eval time = 4263.58 ms / 902 tokens ( 4.73 ms per token, 211.56 tokens per second) 7.06.671.042 I slot print_timing: id 0 | task 4761 | eval time = 1057.25 ms / 2 tokens ( 1057.25 ms per token, 0.95 tokens per second) 7.06.671.042 I slot print_timing: id 0 | task 4761 | total time = 5320.83 ms / 904 tokens 7.06.671.043 I slot print_timing: id 0 | task 4761 | graphs reused = 3659 7.06.671.043 I slot print_timing: id 0 | task 4761 | graph reallocs = 0 / 0 (same size) / (changed size) 7.06.671.086 I slot release: id 0 | task 4761 | stop processing: n_tokens = 903, truncated = 0 7.08.023.859 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 903, t_last = 390260261216 7.08.023.928 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 330.629 MiB) 7.08.217.585 I slot launch_slot_: id 0 | task 4774 | processing task, is_child = 0 7.08.217.677 I slot print_timing: id 2 | task 4767 | prompt processing, n_tokens = 774, progress = 0.85, t = 3.70 s / 209.32 tokens per second 7.08.219.713 I slot print_timing: id 3 | task 4768 | prompt processing, n_tokens = 774, progress = 0.81, t = 3.70 s / 209.32 tokens per second 7.09.639.396 I slot print_timing: id 1 | task 4771 | prompt processing, n_tokens = 424, progress = 0.45, t = 3.81 s / 111.18 tokens per second 7.09.643.347 I slot print_timing: id 2 | task 4767 | prompt processing, n_tokens = 902, progress = 1.00, t = 5.12 s / 176.16 tokens per second 7.09.645.360 I slot print_timing: id 3 | task 4768 | prompt processing, n_tokens = 948, progress = 1.00, t = 5.12 s / 185.15 tokens per second 7.10.868.357 I slot print_timing: id 1 | task 4771 | prompt processing, n_tokens = 774, progress = 0.82, t = 5.24 s / 147.84 tokens per second 7.12.006.567 I slot print_timing: id 2 | task 4767 | prompt eval time = 6542.01 ms / 906 tokens ( 7.22 ms per token, 138.49 tokens per second) 7.12.006.570 I slot print_timing: id 2 | task 4767 | eval time = 1138.44 ms / 2 tokens ( 1138.44 ms per token, 0.88 tokens per second) 7.12.006.571 I slot print_timing: id 2 | task 4767 | total time = 7680.45 ms / 908 tokens 7.12.006.571 I slot print_timing: id 2 | task 4767 | graphs reused = 3659 7.12.006.572 I slot print_timing: id 2 | task 4767 | graph reallocs = 0 / 0 (same size) / (changed size) 7.12.006.616 I slot release: id 2 | task 4767 | stop processing: n_tokens = 907, truncated = 0 7.12.006.846 I slot print_timing: id 3 | task 4768 | prompt eval time = 6542.15 ms / 952 tokens ( 6.87 ms per token, 145.52 tokens per second) 7.12.006.850 I slot print_timing: id 3 | task 4768 | eval time = 1138.51 ms / 2 tokens ( 1138.51 ms per token, 0.88 tokens per second) 7.12.006.850 I slot print_timing: id 3 | task 4768 | total time = 7680.66 ms / 954 tokens 7.12.006.850 I slot print_timing: id 3 | task 4768 | graphs reused = 3659 7.12.006.851 I slot print_timing: id 3 | task 4768 | graph reallocs = 0 / 0 (same size) / (changed size) 7.12.006.876 I slot release: id 3 | task 4768 | stop processing: n_tokens = 953, truncated = 0 7.12.006.885 I slot print_timing: id 0 | task 4774 | prompt processing, n_tokens = 840, progress = 0.62, t = 3.79 s / 221.71 tokens per second 7.12.010.021 I slot print_timing: id 1 | task 4771 | prompt processing, n_tokens = 936, progress = 1.00, t = 6.37 s / 146.85 tokens per second 7.12.650.827 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 907, t_last = 390265596746 7.12.650.884 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 330.218 MiB) 7.12.670.505 I slot launch_slot_: id 2 | task 4779 | processing task, is_child = 0 7.12.670.558 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 332.917 MiB) 7.12.678.368 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 953, t_last = 390265597006 7.12.678.452 I slot launch_slot_: id 3 | task 4780 | processing task, is_child = 0 7.12.678.461 I slot print_timing: id 0 | task 4774 | prompt processing, n_tokens = 1152, progress = 0.85, t = 4.43 s / 259.87 tokens per second 7.13.752.808 I slot print_timing: id 1 | task 4771 | prompt eval time = 7018.13 ms / 940 tokens ( 7.47 ms per token, 133.94 tokens per second) 7.13.752.811 I slot print_timing: id 1 | task 4771 | eval time = 1101.98 ms / 2 tokens ( 1101.98 ms per token, 0.91 tokens per second) 7.13.752.812 I slot print_timing: id 1 | task 4771 | total time = 8120.11 ms / 942 tokens 7.13.752.812 I slot print_timing: id 1 | task 4771 | graphs reused = 3659 7.13.752.813 I slot print_timing: id 1 | task 4771 | graph reallocs = 0 / 0 (same size) / (changed size) 7.13.752.859 I slot release: id 1 | task 4771 | stop processing: n_tokens = 941, truncated = 0 7.13.752.870 I slot print_timing: id 0 | task 4774 | prompt processing, n_tokens = 1352, progress = 1.00, t = 5.54 s / 244.26 tokens per second 7.14.610.782 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 941, t_last = 390267342989 7.14.610.852 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.606 MiB) 7.14.630.989 I slot launch_slot_: id 1 | task 4783 | processing task, is_child = 0 7.16.375.674 I slot print_timing: id 0 | task 4774 | prompt eval time = 6393.18 ms / 1356 tokens ( 4.71 ms per token, 212.10 tokens per second) 7.16.375.677 I slot print_timing: id 0 | task 4774 | eval time = 1764.89 ms / 2 tokens ( 1764.89 ms per token, 0.57 tokens per second) 7.16.375.677 I slot print_timing: id 0 | task 4774 | total time = 8158.07 ms / 1358 tokens 7.16.375.678 I slot print_timing: id 0 | task 4774 | graphs reused = 3659 7.16.375.678 I slot print_timing: id 0 | task 4774 | graph reallocs = 0 / 0 (same size) / (changed size) 7.16.375.729 I slot release: id 0 | task 4774 | stop processing: n_tokens = 1357, truncated = 0 7.16.379.319 I slot print_timing: id 2 | task 4779 | prompt processing, n_tokens = 743, progress = 0.59, t = 3.70 s / 201.07 tokens per second 7.16.381.248 I slot print_timing: id 3 | task 4780 | prompt processing, n_tokens = 826, progress = 0.62, t = 3.70 s / 223.54 tokens per second 7.18.075.732 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1357, t_last = 390269965859 7.18.075.807 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.294 MiB) 7.18.340.812 I slot launch_slot_: id 0 | task 4786 | processing task, is_child = 0 7.18.340.933 I slot print_timing: id 1 | task 4783 | prompt processing, n_tokens = 431, progress = 0.33, t = 3.44 s / 125.12 tokens per second 7.18.340.945 I slot print_timing: id 2 | task 4779 | prompt processing, n_tokens = 1152, progress = 0.92, t = 5.40 s / 213.52 tokens per second 7.18.342.840 I slot print_timing: id 3 | task 4780 | prompt processing, n_tokens = 1152, progress = 0.86, t = 5.40 s / 213.52 tokens per second 7.20.008.385 I slot print_timing: id 1 | task 4783 | prompt processing, n_tokens = 784, progress = 0.60, t = 5.12 s / 153.20 tokens per second 7.20.010.617 I slot print_timing: id 2 | task 4779 | prompt processing, n_tokens = 1255, progress = 1.00, t = 7.07 s / 177.56 tokens per second 7.20.012.614 I slot print_timing: id 3 | task 4780 | prompt processing, n_tokens = 1338, progress = 1.00, t = 7.07 s / 189.30 tokens per second 7.21.142.721 I slot print_timing: id 1 | task 4783 | prompt processing, n_tokens = 1152, progress = 0.89, t = 6.51 s / 177.01 tokens per second 7.22.239.009 I slot print_timing: id 2 | task 4779 | prompt eval time = 8458.87 ms / 1259 tokens ( 6.72 ms per token, 148.84 tokens per second) 7.22.239.011 I slot print_timing: id 2 | task 4779 | eval time = 1099.79 ms / 2 tokens ( 1099.79 ms per token, 0.91 tokens per second) 7.22.239.012 I slot print_timing: id 2 | task 4779 | total time = 9558.66 ms / 1261 tokens 7.22.239.012 I slot print_timing: id 2 | task 4779 | graphs reused = 3659 7.22.239.013 I slot print_timing: id 2 | task 4779 | graph reallocs = 0 / 0 (same size) / (changed size) 7.22.239.070 I slot release: id 2 | task 4779 | stop processing: n_tokens = 1260, truncated = 0 7.22.239.304 I slot print_timing: id 3 | task 4780 | prompt eval time = 8459.02 ms / 1342 tokens ( 6.30 ms per token, 158.65 tokens per second) 7.22.239.308 I slot print_timing: id 3 | task 4780 | eval time = 1099.87 ms / 2 tokens ( 1099.87 ms per token, 0.91 tokens per second) 7.22.239.308 I slot print_timing: id 3 | task 4780 | total time = 9558.89 ms / 1344 tokens 7.22.239.309 I slot print_timing: id 3 | task 4780 | graphs reused = 3659 7.22.239.309 I slot print_timing: id 3 | task 4780 | graph reallocs = 0 / 0 (same size) / (changed size) 7.22.239.352 I slot release: id 3 | task 4780 | stop processing: n_tokens = 1343, truncated = 0 7.22.239.361 I slot print_timing: id 0 | task 4786 | prompt processing, n_tokens = 681, progress = 0.86, t = 3.90 s / 174.70 tokens per second 7.22.243.153 I slot print_timing: id 1 | task 4783 | prompt processing, n_tokens = 1296, progress = 1.00, t = 7.61 s / 170.35 tokens per second 7.22.607.383 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1260, t_last = 390275829200 7.22.607.451 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 333.386 MiB) 7.22.628.397 I slot launch_slot_: id 2 | task 4791 | processing task, is_child = 0 7.22.628.466 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 334.070 MiB) 7.22.644.914 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1343, t_last = 390275829482 7.22.645.012 I slot launch_slot_: id 3 | task 4792 | processing task, is_child = 0 7.22.645.020 I slot print_timing: id 0 | task 4786 | prompt processing, n_tokens = 788, progress = 0.99, t = 4.27 s / 184.70 tokens per second 7.23.322.501 I slot print_timing: id 1 | task 4783 | prompt eval time = 7976.38 ms / 1300 tokens ( 6.14 ms per token, 162.98 tokens per second) 7.23.322.506 I slot print_timing: id 1 | task 4783 | eval time = 715.12 ms / 2 tokens ( 715.12 ms per token, 1.40 tokens per second) 7.23.322.507 I slot print_timing: id 1 | task 4783 | total time = 8691.50 ms / 1302 tokens 7.23.322.507 I slot print_timing: id 1 | task 4783 | graphs reused = 3659 7.23.322.508 I slot print_timing: id 1 | task 4783 | graph reallocs = 0 / 0 (same size) / (changed size) 7.23.322.563 I slot release: id 1 | task 4783 | stop processing: n_tokens = 1301, truncated = 0 7.23.948.381 I slot print_timing: id 0 | task 4786 | prompt eval time = 4981.48 ms / 792 tokens ( 6.29 ms per token, 158.99 tokens per second) 7.23.948.384 I slot print_timing: id 0 | task 4786 | eval time = 626.07 ms / 2 tokens ( 626.07 ms per token, 1.60 tokens per second) 7.23.948.384 I slot print_timing: id 0 | task 4786 | total time = 5607.55 ms / 794 tokens 7.23.948.385 I slot print_timing: id 0 | task 4786 | graphs reused = 3659 7.23.948.385 I slot print_timing: id 0 | task 4786 | graph reallocs = 0 / 0 (same size) / (changed size) 7.23.948.425 I slot release: id 0 | task 4786 | stop processing: n_tokens = 793, truncated = 0 7.23.948.433 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1301, t_last = 390276912693 7.23.948.502 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 332.154 MiB) 7.23.972.695 I slot launch_slot_: id 1 | task 4795 | processing task, is_child = 0 7.23.972.756 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 348.892 MiB) 7.23.980.491 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 793, t_last = 390277538555 7.23.980.567 I slot launch_slot_: id 0 | task 4796 | processing task, is_child = 0 7.26.950.784 I slot print_timing: id 2 | task 4791 | prompt processing, n_tokens = 741, progress = 0.83, t = 4.15 s / 178.62 tokens per second 7.26.954.719 I slot print_timing: id 3 | task 4792 | prompt processing, n_tokens = 681, progress = 0.84, t = 4.15 s / 164.17 tokens per second 7.28.350.591 I slot print_timing: id 0 | task 4796 | prompt processing, n_tokens = 655, progress = 0.83, t = 4.37 s / 149.89 tokens per second 7.28.506.375 I slot print_timing: id 1 | task 4795 | prompt processing, n_tokens = 343, progress = 0.40, t = 4.37 s / 78.49 tokens per second 7.28.509.708 I slot print_timing: id 2 | task 4791 | prompt processing, n_tokens = 887, progress = 1.00, t = 5.70 s / 155.52 tokens per second 7.28.511.678 I slot print_timing: id 3 | task 4792 | prompt processing, n_tokens = 804, progress = 1.00, t = 5.70 s / 140.97 tokens per second 7.29.638.538 I slot print_timing: id 0 | task 4796 | prompt processing, n_tokens = 786, progress = 0.99, t = 5.66 s / 138.93 tokens per second 7.29.642.492 I slot print_timing: id 1 | task 4795 | prompt processing, n_tokens = 741, progress = 0.86, t = 5.66 s / 130.98 tokens per second 7.30.037.247 I slot print_timing: id 2 | task 4791 | prompt eval time = 6991.00 ms / 891 tokens ( 7.85 ms per token, 127.45 tokens per second) 7.30.037.250 I slot print_timing: id 2 | task 4791 | eval time = 398.98 ms / 2 tokens ( 398.98 ms per token, 2.51 tokens per second) 7.30.037.250 I slot print_timing: id 2 | task 4791 | total time = 7389.98 ms / 893 tokens 7.30.037.251 I slot print_timing: id 2 | task 4791 | graphs reused = 3659 7.30.037.251 I slot print_timing: id 2 | task 4791 | graph reallocs = 0 / 0 (same size) / (changed size) 7.30.037.293 I slot release: id 2 | task 4791 | stop processing: n_tokens = 892, truncated = 0 7.30.037.448 I slot print_timing: id 3 | task 4792 | prompt eval time = 6991.14 ms / 808 tokens ( 8.65 ms per token, 115.57 tokens per second) 7.30.037.453 I slot print_timing: id 3 | task 4792 | eval time = 398.93 ms / 2 tokens ( 398.93 ms per token, 2.51 tokens per second) 7.30.037.454 I slot print_timing: id 3 | task 4792 | total time = 7390.07 ms / 810 tokens 7.30.037.454 I slot print_timing: id 3 | task 4792 | graphs reused = 3659 7.30.037.454 I slot print_timing: id 3 | task 4792 | graph reallocs = 0 / 0 (same size) / (changed size) 7.30.037.482 I slot release: id 3 | task 4792 | stop processing: n_tokens = 809, truncated = 0 7.30.037.491 I slot print_timing: id 1 | task 4795 | prompt processing, n_tokens = 855, progress = 1.00, t = 6.06 s / 141.18 tokens per second 7.30.110.758 I slot print_timing: id 0 | task 4796 | prompt eval time = 6056.52 ms / 790 tokens ( 7.67 ms per token, 130.44 tokens per second) 7.30.110.760 I slot print_timing: id 0 | task 4796 | eval time = 73.66 ms / 2 tokens ( 73.66 ms per token, 13.58 tokens per second) 7.30.110.761 I slot print_timing: id 0 | task 4796 | total time = 6130.18 ms / 792 tokens 7.30.110.761 I slot print_timing: id 0 | task 4796 | graphs reused = 3659 7.30.110.762 I slot print_timing: id 0 | task 4796 | graph reallocs = 0 / 0 (same size) / (changed size) 7.30.110.793 I slot release: id 0 | task 4796 | stop processing: n_tokens = 791, truncated = 0 7.30.110.974 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.799 (> 0.100 thold), f_keep = 0.863 7.30.111.021 I slot launch_slot_: id 0 | task 4803 | processing task, is_child = 0 7.30.111.078 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 332.408 MiB) 7.30.119.479 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.028 MiB) 7.30.127.087 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 892, t_last = 390283627423 7.30.127.167 I slot launch_slot_: id 2 | task 4804 | processing task, is_child = 0 7.30.127.204 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 809, t_last = 390283627612 7.30.127.264 I slot launch_slot_: id 3 | task 4805 | processing task, is_child = 0 7.31.164.553 I slot print_timing: id 1 | task 4795 | prompt eval time = 6130.32 ms / 859 tokens ( 7.14 ms per token, 140.12 tokens per second) 7.31.164.555 I slot print_timing: id 1 | task 4795 | eval time = 1053.58 ms / 2 tokens ( 1053.58 ms per token, 0.95 tokens per second) 7.31.164.559 I slot print_timing: id 1 | task 4795 | total time = 7183.89 ms / 861 tokens 7.31.164.560 I slot print_timing: id 1 | task 4795 | graphs reused = 3659 7.31.164.560 I slot print_timing: id 1 | task 4795 | graph reallocs = 0 / 0 (same size) / (changed size) 7.31.164.598 I slot release: id 1 | task 4795 | stop processing: n_tokens = 860, truncated = 0 7.31.629.766 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 860, t_last = 390284754729 7.31.629.824 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.294 MiB) 7.31.639.890 I slot launch_slot_: id 1 | task 4808 | processing task, is_child = 0 7.33.288.417 I slot print_timing: id 0 | task 4803 | prompt eval time = 1502.49 ms / 200 tokens ( 7.51 ms per token, 133.11 tokens per second) 7.33.288.420 I slot print_timing: id 0 | task 4803 | eval time = 1658.65 ms / 2 tokens ( 1658.65 ms per token, 0.60 tokens per second) 7.33.288.421 I slot print_timing: id 0 | task 4803 | total time = 3161.14 ms / 202 tokens 7.33.288.421 I slot print_timing: id 0 | task 4803 | graphs reused = 3659 7.33.288.422 I slot print_timing: id 0 | task 4803 | graph reallocs = 0 / 0 (same size) / (changed size) 7.33.288.461 I slot release: id 0 | task 4803 | stop processing: n_tokens = 856, truncated = 0 7.33.290.706 I slot print_timing: id 2 | task 4804 | prompt processing, n_tokens = 655, progress = 0.84, t = 3.16 s / 207.43 tokens per second 7.33.292.923 I slot print_timing: id 3 | task 4805 | prompt processing, n_tokens = 655, progress = 0.85, t = 3.16 s / 207.43 tokens per second 7.33.976.668 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 856, t_last = 390286878591 7.33.976.726 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.087 MiB) 7.34.016.375 I slot launch_slot_: id 0 | task 4811 | processing task, is_child = 0 7.34.018.398 I slot print_timing: id 2 | task 4804 | prompt processing, n_tokens = 774, progress = 0.99, t = 3.85 s / 201.24 tokens per second 7.34.020.490 I slot print_timing: id 3 | task 4805 | prompt processing, n_tokens = 770, progress = 0.99, t = 3.85 s / 200.20 tokens per second 7.35.188.889 I slot print_timing: id 1 | task 4808 | prompt processing, n_tokens = 655, progress = 0.82, t = 3.54 s / 184.77 tokens per second 7.35.820.602 I slot print_timing: id 2 | task 4804 | prompt eval time = 5054.53 ms / 778 tokens ( 6.50 ms per token, 153.92 tokens per second) 7.35.820.604 I slot print_timing: id 2 | task 4804 | eval time = 635.57 ms / 2 tokens ( 635.57 ms per token, 1.57 tokens per second) 7.35.820.605 I slot print_timing: id 2 | task 4804 | total time = 5690.10 ms / 780 tokens 7.35.820.605 I slot print_timing: id 2 | task 4804 | graphs reused = 3659 7.35.820.606 I slot print_timing: id 2 | task 4804 | graph reallocs = 0 / 0 (same size) / (changed size) 7.35.820.643 I slot release: id 2 | task 4804 | stop processing: n_tokens = 779, truncated = 0 7.35.820.953 I slot print_timing: id 3 | task 4805 | prompt eval time = 5054.84 ms / 774 tokens ( 6.53 ms per token, 153.12 tokens per second) 7.35.820.955 I slot print_timing: id 3 | task 4805 | eval time = 635.52 ms / 2 tokens ( 635.52 ms per token, 1.57 tokens per second) 7.35.820.956 I slot print_timing: id 3 | task 4805 | total time = 5690.37 ms / 776 tokens 7.35.820.956 I slot print_timing: id 3 | task 4805 | graphs reused = 3659 7.35.820.957 I slot print_timing: id 3 | task 4805 | graph reallocs = 0 / 0 (same size) / (changed size) 7.35.820.983 I slot release: id 3 | task 4805 | stop processing: n_tokens = 775, truncated = 0 7.35.820.999 I slot print_timing: id 1 | task 4808 | prompt processing, n_tokens = 798, progress = 1.00, t = 4.18 s / 190.88 tokens per second 7.36.194.744 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 779, t_last = 390289410773 7.36.194.798 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.145 MiB) 7.36.207.559 I slot launch_slot_: id 2 | task 4815 | processing task, is_child = 0 7.36.207.607 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.263 MiB) 7.36.215.438 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 775, t_last = 390289411113 7.36.215.510 I slot launch_slot_: id 3 | task 4816 | processing task, is_child = 0 7.37.530.340 I slot print_timing: id 1 | task 4808 | prompt eval time = 4554.84 ms / 802 tokens ( 5.68 ms per token, 176.08 tokens per second) 7.37.530.343 I slot print_timing: id 1 | task 4808 | eval time = 1335.59 ms / 2 tokens ( 1335.59 ms per token, 0.75 tokens per second) 7.37.530.344 I slot print_timing: id 1 | task 4808 | total time = 5890.43 ms / 804 tokens 7.37.530.344 I slot print_timing: id 1 | task 4808 | graphs reused = 3659 7.37.530.345 I slot print_timing: id 1 | task 4808 | graph reallocs = 0 / 0 (same size) / (changed size) 7.37.530.382 I slot release: id 1 | task 4808 | stop processing: n_tokens = 803, truncated = 0 7.37.530.394 I slot print_timing: id 0 | task 4811 | prompt processing, n_tokens = 836, progress = 0.86, t = 3.51 s / 237.92 tokens per second 7.37.876.724 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 803, t_last = 390291120512 7.37.876.780 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.215 MiB) 7.38.406.515 I slot launch_slot_: id 1 | task 4819 | processing task, is_child = 0 7.38.406.533 I slot print_timing: id 0 | task 4811 | prompt processing, n_tokens = 967, progress = 1.00, t = 3.86 s / 250.50 tokens per second 7.39.456.259 I slot print_timing: id 2 | task 4815 | prompt processing, n_tokens = 448, progress = 0.46, t = 3.23 s / 138.54 tokens per second 7.39.459.391 I slot print_timing: id 3 | task 4816 | prompt processing, n_tokens = 428, progress = 0.45, t = 3.23 s / 132.36 tokens per second 7.41.163.863 I slot print_timing: id 0 | task 4811 | prompt eval time = 5436.63 ms / 971 tokens ( 5.60 ms per token, 178.60 tokens per second) 7.41.163.865 I slot print_timing: id 0 | task 4811 | eval time = 1710.84 ms / 2 tokens ( 1710.84 ms per token, 0.58 tokens per second) 7.41.163.866 I slot print_timing: id 0 | task 4811 | total time = 7147.47 ms / 973 tokens 7.41.163.866 I slot print_timing: id 0 | task 4811 | graphs reused = 3659 7.41.163.867 I slot print_timing: id 0 | task 4811 | graph reallocs = 0 / 0 (same size) / (changed size) 7.41.163.908 I slot release: id 0 | task 4811 | stop processing: n_tokens = 972, truncated = 0 7.41.163.930 I slot print_timing: id 2 | task 4815 | prompt processing, n_tokens = 836, progress = 0.87, t = 4.94 s / 169.07 tokens per second 7.41.167.617 I slot print_timing: id 3 | task 4816 | prompt processing, n_tokens = 836, progress = 0.89, t = 4.94 s / 169.07 tokens per second 7.41.822.483 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 7.41.822.559 I slot launch_slot_: id 0 | task 4823 | processing task, is_child = 0 7.41.966.340 I slot print_timing: id 1 | task 4819 | prompt processing, n_tokens = 431, progress = 0.46, t = 3.41 s / 126.25 tokens per second 7.41.968.233 I slot print_timing: id 2 | task 4815 | prompt processing, n_tokens = 960, progress = 1.00, t = 5.60 s / 171.32 tokens per second 7.41.970.192 I slot print_timing: id 3 | task 4816 | prompt processing, n_tokens = 940, progress = 1.00, t = 5.60 s / 167.76 tokens per second 7.43.112.859 I slot print_timing: id 1 | task 4819 | prompt processing, n_tokens = 836, progress = 0.88, t = 4.70 s / 177.87 tokens per second 7.43.513.332 I slot print_timing: id 2 | task 4815 | prompt eval time = 6889.90 ms / 964 tokens ( 7.15 ms per token, 139.91 tokens per second) 7.43.513.334 I slot print_timing: id 2 | task 4815 | eval time = 404.39 ms / 2 tokens ( 404.39 ms per token, 2.47 tokens per second) 7.43.513.335 I slot print_timing: id 2 | task 4815 | total time = 7294.29 ms / 966 tokens 7.43.513.335 I slot print_timing: id 2 | task 4815 | graphs reused = 3659 7.43.513.336 I slot print_timing: id 2 | task 4815 | graph reallocs = 0 / 0 (same size) / (changed size) 7.43.513.380 I slot release: id 2 | task 4815 | stop processing: n_tokens = 965, truncated = 0 7.43.513.609 I slot print_timing: id 3 | task 4816 | prompt eval time = 6890.07 ms / 944 tokens ( 7.30 ms per token, 137.01 tokens per second) 7.43.513.616 I slot print_timing: id 3 | task 4816 | eval time = 404.44 ms / 2 tokens ( 404.44 ms per token, 2.47 tokens per second) 7.43.513.617 I slot print_timing: id 3 | task 4816 | total time = 7294.51 ms / 946 tokens 7.43.513.617 I slot print_timing: id 3 | task 4816 | graphs reused = 3659 7.43.513.617 I slot print_timing: id 3 | task 4816 | graph reallocs = 0 / 0 (same size) / (changed size) 7.43.513.646 I slot release: id 3 | task 4816 | stop processing: n_tokens = 945, truncated = 0 7.43.513.654 I slot print_timing: id 1 | task 4819 | prompt processing, n_tokens = 943, progress = 1.00, t = 5.10 s / 184.74 tokens per second 7.43.587.890 I slot print_timing: id 0 | task 4823 | prompt eval time = 1690.61 ms / 133 tokens ( 12.71 ms per token, 78.67 tokens per second) 7.43.587.893 I slot print_timing: id 0 | task 4823 | eval time = 74.71 ms / 2 tokens ( 74.71 ms per token, 13.38 tokens per second) 7.43.587.893 I slot print_timing: id 0 | task 4823 | total time = 1765.32 ms / 135 tokens 7.43.587.893 I slot print_timing: id 0 | task 4823 | graphs reused = 3659 7.43.587.894 I slot print_timing: id 0 | task 4823 | graph reallocs = 0 / 0 (same size) / (changed size) 7.43.587.929 I slot release: id 0 | task 4823 | stop processing: n_tokens = 970, truncated = 0 7.43.588.259 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 965, t_last = 390297103510 7.43.588.324 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 333.757 MiB) 7.43.596.202 I slot launch_slot_: id 2 | task 4827 | processing task, is_child = 0 7.43.596.257 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 334.305 MiB) 7.43.604.085 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 333.503 MiB) 7.43.612.401 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 945, t_last = 390297103776 7.43.612.499 I slot launch_slot_: id 3 | task 4828 | processing task, is_child = 0 7.43.612.548 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 970, t_last = 390297178059 7.43.612.618 I slot launch_slot_: id 0 | task 4829 | processing task, is_child = 0 7.44.553.901 I slot print_timing: id 1 | task 4819 | prompt eval time = 5179.64 ms / 947 tokens ( 5.47 ms per token, 182.83 tokens per second) 7.44.553.903 I slot print_timing: id 1 | task 4819 | eval time = 965.64 ms / 2 tokens ( 965.64 ms per token, 1.04 tokens per second) 7.44.553.903 I slot print_timing: id 1 | task 4819 | total time = 6145.28 ms / 949 tokens 7.44.553.904 I slot print_timing: id 1 | task 4819 | graphs reused = 3659 7.44.553.904 I slot print_timing: id 1 | task 4819 | graph reallocs = 0 / 0 (same size) / (changed size) 7.44.553.942 I slot release: id 1 | task 4819 | stop processing: n_tokens = 948, truncated = 0 7.45.437.618 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 948, t_last = 390298144072 7.45.437.684 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 333.620 MiB) 7.45.456.679 I slot launch_slot_: id 1 | task 4832 | processing task, is_child = 0 7.47.318.649 I slot print_timing: id 0 | task 4829 | prompt processing, n_tokens = 459, progress = 0.47, t = 3.71 s / 123.85 tokens per second 7.47.339.426 I slot print_timing: id 2 | task 4827 | prompt processing, n_tokens = 679, progress = 0.85, t = 3.71 s / 183.22 tokens per second 7.47.341.556 I slot print_timing: id 3 | task 4828 | prompt processing, n_tokens = 679, progress = 0.85, t = 3.71 s / 183.22 tokens per second 7.48.554.907 I slot print_timing: id 0 | task 4829 | prompt processing, n_tokens = 826, progress = 0.85, t = 4.94 s / 167.13 tokens per second 7.48.942.103 I slot print_timing: id 1 | task 4832 | prompt processing, n_tokens = 335, progress = 0.35, t = 3.10 s / 108.13 tokens per second 7.48.942.114 I slot print_timing: id 2 | task 4827 | prompt processing, n_tokens = 795, progress = 0.99, t = 4.94 s / 160.86 tokens per second 7.48.944.339 I slot print_timing: id 3 | task 4828 | prompt processing, n_tokens = 794, progress = 0.99, t = 4.94 s / 160.66 tokens per second 7.49.684.605 I slot print_timing: id 0 | task 4829 | prompt processing, n_tokens = 971, progress = 1.00, t = 6.07 s / 159.93 tokens per second 7.49.687.992 I slot print_timing: id 1 | task 4832 | prompt processing, n_tokens = 437, progress = 0.46, t = 4.23 s / 103.37 tokens per second 7.50.470.745 I slot print_timing: id 2 | task 4827 | prompt eval time = 6071.71 ms / 799 tokens ( 7.60 ms per token, 131.59 tokens per second) 7.50.470.748 I slot print_timing: id 2 | task 4827 | eval time = 786.34 ms / 2 tokens ( 786.34 ms per token, 1.27 tokens per second) 7.50.470.748 I slot print_timing: id 2 | task 4827 | total time = 6858.05 ms / 801 tokens 7.50.470.749 I slot print_timing: id 2 | task 4827 | graphs reused = 3659 7.50.470.749 I slot print_timing: id 2 | task 4827 | graph reallocs = 0 / 0 (same size) / (changed size) 7.50.470.789 I slot release: id 2 | task 4827 | stop processing: n_tokens = 800, truncated = 0 7.50.470.947 I slot print_timing: id 3 | task 4828 | prompt eval time = 6071.84 ms / 798 tokens ( 7.61 ms per token, 131.43 tokens per second) 7.50.470.950 I slot print_timing: id 3 | task 4828 | eval time = 786.35 ms / 2 tokens ( 786.35 ms per token, 1.27 tokens per second) 7.50.470.951 I slot print_timing: id 3 | task 4828 | total time = 6858.19 ms / 800 tokens 7.50.470.951 I slot print_timing: id 3 | task 4828 | graphs reused = 3659 7.50.470.951 I slot print_timing: id 3 | task 4828 | graph reallocs = 0 / 0 (same size) / (changed size) 7.50.470.974 I slot release: id 3 | task 4828 | stop processing: n_tokens = 799, truncated = 0 7.50.470.981 I slot print_timing: id 1 | task 4832 | prompt processing, n_tokens = 826, progress = 0.87, t = 5.01 s / 164.75 tokens per second 7.50.821.430 I slot print_timing: id 0 | task 4829 | prompt eval time = 6857.98 ms / 975 tokens ( 7.03 ms per token, 142.17 tokens per second) 7.50.821.435 I slot print_timing: id 0 | task 4829 | eval time = 350.82 ms / 2 tokens ( 350.82 ms per token, 2.85 tokens per second) 7.50.821.436 I slot print_timing: id 0 | task 4829 | total time = 7208.80 ms / 977 tokens 7.50.821.436 I slot print_timing: id 0 | task 4829 | graphs reused = 3659 7.50.821.436 I slot print_timing: id 0 | task 4829 | graph reallocs = 0 / 0 (same size) / (changed size) 7.50.821.479 I slot release: id 0 | task 4829 | stop processing: n_tokens = 976, truncated = 0 7.50.821.487 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 7.50.821.529 I slot launch_slot_: id 0 | task 4838 | processing task, is_child = 0 7.50.821.587 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.274 MiB) 7.50.831.274 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 333.347 MiB) 7.50.838.838 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 800, t_last = 390304060919 7.50.838.954 I slot launch_slot_: id 2 | task 4839 | processing task, is_child = 0 7.50.838.999 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 799, t_last = 390304061104 7.50.839.064 I slot launch_slot_: id 3 | task 4840 | processing task, is_child = 0 7.50.842.291 I slot print_timing: id 1 | task 4832 | prompt processing, n_tokens = 949, progress = 1.00, t = 5.36 s / 176.90 tokens per second 7.52.433.483 I slot print_timing: id 1 | task 4832 | prompt eval time = 6313.05 ms / 953 tokens ( 6.62 ms per token, 150.96 tokens per second) 7.52.433.485 I slot print_timing: id 1 | task 4832 | eval time = 663.74 ms / 2 tokens ( 663.74 ms per token, 1.51 tokens per second) 7.52.433.485 I slot print_timing: id 1 | task 4832 | total time = 6976.78 ms / 955 tokens 7.52.433.486 I slot print_timing: id 1 | task 4832 | graphs reused = 3659 7.52.433.486 I slot print_timing: id 1 | task 4832 | graph reallocs = 0 / 0 (same size) / (changed size) 7.52.433.524 I slot release: id 1 | task 4832 | stop processing: n_tokens = 954, truncated = 0 7.52.912.180 I slot print_timing: id 0 | task 4838 | prompt eval time = 1594.26 ms / 135 tokens ( 11.81 ms per token, 84.68 tokens per second) 7.52.912.183 I slot print_timing: id 0 | task 4838 | eval time = 478.85 ms / 2 tokens ( 478.85 ms per token, 2.09 tokens per second) 7.52.912.184 I slot print_timing: id 0 | task 4838 | total time = 2073.11 ms / 137 tokens 7.52.912.184 I slot print_timing: id 0 | task 4838 | graphs reused = 3659 7.52.912.185 I slot print_timing: id 0 | task 4838 | graph reallocs = 0 / 0 (same size) / (changed size) 7.52.912.231 I slot release: id 0 | task 4838 | stop processing: n_tokens = 962, truncated = 0 7.52.912.239 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 954, t_last = 390306023654 7.52.912.297 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 333.816 MiB) 7.52.921.242 I slot launch_slot_: id 1 | task 4844 | processing task, is_child = 0 7.52.921.294 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.313 MiB) 7.52.929.363 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 962, t_last = 390306502361 7.52.929.452 I slot launch_slot_: id 0 | task 4845 | processing task, is_child = 0 7.54.843.688 I slot print_timing: id 2 | task 4839 | prompt processing, n_tokens = 779, progress = 0.84, t = 3.85 s / 202.13 tokens per second 7.54.845.565 I slot print_timing: id 3 | task 4840 | prompt processing, n_tokens = 779, progress = 0.87, t = 3.85 s / 202.13 tokens per second 7.55.870.540 I slot print_timing: id 2 | task 4839 | prompt processing, n_tokens = 926, progress = 1.00, t = 5.03 s / 184.23 tokens per second 7.56.013.955 I slot print_timing: id 3 | task 4840 | prompt processing, n_tokens = 894, progress = 1.00, t = 5.03 s / 177.87 tokens per second 7.56.496.051 I slot print_timing: id 0 | task 4845 | prompt processing, n_tokens = 383, progress = 0.43, t = 3.57 s / 107.40 tokens per second 7.56.498.491 I slot print_timing: id 1 | task 4844 | prompt processing, n_tokens = 386, progress = 0.43, t = 3.57 s / 108.24 tokens per second 7.57.886.640 I slot print_timing: id 2 | task 4839 | prompt eval time = 5651.64 ms / 930 tokens ( 6.08 ms per token, 164.55 tokens per second) 7.57.886.647 I slot print_timing: id 2 | task 4839 | eval time = 1390.75 ms / 2 tokens ( 1390.75 ms per token, 0.72 tokens per second) 7.57.886.648 I slot print_timing: id 2 | task 4839 | total time = 7042.40 ms / 932 tokens 7.57.886.648 I slot print_timing: id 2 | task 4839 | graphs reused = 3659 7.57.886.649 I slot print_timing: id 2 | task 4839 | graph reallocs = 0 / 0 (same size) / (changed size) 7.57.886.696 I slot release: id 2 | task 4839 | stop processing: n_tokens = 931, truncated = 0 7.57.886.861 I slot print_timing: id 3 | task 4840 | prompt eval time = 5651.74 ms / 898 tokens ( 6.29 ms per token, 158.89 tokens per second) 7.57.886.864 I slot print_timing: id 3 | task 4840 | eval time = 1390.82 ms / 2 tokens ( 1390.82 ms per token, 0.72 tokens per second) 7.57.886.864 I slot print_timing: id 3 | task 4840 | total time = 7042.56 ms / 900 tokens 7.57.886.865 I slot print_timing: id 3 | task 4840 | graphs reused = 3659 7.57.886.865 I slot print_timing: id 3 | task 4840 | graph reallocs = 0 / 0 (same size) / (changed size) 7.57.886.897 I slot release: id 3 | task 4840 | stop processing: n_tokens = 899, truncated = 0 7.57.886.906 I slot print_timing: id 0 | task 4845 | prompt processing, n_tokens = 779, progress = 0.87, t = 4.96 s / 157.15 tokens per second 7.57.889.762 I slot print_timing: id 1 | task 4844 | prompt processing, n_tokens = 779, progress = 0.86, t = 4.96 s / 157.15 tokens per second 7.58.373.331 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.867 7.58.373.375 I slot launch_slot_: id 2 | task 4851 | processing task, is_child = 0 7.58.373.433 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.724 MiB) 7.58.408.042 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 899, t_last = 390311477027 7.58.408.128 I slot launch_slot_: id 3 | task 4852 | processing task, is_child = 0 7.58.408.139 I slot print_timing: id 0 | task 4845 | prompt processing, n_tokens = 895, progress = 1.00, t = 5.44 s / 164.41 tokens per second 7.58.410.166 I slot print_timing: id 1 | task 4844 | prompt processing, n_tokens = 898, progress = 1.00, t = 5.44 s / 164.96 tokens per second 7.59.768.584 I slot print_timing: id 0 | task 4845 | prompt eval time = 6296.41 ms / 899 tokens ( 7.00 ms per token, 142.78 tokens per second) 7.59.768.590 I slot print_timing: id 0 | task 4845 | eval time = 542.71 ms / 2 tokens ( 542.71 ms per token, 1.84 tokens per second) 7.59.768.590 I slot print_timing: id 0 | task 4845 | total time = 6839.12 ms / 901 tokens 7.59.768.591 I slot print_timing: id 0 | task 4845 | graphs reused = 3659 7.59.768.591 I slot print_timing: id 0 | task 4845 | graph reallocs = 0 / 0 (same size) / (changed size) 7.59.768.633 I slot release: id 0 | task 4845 | stop processing: n_tokens = 900, truncated = 0 7.59.768.805 I slot print_timing: id 1 | task 4844 | prompt eval time = 6296.50 ms / 902 tokens ( 6.98 ms per token, 143.25 tokens per second) 7.59.768.808 I slot print_timing: id 1 | task 4844 | eval time = 542.76 ms / 2 tokens ( 542.76 ms per token, 1.84 tokens per second) 7.59.768.809 I slot print_timing: id 1 | task 4844 | total time = 6839.27 ms / 904 tokens 7.59.768.809 I slot print_timing: id 1 | task 4844 | graphs reused = 3659 7.59.768.809 I slot print_timing: id 1 | task 4844 | graph reallocs = 0 / 0 (same size) / (changed size) 7.59.768.834 I slot release: id 1 | task 4844 | stop processing: n_tokens = 903, truncated = 0 8.00.376.321 I slot print_timing: id 2 | task 4851 | prompt eval time = 1356.89 ms / 111 tokens ( 12.22 ms per token, 81.80 tokens per second) 8.00.376.323 I slot print_timing: id 2 | task 4851 | eval time = 607.21 ms / 2 tokens ( 607.21 ms per token, 1.65 tokens per second) 8.00.376.324 I slot print_timing: id 2 | task 4851 | total time = 1964.10 ms / 113 tokens 8.00.376.324 I slot print_timing: id 2 | task 4851 | graphs reused = 3659 8.00.376.325 I slot print_timing: id 2 | task 4851 | graph reallocs = 0 / 0 (same size) / (changed size) 8.00.376.379 I slot release: id 2 | task 4851 | stop processing: n_tokens = 891, truncated = 0 8.00.376.385 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 900, t_last = 390313358763 8.00.376.439 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.802 MiB) 8.00.392.112 I slot launch_slot_: id 0 | task 4856 | processing task, is_child = 0 8.00.392.165 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 332.701 MiB) 8.00.399.795 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 332.467 MiB) 8.00.407.482 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 903, t_last = 390313358964 8.00.407.577 I slot launch_slot_: id 1 | task 4857 | processing task, is_child = 0 8.00.407.625 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 891, t_last = 390313966509 8.00.407.695 I slot launch_slot_: id 2 | task 4858 | processing task, is_child = 0 8.02.533.447 I slot print_timing: id 3 | task 4852 | prompt processing, n_tokens = 1061, progress = 0.87, t = 3.93 s / 270.23 tokens per second 8.04.052.815 I slot print_timing: id 0 | task 4856 | prompt processing, n_tokens = 402, progress = 0.33, t = 3.65 s / 110.28 tokens per second 8.04.052.833 I slot print_timing: id 1 | task 4857 | prompt processing, n_tokens = 402, progress = 0.31, t = 3.65 s / 110.29 tokens per second 8.04.052.843 I slot print_timing: id 2 | task 4858 | prompt processing, n_tokens = 961, progress = 0.37, t = 3.64 s / 263.65 tokens per second 8.04.052.875 I slot print_timing: id 3 | task 4852 | prompt processing, n_tokens = 1221, progress = 1.00, t = 5.64 s / 216.59 tokens per second 8.07.999.724 I slot print_timing: id 0 | task 4856 | prompt processing, n_tokens = 720, progress = 0.58, t = 7.59 s / 94.84 tokens per second 8.08.003.101 I slot print_timing: id 1 | task 4857 | prompt processing, n_tokens = 774, progress = 0.60, t = 7.59 s / 101.95 tokens per second 8.08.005.976 I slot print_timing: id 2 | task 4858 | prompt processing, n_tokens = 2071, progress = 0.80, t = 7.59 s / 272.80 tokens per second 8.09.784.533 I slot print_timing: id 3 | task 4852 | prompt eval time = 9584.18 ms / 1225 tokens ( 7.82 ms per token, 127.81 tokens per second) 8.09.784.538 I slot print_timing: id 3 | task 4852 | eval time = 1784.81 ms / 2 tokens ( 1784.81 ms per token, 0.56 tokens per second) 8.09.784.539 I slot print_timing: id 3 | task 4852 | total time = 11368.99 ms / 1227 tokens 8.09.784.539 I slot print_timing: id 3 | task 4852 | graphs reused = 3659 8.09.784.540 I slot print_timing: id 3 | task 4852 | graph reallocs = 0 / 0 (same size) / (changed size) 8.09.784.595 I slot release: id 3 | task 4852 | stop processing: n_tokens = 1226, truncated = 0 8.09.784.608 I slot print_timing: id 0 | task 4856 | prompt processing, n_tokens = 1061, progress = 0.86, t = 9.38 s / 113.15 tokens per second 8.09.787.529 I slot print_timing: id 1 | task 4857 | prompt processing, n_tokens = 1061, progress = 0.82, t = 9.38 s / 113.15 tokens per second 8.09.789.444 I slot print_timing: id 2 | task 4858 | prompt processing, n_tokens = 2288, progress = 0.88, t = 9.38 s / 244.01 tokens per second 8.11.032.331 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1226, t_last = 390323374725 8.11.032.401 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 340.601 MiB) 8.11.276.015 I slot launch_slot_: id 3 | task 4864 | processing task, is_child = 0 8.11.276.027 I slot print_timing: id 0 | task 4856 | prompt processing, n_tokens = 1232, progress = 1.00, t = 10.62 s / 115.96 tokens per second 8.11.278.127 I slot print_timing: id 1 | task 4857 | prompt processing, n_tokens = 1286, progress = 1.00, t = 10.62 s / 121.04 tokens per second 8.11.280.088 I slot print_timing: id 2 | task 4858 | prompt processing, n_tokens = 2583, progress = 1.00, t = 10.62 s / 243.12 tokens per second 8.13.162.716 I slot print_timing: id 0 | task 4856 | prompt eval time = 11681.64 ms / 1236 tokens ( 9.45 ms per token, 105.81 tokens per second) 8.13.162.721 I slot print_timing: id 0 | task 4856 | eval time = 1073.36 ms / 2 tokens ( 1073.36 ms per token, 0.93 tokens per second) 8.13.162.722 I slot print_timing: id 0 | task 4856 | total time = 12755.01 ms / 1238 tokens 8.13.162.722 I slot print_timing: id 0 | task 4856 | graphs reused = 3659 8.13.162.723 I slot print_timing: id 0 | task 4856 | graph reallocs = 0 / 0 (same size) / (changed size) 8.13.162.771 I slot release: id 0 | task 4856 | stop processing: n_tokens = 1237, truncated = 0 8.13.162.927 I slot print_timing: id 1 | task 4857 | prompt eval time = 11681.76 ms / 1290 tokens ( 9.06 ms per token, 110.43 tokens per second) 8.13.162.929 I slot print_timing: id 1 | task 4857 | eval time = 1073.40 ms / 2 tokens ( 1073.40 ms per token, 0.93 tokens per second) 8.13.162.929 I slot print_timing: id 1 | task 4857 | total time = 12755.16 ms / 1292 tokens 8.13.162.930 I slot print_timing: id 1 | task 4857 | graphs reused = 3659 8.13.162.930 I slot print_timing: id 1 | task 4857 | graph reallocs = 0 / 0 (same size) / (changed size) 8.13.162.964 I slot release: id 1 | task 4857 | stop processing: n_tokens = 1291, truncated = 0 8.13.163.204 I slot print_timing: id 2 | task 4858 | prompt eval time = 11681.91 ms / 2587 tokens ( 4.52 ms per token, 221.45 tokens per second) 8.13.163.212 I slot print_timing: id 2 | task 4858 | eval time = 1073.46 ms / 2 tokens ( 1073.46 ms per token, 0.93 tokens per second) 8.13.163.212 I slot print_timing: id 2 | task 4858 | total time = 12755.37 ms / 2589 tokens 8.13.163.212 I slot print_timing: id 2 | task 4858 | graphs reused = 3659 8.13.163.213 I slot print_timing: id 2 | task 4858 | graph reallocs = 0 / 0 (same size) / (changed size) 8.13.163.310 I slot release: id 2 | task 4858 | stop processing: n_tokens = 2588, truncated = 0 8.14.010.620 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.848 (> 0.100 thold), f_keep = 0.898 8.14.010.689 I slot launch_slot_: id 2 | task 4868 | processing task, is_child = 0 8.14.010.761 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 338.705 MiB) 8.14.870.047 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 340.328 MiB) 8.14.878.119 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1237, t_last = 390326752901 8.14.878.244 I slot launch_slot_: id 0 | task 4869 | processing task, is_child = 0 8.14.878.306 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1291, t_last = 390326753094 8.14.878.392 I slot launch_slot_: id 1 | task 4870 | processing task, is_child = 0 8.17.533.718 I slot print_timing: id 3 | task 4864 | prompt processing, n_tokens = 2288, progress = 0.92, t = 6.04 s / 378.52 tokens per second 8.19.745.514 I slot print_timing: id 0 | task 4869 | prompt processing, n_tokens = 520, progress = 0.29, t = 4.87 s / 106.84 tokens per second 8.19.745.539 I slot print_timing: id 1 | task 4870 | prompt processing, n_tokens = 961, progress = 0.36, t = 4.87 s / 197.46 tokens per second 8.19.745.564 I slot print_timing: id 3 | task 4864 | prompt processing, n_tokens = 2496, progress = 1.00, t = 8.46 s / 294.93 tokens per second 8.23.070.630 I slot print_timing: id 2 | task 4868 | prompt eval time = 4866.93 ms / 454 tokens ( 10.72 ms per token, 93.28 tokens per second) 8.23.070.635 I slot print_timing: id 2 | task 4868 | eval time = 3325.12 ms / 2 tokens ( 3325.12 ms per token, 0.30 tokens per second) 8.23.070.636 I slot print_timing: id 2 | task 4868 | total time = 8192.05 ms / 456 tokens 8.23.070.636 I slot print_timing: id 2 | task 4868 | graphs reused = 3659 8.23.070.637 I slot print_timing: id 2 | task 4868 | graph reallocs = 0 / 0 (same size) / (changed size) 8.23.070.749 I slot release: id 2 | task 4868 | stop processing: n_tokens = 2743, truncated = 0 8.23.070.962 I slot print_timing: id 0 | task 4869 | prompt processing, n_tokens = 1263, progress = 0.71, t = 8.19 s / 154.17 tokens per second 8.23.074.135 I slot print_timing: id 1 | task 4870 | prompt processing, n_tokens = 2139, progress = 0.81, t = 8.19 s / 261.11 tokens per second 8.23.856.841 I slot print_timing: id 3 | task 4864 | prompt eval time = 11788.71 ms / 2500 tokens ( 4.72 ms per token, 212.07 tokens per second) 8.23.856.846 I slot print_timing: id 3 | task 4864 | eval time = 785.89 ms / 2 tokens ( 785.89 ms per token, 1.27 tokens per second) 8.23.856.848 I slot print_timing: id 3 | task 4864 | total time = 12574.60 ms / 2502 tokens 8.23.856.848 I slot print_timing: id 3 | task 4864 | graphs reused = 3659 8.23.856.849 I slot print_timing: id 3 | task 4864 | graph reallocs = 0 / 0 (same size) / (changed size) 8.23.856.944 I slot release: id 3 | task 4864 | stop processing: n_tokens = 2501, truncated = 0 8.23.856.952 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 2743, t_last = 390336660880 8.23.857.075 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 339.506 MiB) 8.23.875.670 I slot launch_slot_: id 2 | task 4875 | processing task, is_child = 0 8.23.875.776 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 329.573 MiB) 8.23.890.781 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 2501, t_last = 390337447075 8.23.890.914 I slot launch_slot_: id 3 | task 4876 | processing task, is_child = 0 8.23.890.920 I slot print_timing: id 0 | task 4869 | prompt processing, n_tokens = 1447, progress = 0.81, t = 8.98 s / 161.17 tokens per second 8.23.892.793 I slot print_timing: id 1 | task 4870 | prompt processing, n_tokens = 2288, progress = 0.86, t = 8.98 s / 254.84 tokens per second 8.25.815.658 I slot print_timing: id 0 | task 4869 | prompt processing, n_tokens = 1775, progress = 1.00, t = 10.94 s / 162.29 tokens per second 8.25.991.589 I slot print_timing: id 1 | task 4870 | prompt processing, n_tokens = 2651, progress = 1.00, t = 10.94 s / 242.38 tokens per second 8.27.187.802 I slot print_timing: id 2 | task 4875 | prompt processing, n_tokens = 520, progress = 0.28, t = 3.29 s / 157.93 tokens per second 8.27.187.829 I slot print_timing: id 3 | task 4876 | prompt processing, n_tokens = 520, progress = 0.25, t = 3.29 s / 157.94 tokens per second 8.30.231.808 I slot print_timing: id 0 | task 4869 | prompt eval time = 12309.16 ms / 1779 tokens ( 6.92 ms per token, 144.53 tokens per second) 8.30.231.813 I slot print_timing: id 0 | task 4869 | eval time = 3044.24 ms / 2 tokens ( 3044.24 ms per token, 0.33 tokens per second) 8.30.231.814 I slot print_timing: id 0 | task 4869 | total time = 15353.40 ms / 1781 tokens 8.30.231.814 I slot print_timing: id 0 | task 4869 | graphs reused = 3659 8.30.231.815 I slot print_timing: id 0 | task 4869 | graph reallocs = 0 / 0 (same size) / (changed size) 8.30.231.897 I slot release: id 0 | task 4869 | stop processing: n_tokens = 1780, truncated = 0 8.30.232.126 I slot print_timing: id 1 | task 4870 | prompt eval time = 12309.29 ms / 2655 tokens ( 4.64 ms per token, 215.69 tokens per second) 8.30.232.136 I slot print_timing: id 1 | task 4870 | eval time = 3044.34 ms / 2 tokens ( 3044.34 ms per token, 0.33 tokens per second) 8.30.232.136 I slot print_timing: id 1 | task 4870 | total time = 15353.63 ms / 2657 tokens 8.30.232.141 I slot print_timing: id 1 | task 4870 | graphs reused = 3659 8.30.232.141 I slot print_timing: id 1 | task 4870 | graph reallocs = 0 / 0 (same size) / (changed size) 8.30.232.238 I slot release: id 1 | task 4870 | stop processing: n_tokens = 2656, truncated = 0 8.30.232.255 I slot print_timing: id 2 | task 4875 | prompt processing, n_tokens = 1325, progress = 0.72, t = 6.34 s / 209.09 tokens per second 8.30.235.864 I slot print_timing: id 3 | task 4876 | prompt processing, n_tokens = 1447, progress = 0.71, t = 6.34 s / 228.35 tokens per second 8.30.643.897 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.801 (> 0.100 thold), f_keep = 0.834 8.30.643.947 I slot launch_slot_: id 0 | task 4881 | processing task, is_child = 0 8.30.644.062 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.509 MiB) 8.30.822.792 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 2656, t_last = 390343822369 8.30.822.967 I slot launch_slot_: id 1 | task 4882 | processing task, is_child = 0 8.30.826.374 I slot print_timing: id 2 | task 4875 | prompt processing, n_tokens = 1447, progress = 0.79, t = 6.75 s / 214.39 tokens per second 8.30.828.266 I slot print_timing: id 3 | task 4876 | prompt processing, n_tokens = 1532, progress = 0.75, t = 6.75 s / 226.99 tokens per second 8.33.718.143 I slot print_timing: id 2 | task 4875 | prompt processing, n_tokens = 1837, progress = 1.00, t = 9.50 s / 193.29 tokens per second 8.33.722.679 I slot print_timing: id 3 | task 4876 | prompt processing, n_tokens = 2044, progress = 1.00, t = 9.50 s / 215.08 tokens per second 8.34.414.700 I slot print_timing: id 1 | task 4882 | prompt processing, n_tokens = 520, progress = 0.27, t = 3.59 s / 144.93 tokens per second 8.36.025.083 I slot print_timing: id 0 | task 4881 | prompt eval time = 3591.34 ms / 405 tokens ( 8.87 ms per token, 112.77 tokens per second) 8.36.025.086 I slot print_timing: id 0 | task 4881 | eval time = 1610.77 ms / 2 tokens ( 1610.77 ms per token, 0.62 tokens per second) 8.36.025.086 I slot print_timing: id 0 | task 4881 | total time = 5202.10 ms / 407 tokens 8.36.025.087 I slot print_timing: id 0 | task 4881 | graphs reused = 3659 8.36.025.087 I slot print_timing: id 0 | task 4881 | graph reallocs = 0 / 0 (same size) / (changed size) 8.36.025.164 I slot release: id 0 | task 4881 | stop processing: n_tokens = 1853, truncated = 0 8.36.025.334 I slot print_timing: id 2 | task 4875 | prompt eval time = 10519.82 ms / 1841 tokens ( 5.71 ms per token, 175.00 tokens per second) 8.36.025.336 I slot print_timing: id 2 | task 4875 | eval time = 1610.85 ms / 2 tokens ( 1610.85 ms per token, 0.62 tokens per second) 8.36.025.337 I slot print_timing: id 2 | task 4875 | total time = 12130.67 ms / 1843 tokens 8.36.025.337 I slot print_timing: id 2 | task 4875 | graphs reused = 3659 8.36.025.337 I slot print_timing: id 2 | task 4875 | graph reallocs = 0 / 0 (same size) / (changed size) 8.36.025.385 I slot release: id 2 | task 4875 | stop processing: n_tokens = 1842, truncated = 0 8.36.025.620 I slot print_timing: id 3 | task 4876 | prompt eval time = 10519.86 ms / 2048 tokens ( 5.14 ms per token, 194.68 tokens per second) 8.36.025.622 I slot print_timing: id 3 | task 4876 | eval time = 1610.93 ms / 2 tokens ( 1610.93 ms per token, 0.62 tokens per second) 8.36.025.623 I slot print_timing: id 3 | task 4876 | total time = 12130.78 ms / 2050 tokens 8.36.025.624 I slot print_timing: id 3 | task 4876 | graphs reused = 3659 8.36.025.624 I slot print_timing: id 3 | task 4876 | graph reallocs = 0 / 0 (same size) / (changed size) 8.36.025.671 I slot release: id 3 | task 4876 | stop processing: n_tokens = 2049, truncated = 0 8.36.025.680 I slot print_timing: id 1 | task 4882 | prompt processing, n_tokens = 1446, progress = 0.74, t = 5.20 s / 278.15 tokens per second 8.36.029.837 I slot print_timing: id 1 | task 4882 | prompt processing, n_tokens = 1447, progress = 0.74, t = 5.20 s / 278.07 tokens per second 8.36.053.695 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1853, t_last = 390349615295 8.36.053.783 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 329.886 MiB) 8.36.912.477 I slot launch_slot_: id 0 | task 4888 | processing task, is_child = 0 8.36.912.563 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 330.883 MiB) 8.36.926.845 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 330.805 MiB) 8.36.940.993 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1842, t_last = 390349615515 8.36.941.127 I slot launch_slot_: id 2 | task 4889 | processing task, is_child = 0 8.36.941.210 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.833 (> 0.100 thold), f_keep = 0.724 8.36.941.233 I slot launch_slot_: id 3 | task 4890 | processing task, is_child = 0 8.36.941.379 I slot print_timing: id 1 | task 4882 | prompt processing, n_tokens = 1958, progress = 1.00, t = 5.23 s / 374.56 tokens per second 8.38.958.554 I slot print_timing: id 1 | task 4882 | prompt eval time = 7492.35 ms / 1962 tokens ( 3.82 ms per token, 261.87 tokens per second) 8.38.958.557 I slot print_timing: id 1 | task 4882 | eval time = 640.01 ms / 2 tokens ( 640.01 ms per token, 1.56 tokens per second) 8.38.958.557 I slot print_timing: id 1 | task 4882 | total time = 8132.36 ms / 1964 tokens 8.38.958.558 I slot print_timing: id 1 | task 4882 | graphs reused = 3659 8.38.958.558 I slot print_timing: id 1 | task 4882 | graph reallocs = 0 / 0 (same size) / (changed size) 8.38.958.640 I slot release: id 1 | task 4882 | stop processing: n_tokens = 1963, truncated = 0 8.40.328.123 I slot print_timing: id 3 | task 4890 | prompt eval time = 2015.25 ms / 334 tokens ( 6.03 ms per token, 165.74 tokens per second) 8.40.328.129 I slot print_timing: id 3 | task 4890 | eval time = 1369.30 ms / 2 tokens ( 1369.30 ms per token, 0.73 tokens per second) 8.40.328.130 I slot print_timing: id 3 | task 4890 | total time = 3384.55 ms / 336 tokens 8.40.328.130 I slot print_timing: id 3 | task 4890 | graphs reused = 3659 8.40.328.131 I slot print_timing: id 3 | task 4890 | graph reallocs = 0 / 0 (same size) / (changed size) 8.40.328.203 I slot release: id 3 | task 4890 | stop processing: n_tokens = 1782, truncated = 0 8.40.328.211 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1963, t_last = 390352548770 8.40.328.303 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 329.299 MiB) 8.40.344.127 I slot launch_slot_: id 1 | task 4894 | processing task, is_child = 0 8.40.344.207 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 329.221 MiB) 8.40.356.658 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1782, t_last = 390353918333 8.40.356.767 I slot launch_slot_: id 3 | task 4895 | processing task, is_child = 0 8.40.356.775 I slot print_timing: id 0 | task 4888 | prompt processing, n_tokens = 615, progress = 0.85, t = 3.39 s / 181.60 tokens per second 8.40.358.789 I slot print_timing: id 2 | task 4889 | prompt processing, n_tokens = 615, progress = 0.82, t = 3.38 s / 181.71 tokens per second 8.41.326.839 I slot print_timing: id 0 | task 4888 | prompt processing, n_tokens = 722, progress = 0.99, t = 4.39 s / 164.63 tokens per second 8.41.347.225 I slot print_timing: id 2 | task 4889 | prompt processing, n_tokens = 744, progress = 0.99, t = 4.38 s / 169.73 tokens per second 8.43.418.889 I slot print_timing: id 0 | task 4888 | prompt eval time = 5073.65 ms / 726 tokens ( 6.99 ms per token, 143.09 tokens per second) 8.43.418.892 I slot print_timing: id 0 | task 4888 | eval time = 1403.99 ms / 2 tokens ( 1403.99 ms per token, 0.71 tokens per second) 8.43.418.893 I slot print_timing: id 0 | task 4888 | total time = 6477.64 ms / 728 tokens 8.43.418.893 I slot print_timing: id 0 | task 4888 | graphs reused = 3659 8.43.418.894 I slot print_timing: id 0 | task 4888 | graph reallocs = 0 / 0 (same size) / (changed size) 8.43.418.930 I slot release: id 0 | task 4888 | stop processing: n_tokens = 727, truncated = 0 8.43.419.193 I slot print_timing: id 2 | task 4889 | prompt eval time = 5071.67 ms / 748 tokens ( 6.78 ms per token, 147.49 tokens per second) 8.43.419.196 I slot print_timing: id 2 | task 4889 | eval time = 1404.08 ms / 2 tokens ( 1404.08 ms per token, 0.71 tokens per second) 8.43.419.196 I slot print_timing: id 2 | task 4889 | total time = 6475.75 ms / 750 tokens 8.43.419.196 I slot print_timing: id 2 | task 4889 | graphs reused = 3659 8.43.419.197 I slot print_timing: id 2 | task 4889 | graph reallocs = 0 / 0 (same size) / (changed size) 8.43.419.218 I slot release: id 2 | task 4889 | stop processing: n_tokens = 749, truncated = 0 8.43.419.228 I slot print_timing: id 1 | task 4894 | prompt processing, n_tokens = 615, progress = 0.81, t = 3.06 s / 200.98 tokens per second 8.43.423.007 I slot print_timing: id 3 | task 4895 | prompt processing, n_tokens = 615, progress = 0.85, t = 3.06 s / 201.11 tokens per second 8.43.775.217 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 727, t_last = 390357009060 8.43.775.275 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 329.768 MiB) 8.44.070.337 I slot launch_slot_: id 0 | task 4900 | processing task, is_child = 0 8.44.070.392 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 332.936 MiB) 8.44.079.069 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.870 (> 0.100 thold), f_keep = 0.858 8.44.079.104 I slot launch_slot_: id 2 | task 4901 | processing task, is_child = 0 8.44.079.180 I slot print_timing: id 1 | task 4894 | prompt processing, n_tokens = 757, progress = 0.99, t = 3.42 s / 221.57 tokens per second 8.44.084.336 I slot print_timing: id 3 | task 4895 | prompt processing, n_tokens = 721, progress = 0.99, t = 3.41 s / 211.16 tokens per second 8.45.247.458 I slot print_timing: id 1 | task 4894 | prompt eval time = 4450.11 ms / 761 tokens ( 5.85 ms per token, 171.01 tokens per second) 8.45.247.463 I slot print_timing: id 1 | task 4894 | eval time = 438.68 ms / 2 tokens ( 438.68 ms per token, 2.28 tokens per second) 8.45.247.463 I slot print_timing: id 1 | task 4894 | total time = 4888.79 ms / 763 tokens 8.45.247.464 I slot print_timing: id 1 | task 4894 | graphs reused = 3659 8.45.247.464 I slot print_timing: id 1 | task 4894 | graph reallocs = 0 / 0 (same size) / (changed size) 8.45.247.503 I slot release: id 1 | task 4894 | stop processing: n_tokens = 762, truncated = 0 8.45.247.908 I slot print_timing: id 3 | task 4895 | prompt eval time = 4448.34 ms / 725 tokens ( 6.14 ms per token, 162.98 tokens per second) 8.45.247.911 I slot print_timing: id 3 | task 4895 | eval time = 438.90 ms / 2 tokens ( 438.90 ms per token, 2.28 tokens per second) 8.45.247.911 I slot print_timing: id 3 | task 4895 | total time = 4887.24 ms / 727 tokens 8.45.247.911 I slot print_timing: id 3 | task 4895 | graphs reused = 3659 8.45.247.912 I slot print_timing: id 3 | task 4895 | graph reallocs = 0 / 0 (same size) / (changed size) 8.45.247.937 I slot release: id 3 | task 4895 | stop processing: n_tokens = 726, truncated = 0 8.45.435.266 I slot print_timing: id 2 | task 4901 | prompt eval time = 1166.56 ms / 124 tokens ( 9.41 ms per token, 106.30 tokens per second) 8.45.435.269 I slot print_timing: id 2 | task 4901 | eval time = 187.58 ms / 2 tokens ( 187.58 ms per token, 5.33 tokens per second) 8.45.435.269 I slot print_timing: id 2 | task 4901 | total time = 1354.14 ms / 126 tokens 8.45.435.270 I slot print_timing: id 2 | task 4901 | graphs reused = 3659 8.45.435.270 I slot print_timing: id 2 | task 4901 | graph reallocs = 0 / 0 (same size) / (changed size) 8.45.435.307 I slot release: id 2 | task 4901 | stop processing: n_tokens = 740, truncated = 0 8.45.435.314 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 762, t_last = 390358837633 8.45.435.368 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 333.034 MiB) 8.45.444.972 I slot launch_slot_: id 1 | task 4905 | processing task, is_child = 0 8.45.445.022 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 332.545 MiB) 8.45.453.396 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 332.604 MiB) 8.45.460.882 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 726, t_last = 390358838067 8.45.460.968 I slot launch_slot_: id 3 | task 4906 | processing task, is_child = 0 8.45.461.010 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 740, t_last = 390359025437 8.45.461.070 I slot launch_slot_: id 2 | task 4907 | processing task, is_child = 0 8.48.161.056 I slot print_timing: id 0 | task 4900 | prompt processing, n_tokens = 794, progress = 0.99, t = 4.08 s / 194.52 tokens per second 8.48.963.277 I slot print_timing: id 1 | task 4905 | prompt processing, n_tokens = 526, progress = 0.50, t = 3.50 s / 150.28 tokens per second 8.48.965.920 I slot print_timing: id 2 | task 4907 | prompt processing, n_tokens = 283, progress = 0.35, t = 3.50 s / 80.86 tokens per second 8.48.968.151 I slot print_timing: id 3 | task 4906 | prompt processing, n_tokens = 293, progress = 0.36, t = 3.50 s / 83.72 tokens per second 8.51.165.438 I slot print_timing: id 0 | task 4900 | prompt eval time = 4884.15 ms / 798 tokens ( 6.12 ms per token, 163.39 tokens per second) 8.51.165.441 I slot print_timing: id 0 | task 4900 | eval time = 2202.16 ms / 2 tokens ( 2202.16 ms per token, 0.45 tokens per second) 8.51.165.442 I slot print_timing: id 0 | task 4900 | total time = 7086.32 ms / 800 tokens 8.51.165.442 I slot print_timing: id 0 | task 4900 | graphs reused = 3659 8.51.165.442 I slot print_timing: id 0 | task 4900 | graph reallocs = 0 / 0 (same size) / (changed size) 8.51.165.482 I slot release: id 0 | task 4900 | stop processing: n_tokens = 799, truncated = 0 8.51.165.496 I slot print_timing: id 1 | task 4905 | prompt processing, n_tokens = 893, progress = 0.86, t = 5.70 s / 156.60 tokens per second 8.51.168.127 I slot print_timing: id 2 | task 4907 | prompt processing, n_tokens = 679, progress = 0.85, t = 5.70 s / 119.08 tokens per second 8.51.171.351 I slot print_timing: id 3 | task 4906 | prompt processing, n_tokens = 679, progress = 0.84, t = 5.70 s / 119.08 tokens per second 8.51.980.513 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 799, t_last = 390364755612 8.51.980.567 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 329.710 MiB) 8.52.057.109 I slot launch_slot_: id 0 | task 4913 | processing task, is_child = 0 8.52.057.193 I slot print_timing: id 1 | task 4905 | prompt processing, n_tokens = 1038, progress = 1.00, t = 6.52 s / 159.26 tokens per second 8.52.059.526 I slot print_timing: id 2 | task 4907 | prompt processing, n_tokens = 795, progress = 0.99, t = 6.52 s / 121.98 tokens per second 8.52.061.474 I slot print_timing: id 3 | task 4906 | prompt processing, n_tokens = 805, progress = 1.00, t = 6.52 s / 123.51 tokens per second 8.52.951.525 I slot print_timing: id 1 | task 4905 | prompt eval time = 7054.23 ms / 1042 tokens ( 6.77 ms per token, 147.71 tokens per second) 8.52.951.528 I slot print_timing: id 1 | task 4905 | eval time = 434.32 ms / 2 tokens ( 434.32 ms per token, 2.30 tokens per second) 8.52.951.528 I slot print_timing: id 1 | task 4905 | total time = 7488.56 ms / 1044 tokens 8.52.951.529 I slot print_timing: id 1 | task 4905 | graphs reused = 3659 8.52.951.529 I slot print_timing: id 1 | task 4905 | graph reallocs = 0 / 0 (same size) / (changed size) 8.52.951.574 I slot release: id 1 | task 4905 | stop processing: n_tokens = 1043, truncated = 0 8.52.951.727 I slot print_timing: id 2 | task 4907 | prompt eval time = 7054.35 ms / 799 tokens ( 8.83 ms per token, 113.26 tokens per second) 8.52.951.731 I slot print_timing: id 2 | task 4907 | eval time = 434.36 ms / 2 tokens ( 434.36 ms per token, 2.30 tokens per second) 8.52.951.732 I slot print_timing: id 2 | task 4907 | total time = 7488.71 ms / 801 tokens 8.52.951.732 I slot print_timing: id 2 | task 4907 | graphs reused = 3659 8.52.951.732 I slot print_timing: id 2 | task 4907 | graph reallocs = 0 / 0 (same size) / (changed size) 8.52.951.762 I slot release: id 2 | task 4907 | stop processing: n_tokens = 800, truncated = 0 8.52.951.940 I slot print_timing: id 3 | task 4906 | prompt eval time = 7054.52 ms / 809 tokens ( 8.72 ms per token, 114.68 tokens per second) 8.52.951.941 I slot print_timing: id 3 | task 4906 | eval time = 434.34 ms / 2 tokens ( 434.34 ms per token, 2.30 tokens per second) 8.52.951.941 I slot print_timing: id 3 | task 4906 | total time = 7488.86 ms / 811 tokens 8.52.951.942 I slot print_timing: id 3 | task 4906 | graphs reused = 3659 8.52.951.942 I slot print_timing: id 3 | task 4906 | graph reallocs = 0 / 0 (same size) / (changed size) 8.52.951.963 I slot release: id 3 | task 4906 | stop processing: n_tokens = 810, truncated = 0 8.53.036.088 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1043, t_last = 390366541704 8.53.036.146 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 329.690 MiB) 8.53.710.418 I slot launch_slot_: id 1 | task 4918 | processing task, is_child = 0 8.53.710.471 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 332.721 MiB) 8.53.718.033 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 332.877 MiB) 8.53.725.547 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 800, t_last = 390366541892 8.53.725.637 I slot launch_slot_: id 2 | task 4919 | processing task, is_child = 0 8.53.725.679 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 810, t_last = 390366542093 8.53.725.738 I slot launch_slot_: id 3 | task 4920 | processing task, is_child = 0 8.56.295.938 I slot print_timing: id 0 | task 4913 | prompt eval time = 3667.83 ms / 845 tokens ( 4.34 ms per token, 230.38 tokens per second) 8.56.295.942 I slot print_timing: id 0 | task 4913 | eval time = 570.98 ms / 2 tokens ( 570.98 ms per token, 1.75 tokens per second) 8.56.295.943 I slot print_timing: id 0 | task 4913 | total time = 4238.82 ms / 847 tokens 8.56.295.943 I slot print_timing: id 0 | task 4913 | graphs reused = 3659 8.56.295.944 I slot print_timing: id 0 | task 4913 | graph reallocs = 0 / 0 (same size) / (changed size) 8.56.295.986 I slot release: id 0 | task 4913 | stop processing: n_tokens = 846, truncated = 0 8.58.013.664 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.871 (> 0.100 thold), f_keep = 0.888 8.58.013.736 I slot launch_slot_: id 0 | task 4925 | processing task, is_child = 0 8.58.228.052 I slot print_timing: id 1 | task 4918 | prompt processing, n_tokens = 723, progress = 0.80, t = 4.29 s / 168.69 tokens per second 8.58.230.209 I slot print_timing: id 2 | task 4919 | prompt processing, n_tokens = 723, progress = 0.86, t = 4.29 s / 168.69 tokens per second 8.58.232.249 I slot print_timing: id 3 | task 4920 | prompt processing, n_tokens = 723, progress = 0.79, t = 4.29 s / 168.69 tokens per second 8.59.605.608 I slot print_timing: id 1 | task 4918 | prompt processing, n_tokens = 897, progress = 1.00, t = 5.63 s / 159.19 tokens per second 8.59.608.265 I slot print_timing: id 2 | task 4919 | prompt processing, n_tokens = 835, progress = 1.00, t = 5.63 s / 148.19 tokens per second 8.59.610.517 I slot print_timing: id 3 | task 4920 | prompt processing, n_tokens = 906, progress = 1.00, t = 5.63 s / 160.80 tokens per second 8.59.791.195 I slot print_timing: id 0 | task 4925 | prompt eval time = 1723.38 ms / 139 tokens ( 12.40 ms per token, 80.66 tokens per second) 8.59.791.198 I slot print_timing: id 0 | task 4925 | eval time = 54.07 ms / 2 tokens ( 54.07 ms per token, 18.49 tokens per second) 8.59.791.198 I slot print_timing: id 0 | task 4925 | total time = 1777.45 ms / 141 tokens 8.59.791.199 I slot print_timing: id 0 | task 4925 | graphs reused = 3659 8.59.791.199 I slot print_timing: id 0 | task 4925 | graph reallocs = 0 / 0 (same size) / (changed size) 8.59.791.244 I slot release: id 0 | task 4925 | stop processing: n_tokens = 863, truncated = 0 8.59.791.396 I slot print_timing: id 1 | task 4918 | prompt eval time = 6009.71 ms / 901 tokens ( 6.67 ms per token, 149.92 tokens per second) 8.59.791.398 I slot print_timing: id 1 | task 4918 | eval time = 54.08 ms / 2 tokens ( 54.08 ms per token, 18.49 tokens per second) 8.59.791.399 I slot print_timing: id 1 | task 4918 | total time = 6063.80 ms / 903 tokens 8.59.791.399 I slot print_timing: id 1 | task 4918 | graphs reused = 3659 8.59.791.399 I slot print_timing: id 1 | task 4918 | graph reallocs = 0 / 0 (same size) / (changed size) 8.59.791.426 I slot release: id 1 | task 4918 | stop processing: n_tokens = 902, truncated = 0 8.59.791.590 I slot print_timing: id 2 | task 4919 | prompt eval time = 6009.84 ms / 839 tokens ( 7.16 ms per token, 139.60 tokens per second) 8.59.791.592 I slot print_timing: id 2 | task 4919 | eval time = 54.08 ms / 2 tokens ( 54.08 ms per token, 18.49 tokens per second) 8.59.791.593 I slot print_timing: id 2 | task 4919 | total time = 6063.92 ms / 841 tokens 8.59.791.593 I slot print_timing: id 2 | task 4919 | graphs reused = 3659 8.59.791.593 I slot print_timing: id 2 | task 4919 | graph reallocs = 0 / 0 (same size) / (changed size) 8.59.791.614 I slot release: id 2 | task 4919 | stop processing: n_tokens = 840, truncated = 0 8.59.791.778 I slot print_timing: id 3 | task 4920 | prompt eval time = 6010.01 ms / 910 tokens ( 6.60 ms per token, 151.41 tokens per second) 8.59.791.781 I slot print_timing: id 3 | task 4920 | eval time = 54.04 ms / 2 tokens ( 54.04 ms per token, 18.51 tokens per second) 8.59.791.781 I slot print_timing: id 3 | task 4920 | total time = 6064.05 ms / 912 tokens 8.59.791.781 I slot print_timing: id 3 | task 4920 | graphs reused = 3659 8.59.791.782 I slot print_timing: id 3 | task 4920 | graph reallocs = 0 / 0 (same size) / (changed size) 8.59.791.800 I slot release: id 3 | task 4920 | stop processing: n_tokens = 911, truncated = 0 8.59.799.469 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 863, t_last = 390373381374 8.59.799.520 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.646 MiB) 8.59.807.182 I slot launch_slot_: id 0 | task 4929 | processing task, is_child = 0 8.59.807.229 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.665 MiB) 8.59.814.935 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.724 MiB) 8.59.822.809 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.489 MiB) 8.59.830.676 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 902, t_last = 390373381556 8.59.830.775 I slot launch_slot_: id 1 | task 4930 | processing task, is_child = 0 8.59.830.860 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 840, t_last = 390373381744 8.59.830.932 I slot launch_slot_: id 2 | task 4931 | processing task, is_child = 0 8.59.830.980 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 911, t_last = 390373381930 8.59.831.052 I slot launch_slot_: id 3 | task 4932 | processing task, is_child = 0 9.02.855.153 I slot print_timing: id 0 | task 4929 | prompt processing, n_tokens = 583, progress = 0.85, t = 3.02 s / 192.79 tokens per second 9.03.394.960 I slot print_timing: id 1 | task 4930 | prompt processing, n_tokens = 309, progress = 0.37, t = 3.02 s / 102.18 tokens per second 9.03.397.118 I slot print_timing: id 2 | task 4931 | prompt processing, n_tokens = 632, progress = 0.82, t = 3.02 s / 209.00 tokens per second 9.03.399.255 I slot print_timing: id 3 | task 4932 | prompt processing, n_tokens = 335, progress = 0.39, t = 3.02 s / 110.78 tokens per second 9.04.888.119 I slot print_timing: id 0 | task 4929 | prompt processing, n_tokens = 684, progress = 0.99, t = 5.06 s / 135.26 tokens per second 9.05.369.996 I slot print_timing: id 1 | task 4930 | prompt processing, n_tokens = 708, progress = 0.86, t = 5.06 s / 140.00 tokens per second 9.05.373.088 I slot print_timing: id 2 | task 4931 | prompt processing, n_tokens = 765, progress = 0.99, t = 5.06 s / 151.28 tokens per second 9.05.375.303 I slot print_timing: id 3 | task 4932 | prompt processing, n_tokens = 708, progress = 0.83, t = 5.06 s / 140.01 tokens per second 9.06.143.100 I slot print_timing: id 1 | task 4930 | prompt processing, n_tokens = 821, progress = 1.00, t = 6.31 s / 130.08 tokens per second 9.06.146.645 I slot print_timing: id 3 | task 4932 | prompt processing, n_tokens = 847, progress = 1.00, t = 6.31 s / 134.20 tokens per second 9.06.286.766 I slot print_timing: id 0 | task 4929 | prompt eval time = 6311.85 ms / 688 tokens ( 9.17 ms per token, 109.00 tokens per second) 9.06.286.773 I slot print_timing: id 0 | task 4929 | eval time = 143.86 ms / 2 tokens ( 143.86 ms per token, 6.95 tokens per second) 9.06.286.774 I slot print_timing: id 0 | task 4929 | total time = 6455.70 ms / 690 tokens 9.06.286.774 I slot print_timing: id 0 | task 4929 | graphs reused = 3659 9.06.286.775 I slot print_timing: id 0 | task 4929 | graph reallocs = 0 / 0 (same size) / (changed size) 9.06.286.830 I slot release: id 0 | task 4929 | stop processing: n_tokens = 689, truncated = 0 9.06.287.448 I slot print_timing: id 2 | task 4931 | prompt eval time = 6311.91 ms / 769 tokens ( 8.21 ms per token, 121.83 tokens per second) 9.06.287.459 I slot print_timing: id 2 | task 4931 | eval time = 144.36 ms / 2 tokens ( 144.36 ms per token, 6.93 tokens per second) 9.06.287.459 I slot print_timing: id 2 | task 4931 | total time = 6456.27 ms / 771 tokens 9.06.287.460 I slot print_timing: id 2 | task 4931 | graphs reused = 3659 9.06.287.461 I slot print_timing: id 2 | task 4931 | graph reallocs = 0 / 0 (same size) / (changed size) 9.06.287.499 I slot release: id 2 | task 4931 | stop processing: n_tokens = 770, truncated = 0 9.06.334.000 I slot print_timing: id 1 | task 4930 | prompt eval time = 6455.99 ms / 825 tokens ( 7.83 ms per token, 127.79 tokens per second) 9.06.334.005 I slot print_timing: id 1 | task 4930 | eval time = 46.88 ms / 2 tokens ( 46.88 ms per token, 21.33 tokens per second) 9.06.334.006 I slot print_timing: id 1 | task 4930 | total time = 6502.87 ms / 827 tokens 9.06.334.007 I slot print_timing: id 1 | task 4930 | graphs reused = 3659 9.06.334.008 I slot print_timing: id 1 | task 4930 | graph reallocs = 0 / 0 (same size) / (changed size) 9.06.334.093 I slot release: id 1 | task 4930 | stop processing: n_tokens = 826, truncated = 0 9.06.334.443 I slot print_timing: id 3 | task 4932 | prompt eval time = 6456.56 ms / 851 tokens ( 7.59 ms per token, 131.80 tokens per second) 9.06.334.448 I slot print_timing: id 3 | task 4932 | eval time = 46.65 ms / 2 tokens ( 46.65 ms per token, 21.44 tokens per second) 9.06.334.449 I slot print_timing: id 3 | task 4932 | total time = 6503.21 ms / 853 tokens 9.06.334.449 I slot print_timing: id 3 | task 4932 | graphs reused = 3659 9.06.334.450 I slot print_timing: id 3 | task 4932 | graph reallocs = 0 / 0 (same size) / (changed size) 9.06.334.500 I slot release: id 3 | task 4932 | stop processing: n_tokens = 852, truncated = 0 9.06.334.508 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 689, t_last = 390379876960 9.06.334.615 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 338.040 MiB) 9.06.347.840 I slot launch_slot_: id 0 | task 4940 | processing task, is_child = 0 9.06.347.920 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 338.255 MiB) 9.06.358.607 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 339.311 MiB) 9.06.368.725 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 367.703 MiB) 9.06.378.818 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 9.06.378.871 I slot launch_slot_: id 2 | task 4941 | processing task, is_child = 0 9.06.378.995 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 826, t_last = 390379924223 9.06.379.081 I slot launch_slot_: id 1 | task 4942 | processing task, is_child = 0 9.06.379.137 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 852, t_last = 390379924630 9.06.379.216 I slot launch_slot_: id 3 | task 4943 | processing task, is_child = 0 9.10.073.233 I slot print_timing: id 2 | task 4941 | prompt eval time = 1635.14 ms / 120 tokens ( 13.63 ms per token, 73.39 tokens per second) 9.10.073.238 I slot print_timing: id 2 | task 4941 | eval time = 2058.72 ms / 2 tokens ( 2058.72 ms per token, 0.49 tokens per second) 9.10.073.238 I slot print_timing: id 2 | task 4941 | total time = 3693.86 ms / 122 tokens 9.10.073.239 I slot print_timing: id 2 | task 4941 | graphs reused = 3659 9.10.073.239 I slot print_timing: id 2 | task 4941 | graph reallocs = 0 / 0 (same size) / (changed size) 9.10.073.275 I slot release: id 2 | task 4941 | stop processing: n_tokens = 753, truncated = 0 9.10.073.288 I slot print_timing: id 0 | task 4940 | prompt processing, n_tokens = 603, progress = 0.85, t = 3.69 s / 163.25 tokens per second 9.10.076.840 I slot print_timing: id 1 | task 4942 | prompt processing, n_tokens = 603, progress = 0.84, t = 3.69 s / 163.25 tokens per second 9.10.079.509 I slot print_timing: id 3 | task 4943 | prompt processing, n_tokens = 603, progress = 0.82, t = 3.69 s / 163.50 tokens per second 9.10.573.031 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 753, t_last = 390383663405 9.10.573.086 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 362.971 MiB) 9.10.910.572 I slot launch_slot_: id 2 | task 4948 | processing task, is_child = 0 9.10.910.582 I slot print_timing: id 0 | task 4940 | prompt processing, n_tokens = 709, progress = 0.99, t = 4.19 s / 169.06 tokens per second 9.10.912.519 I slot print_timing: id 1 | task 4942 | prompt processing, n_tokens = 715, progress = 0.99, t = 4.19 s / 170.49 tokens per second 9.10.914.494 I slot print_timing: id 3 | task 4943 | prompt processing, n_tokens = 732, progress = 0.99, t = 4.19 s / 174.78 tokens per second 9.11.648.377 I slot print_timing: id 0 | task 4940 | prompt eval time = 4944.10 ms / 713 tokens ( 6.93 ms per token, 144.21 tokens per second) 9.11.648.382 I slot print_timing: id 0 | task 4940 | eval time = 325.05 ms / 2 tokens ( 325.05 ms per token, 3.08 tokens per second) 9.11.648.383 I slot print_timing: id 0 | task 4940 | total time = 5269.15 ms / 715 tokens 9.11.648.383 I slot print_timing: id 0 | task 4940 | graphs reused = 3659 9.11.648.383 I slot print_timing: id 0 | task 4940 | graph reallocs = 0 / 0 (same size) / (changed size) 9.11.648.422 I slot release: id 0 | task 4940 | stop processing: n_tokens = 714, truncated = 0 9.11.648.650 I slot print_timing: id 1 | task 4942 | prompt eval time = 4944.21 ms / 719 tokens ( 6.88 ms per token, 145.42 tokens per second) 9.11.648.653 I slot print_timing: id 1 | task 4942 | eval time = 325.14 ms / 2 tokens ( 325.14 ms per token, 3.08 tokens per second) 9.11.648.654 I slot print_timing: id 1 | task 4942 | total time = 5269.36 ms / 721 tokens 9.11.648.654 I slot print_timing: id 1 | task 4942 | graphs reused = 3659 9.11.648.654 I slot print_timing: id 1 | task 4942 | graph reallocs = 0 / 0 (same size) / (changed size) 9.11.648.694 I slot release: id 1 | task 4942 | stop processing: n_tokens = 720, truncated = 0 9.11.648.862 I slot print_timing: id 3 | task 4943 | prompt eval time = 4938.79 ms / 736 tokens ( 6.71 ms per token, 149.02 tokens per second) 9.11.648.864 I slot print_timing: id 3 | task 4943 | eval time = 325.12 ms / 2 tokens ( 325.12 ms per token, 3.08 tokens per second) 9.11.648.864 I slot print_timing: id 3 | task 4943 | total time = 5263.92 ms / 738 tokens 9.11.648.865 I slot print_timing: id 3 | task 4943 | graphs reused = 3659 9.11.648.865 I slot print_timing: id 3 | task 4943 | graph reallocs = 0 / 0 (same size) / (changed size) 9.11.648.886 I slot release: id 3 | task 4943 | stop processing: n_tokens = 737, truncated = 0 9.12.352.443 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.893 (> 0.100 thold), f_keep = 0.884 9.12.352.483 I slot launch_slot_: id 0 | task 4953 | processing task, is_child = 0 9.12.352.528 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 366.002 MiB) 9.12.649.503 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 350.300 MiB) 9.12.657.070 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.890 (> 0.100 thold), f_keep = 0.876 9.12.657.129 I slot launch_slot_: id 1 | task 4955 | processing task, is_child = 0 9.12.657.172 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.883 (> 0.100 thold), f_keep = 0.856 9.12.657.193 I slot launch_slot_: id 3 | task 4954 | processing task, is_child = 0 9.13.654.816 I slot print_timing: id 2 | task 4948 | prompt eval time = 2595.34 ms / 710 tokens ( 3.66 ms per token, 273.57 tokens per second) 9.13.654.819 I slot print_timing: id 2 | task 4948 | eval time = 145.02 ms / 2 tokens ( 145.02 ms per token, 6.90 tokens per second) 9.13.654.820 I slot print_timing: id 2 | task 4948 | total time = 2740.37 ms / 712 tokens 9.13.654.820 I slot print_timing: id 2 | task 4948 | graphs reused = 3659 9.13.654.821 I slot print_timing: id 2 | task 4948 | graph reallocs = 0 / 0 (same size) / (changed size) 9.13.654.857 I slot release: id 2 | task 4948 | stop processing: n_tokens = 711, truncated = 0 9.13.711.265 I slot print_timing: id 0 | task 4953 | prompt eval time = 997.31 ms / 104 tokens ( 9.59 ms per token, 104.28 tokens per second) 9.13.711.270 I slot print_timing: id 0 | task 4953 | eval time = 56.76 ms / 2 tokens ( 56.76 ms per token, 17.62 tokens per second) 9.13.711.270 I slot print_timing: id 0 | task 4953 | total time = 1054.06 ms / 106 tokens 9.13.711.271 I slot print_timing: id 0 | task 4953 | graphs reused = 3659 9.13.711.271 I slot print_timing: id 0 | task 4953 | graph reallocs = 0 / 0 (same size) / (changed size) 9.13.711.300 I slot release: id 0 | task 4953 | stop processing: n_tokens = 708, truncated = 0 9.13.711.456 I slot print_timing: id 1 | task 4955 | prompt eval time = 994.24 ms / 106 tokens ( 9.38 ms per token, 106.61 tokens per second) 9.13.711.459 I slot print_timing: id 1 | task 4955 | eval time = 56.78 ms / 2 tokens ( 56.78 ms per token, 17.61 tokens per second) 9.13.711.459 I slot print_timing: id 1 | task 4955 | total time = 1051.02 ms / 108 tokens 9.13.711.460 I slot print_timing: id 1 | task 4955 | graphs reused = 3659 9.13.711.460 I slot print_timing: id 1 | task 4955 | graph reallocs = 0 / 0 (same size) / (changed size) 9.13.711.481 I slot release: id 1 | task 4955 | stop processing: n_tokens = 710, truncated = 0 9.13.711.644 I slot print_timing: id 3 | task 4954 | prompt eval time = 989.54 ms / 112 tokens ( 8.84 ms per token, 113.18 tokens per second) 9.13.711.646 I slot print_timing: id 3 | task 4954 | eval time = 56.53 ms / 2 tokens ( 56.53 ms per token, 17.69 tokens per second) 9.13.711.647 I slot print_timing: id 3 | task 4954 | total time = 1046.07 ms / 114 tokens 9.13.711.647 I slot print_timing: id 3 | task 4954 | graphs reused = 3659 9.13.711.647 I slot print_timing: id 3 | task 4954 | graph reallocs = 0 / 0 (same size) / (changed size) 9.13.711.669 I slot release: id 3 | task 4954 | stop processing: n_tokens = 716, truncated = 0 9.13.711.675 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.893 9.13.711.718 I slot launch_slot_: id 1 | task 4959 | processing task, is_child = 0 9.13.711.763 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 350.085 MiB) 9.13.730.781 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 354.133 MiB) 9.13.738.285 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.883 (> 0.100 thold), f_keep = 0.893 9.13.738.343 I slot launch_slot_: id 0 | task 4960 | processing task, is_child = 0 9.13.738.436 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.890 (> 0.100 thold), f_keep = 0.887 9.13.738.458 I slot launch_slot_: id 2 | task 4961 | processing task, is_child = 0 9.13.738.501 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.840 (> 0.100 thold), f_keep = 0.881 9.13.738.522 I slot launch_slot_: id 3 | task 4962 | processing task, is_child = 0 9.14.945.095 I slot print_timing: id 0 | task 4960 | prompt eval time = 1152.73 ms / 113 tokens ( 10.20 ms per token, 98.03 tokens per second) 9.14.945.098 I slot print_timing: id 0 | task 4960 | eval time = 53.83 ms / 2 tokens ( 53.83 ms per token, 18.58 tokens per second) 9.14.945.098 I slot print_timing: id 0 | task 4960 | total time = 1206.56 ms / 115 tokens 9.14.945.099 I slot print_timing: id 0 | task 4960 | graphs reused = 3659 9.14.945.099 I slot print_timing: id 0 | task 4960 | graph reallocs = 0 / 0 (same size) / (changed size) 9.14.945.137 I slot release: id 0 | task 4960 | stop processing: n_tokens = 717, truncated = 0 9.14.945.287 I slot print_timing: id 1 | task 4959 | prompt eval time = 1149.68 ms / 114 tokens ( 10.08 ms per token, 99.16 tokens per second) 9.14.945.293 I slot print_timing: id 1 | task 4959 | eval time = 53.84 ms / 2 tokens ( 53.84 ms per token, 18.57 tokens per second) 9.14.945.293 I slot print_timing: id 1 | task 4959 | total time = 1203.52 ms / 116 tokens 9.14.945.294 I slot print_timing: id 1 | task 4959 | graphs reused = 3659 9.14.945.294 I slot print_timing: id 1 | task 4959 | graph reallocs = 0 / 0 (same size) / (changed size) 9.14.945.319 I slot release: id 1 | task 4959 | stop processing: n_tokens = 718, truncated = 0 9.14.945.490 I slot print_timing: id 2 | task 4961 | prompt eval time = 1146.68 ms / 106 tokens ( 10.82 ms per token, 92.44 tokens per second) 9.14.945.495 I slot print_timing: id 2 | task 4961 | eval time = 53.85 ms / 2 tokens ( 53.85 ms per token, 18.57 tokens per second) 9.14.945.496 I slot print_timing: id 2 | task 4961 | total time = 1200.53 ms / 108 tokens 9.14.945.496 I slot print_timing: id 2 | task 4961 | graphs reused = 3659 9.14.945.496 I slot print_timing: id 2 | task 4961 | graph reallocs = 0 / 0 (same size) / (changed size) 9.14.945.520 I slot release: id 2 | task 4961 | stop processing: n_tokens = 710, truncated = 0 9.14.945.694 I slot print_timing: id 3 | task 4962 | prompt eval time = 1143.66 ms / 148 tokens ( 7.73 ms per token, 129.41 tokens per second) 9.14.945.696 I slot print_timing: id 3 | task 4962 | eval time = 53.88 ms / 2 tokens ( 53.88 ms per token, 18.56 tokens per second) 9.14.945.697 I slot print_timing: id 3 | task 4962 | total time = 1197.54 ms / 150 tokens 9.14.945.697 I slot print_timing: id 3 | task 4962 | graphs reused = 3659 9.14.945.697 I slot print_timing: id 3 | task 4962 | graph reallocs = 0 / 0 (same size) / (changed size) 9.14.945.716 I slot release: id 3 | task 4962 | stop processing: n_tokens = 752, truncated = 0 9.14.954.065 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 717, t_last = 390388535267 9.14.954.110 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 289.638 MiB) 9.14.954.115 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 286.099 MiB) 9.14.964.125 I slot launch_slot_: id 0 | task 4966 | processing task, is_child = 0 9.14.964.169 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.282 MiB) 9.14.971.793 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.712 MiB) 9.14.979.549 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.967 MiB) 9.14.987.286 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 718, t_last = 390388535449 9.14.987.378 I slot launch_slot_: id 1 | task 4967 | processing task, is_child = 0 9.14.987.454 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 710, t_last = 390388535650 9.14.987.521 I slot launch_slot_: id 2 | task 4968 | processing task, is_child = 0 9.14.987.563 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 752, t_last = 390388535846 9.14.987.621 I slot launch_slot_: id 3 | task 4969 | processing task, is_child = 0 9.18.443.128 I slot print_timing: id 0 | task 4966 | prompt processing, n_tokens = 364, progress = 0.41, t = 3.46 s / 105.34 tokens per second 9.18.513.458 I slot print_timing: id 1 | task 4967 | prompt processing, n_tokens = 380, progress = 0.42, t = 3.46 s / 109.97 tokens per second 9.18.517.370 I slot print_timing: id 2 | task 4968 | prompt processing, n_tokens = 566, progress = 0.52, t = 3.46 s / 163.80 tokens per second 9.18.519.260 I slot print_timing: id 3 | task 4969 | prompt processing, n_tokens = 575, progress = 0.53, t = 3.46 s / 166.41 tokens per second 9.21.164.675 I slot print_timing: id 0 | task 4966 | prompt processing, n_tokens = 762, progress = 0.87, t = 6.18 s / 123.36 tokens per second 9.21.272.457 I slot print_timing: id 1 | task 4967 | prompt processing, n_tokens = 762, progress = 0.85, t = 6.18 s / 123.36 tokens per second 9.21.274.796 I slot print_timing: id 2 | task 4968 | prompt processing, n_tokens = 905, progress = 0.84, t = 6.18 s / 146.51 tokens per second 9.21.276.701 I slot print_timing: id 3 | task 4969 | prompt processing, n_tokens = 905, progress = 0.83, t = 6.18 s / 146.51 tokens per second 9.22.517.988 I slot print_timing: id 0 | task 4966 | prompt processing, n_tokens = 876, progress = 1.00, t = 7.53 s / 116.33 tokens per second 9.22.588.862 I slot print_timing: id 1 | task 4967 | prompt processing, n_tokens = 892, progress = 1.00, t = 7.53 s / 118.45 tokens per second 9.22.592.550 I slot print_timing: id 2 | task 4968 | prompt processing, n_tokens = 1078, progress = 1.00, t = 7.53 s / 143.16 tokens per second 9.22.594.553 I slot print_timing: id 3 | task 4969 | prompt processing, n_tokens = 1087, progress = 1.00, t = 7.53 s / 144.35 tokens per second 9.22.775.295 I slot print_timing: id 0 | task 4966 | prompt eval time = 7733.81 ms / 880 tokens ( 8.79 ms per token, 113.79 tokens per second) 9.22.775.300 I slot print_timing: id 0 | task 4966 | eval time = 53.85 ms / 2 tokens ( 53.85 ms per token, 18.57 tokens per second) 9.22.775.301 I slot print_timing: id 0 | task 4966 | total time = 7787.66 ms / 882 tokens 9.22.775.301 I slot print_timing: id 0 | task 4966 | graphs reused = 3659 9.22.775.302 I slot print_timing: id 0 | task 4966 | graph reallocs = 0 / 0 (same size) / (changed size) 9.22.775.343 I slot release: id 0 | task 4966 | stop processing: n_tokens = 881, truncated = 0 9.22.775.491 I slot print_timing: id 1 | task 4967 | prompt eval time = 7733.91 ms / 896 tokens ( 8.63 ms per token, 115.85 tokens per second) 9.22.775.493 I slot print_timing: id 1 | task 4967 | eval time = 53.89 ms / 2 tokens ( 53.89 ms per token, 18.56 tokens per second) 9.22.775.494 I slot print_timing: id 1 | task 4967 | total time = 7787.80 ms / 898 tokens 9.22.775.494 I slot print_timing: id 1 | task 4967 | graphs reused = 3659 9.22.775.494 I slot print_timing: id 1 | task 4967 | graph reallocs = 0 / 0 (same size) / (changed size) 9.22.775.520 I slot release: id 1 | task 4967 | stop processing: n_tokens = 897, truncated = 0 9.22.775.695 I slot print_timing: id 2 | task 4968 | prompt eval time = 7734.03 ms / 1082 tokens ( 7.15 ms per token, 139.90 tokens per second) 9.22.775.699 I slot print_timing: id 2 | task 4968 | eval time = 53.92 ms / 2 tokens ( 53.92 ms per token, 18.54 tokens per second) 9.22.775.700 I slot print_timing: id 2 | task 4968 | total time = 7787.95 ms / 1084 tokens 9.22.775.700 I slot print_timing: id 2 | task 4968 | graphs reused = 3659 9.22.775.701 I slot print_timing: id 2 | task 4968 | graph reallocs = 0 / 0 (same size) / (changed size) 9.22.775.729 I slot release: id 2 | task 4968 | stop processing: n_tokens = 1083, truncated = 0 9.22.775.910 I slot print_timing: id 3 | task 4969 | prompt eval time = 7734.19 ms / 1091 tokens ( 7.09 ms per token, 141.06 tokens per second) 9.22.775.913 I slot print_timing: id 3 | task 4969 | eval time = 53.92 ms / 2 tokens ( 53.92 ms per token, 18.55 tokens per second) 9.22.775.914 I slot print_timing: id 3 | task 4969 | total time = 7788.11 ms / 1093 tokens 9.22.775.914 I slot print_timing: id 3 | task 4969 | graphs reused = 3659 9.22.775.914 I slot print_timing: id 3 | task 4969 | graph reallocs = 0 / 0 (same size) / (changed size) 9.22.775.936 I slot release: id 3 | task 4969 | stop processing: n_tokens = 1092, truncated = 0 9.22.783.977 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 9.22.784.013 I slot launch_slot_: id 3 | task 4977 | processing task, is_child = 0 9.22.784.062 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.536 MiB) 9.22.791.927 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.263 MiB) 9.22.799.924 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 329.690 MiB) 9.22.808.407 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.904 (> 0.100 thold), f_keep = 0.901 9.22.808.463 I slot launch_slot_: id 2 | task 4978 | processing task, is_child = 0 9.22.808.553 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 881, t_last = 390396365473 9.22.810.603 I slot launch_slot_: id 0 | task 4979 | processing task, is_child = 0 9.22.810.655 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 897, t_last = 390396365650 9.22.810.716 I slot launch_slot_: id 1 | task 4980 | processing task, is_child = 0 9.25.352.656 I slot print_timing: id 0 | task 4979 | prompt eval time = 2040.85 ms / 180 tokens ( 11.34 ms per token, 88.20 tokens per second) 9.25.352.662 I slot print_timing: id 0 | task 4979 | eval time = 501.07 ms / 2 tokens ( 501.07 ms per token, 2.00 tokens per second) 9.25.352.662 I slot print_timing: id 0 | task 4979 | total time = 2541.93 ms / 182 tokens 9.25.352.663 I slot print_timing: id 0 | task 4979 | graphs reused = 3659 9.25.352.663 I slot print_timing: id 0 | task 4979 | graph reallocs = 0 / 0 (same size) / (changed size) 9.25.352.704 I slot release: id 0 | task 4979 | stop processing: n_tokens = 1086, truncated = 0 9.25.352.854 I slot print_timing: id 2 | task 4978 | prompt eval time = 2037.76 ms / 175 tokens ( 11.64 ms per token, 85.88 tokens per second) 9.25.352.856 I slot print_timing: id 2 | task 4978 | eval time = 501.09 ms / 2 tokens ( 501.09 ms per token, 2.00 tokens per second) 9.25.352.856 I slot print_timing: id 2 | task 4978 | total time = 2538.84 ms / 177 tokens 9.25.352.857 I slot print_timing: id 2 | task 4978 | graphs reused = 3659 9.25.352.857 I slot print_timing: id 2 | task 4978 | graph reallocs = 0 / 0 (same size) / (changed size) 9.25.352.883 I slot release: id 2 | task 4978 | stop processing: n_tokens = 1081, truncated = 0 9.25.353.089 I slot print_timing: id 3 | task 4977 | prompt eval time = 2034.80 ms / 166 tokens ( 12.26 ms per token, 81.58 tokens per second) 9.25.353.092 I slot print_timing: id 3 | task 4977 | eval time = 501.08 ms / 2 tokens ( 501.08 ms per token, 2.00 tokens per second) 9.25.353.093 I slot print_timing: id 3 | task 4977 | total time = 2535.88 ms / 168 tokens 9.25.353.093 I slot print_timing: id 3 | task 4977 | graphs reused = 3659 9.25.353.093 I slot print_timing: id 3 | task 4977 | graph reallocs = 0 / 0 (same size) / (changed size) 9.25.353.116 I slot release: id 3 | task 4977 | stop processing: n_tokens = 1072, truncated = 0 9.25.975.231 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.911 (> 0.100 thold), f_keep = 0.900 9.25.975.282 I slot launch_slot_: id 0 | task 4986 | processing task, is_child = 0 9.26.379.261 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 334.461 MiB) 9.26.387.852 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.904 9.26.387.906 I slot launch_slot_: id 2 | task 4987 | processing task, is_child = 0 9.26.387.959 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.898 (> 0.100 thold), f_keep = 0.911 9.26.387.981 I slot launch_slot_: id 3 | task 4988 | processing task, is_child = 0 9.26.391.233 I slot print_timing: id 1 | task 4980 | prompt processing, n_tokens = 1075, progress = 1.00, t = 3.16 s / 340.05 tokens per second 9.27.711.132 I slot print_timing: id 1 | task 4980 | prompt eval time = 4747.89 ms / 1079 tokens ( 4.40 ms per token, 227.26 tokens per second) 9.27.711.137 I slot print_timing: id 1 | task 4980 | eval time = 149.29 ms / 2 tokens ( 149.29 ms per token, 6.70 tokens per second) 9.27.711.138 I slot print_timing: id 1 | task 4980 | total time = 4897.18 ms / 1081 tokens 9.27.711.138 I slot print_timing: id 1 | task 4980 | graphs reused = 3659 9.27.711.139 I slot print_timing: id 1 | task 4980 | graph reallocs = 0 / 0 (same size) / (changed size) 9.27.711.181 I slot release: id 1 | task 4980 | stop processing: n_tokens = 1080, truncated = 0 9.27.768.228 I slot print_timing: id 0 | task 4986 | prompt eval time = 1323.00 ms / 168 tokens ( 7.87 ms per token, 126.98 tokens per second) 9.27.768.231 I slot print_timing: id 0 | task 4986 | eval time = 57.23 ms / 2 tokens ( 57.23 ms per token, 17.47 tokens per second) 9.27.768.231 I slot print_timing: id 0 | task 4986 | total time = 1380.22 ms / 170 tokens 9.27.768.232 I slot print_timing: id 0 | task 4986 | graphs reused = 3659 9.27.768.232 I slot print_timing: id 0 | task 4986 | graph reallocs = 0 / 0 (same size) / (changed size) 9.27.768.275 I slot release: id 0 | task 4986 | stop processing: n_tokens = 1074, truncated = 0 9.27.768.421 I slot print_timing: id 2 | task 4987 | prompt eval time = 1318.18 ms / 177 tokens ( 7.45 ms per token, 134.28 tokens per second) 9.27.768.423 I slot print_timing: id 2 | task 4987 | eval time = 57.04 ms / 2 tokens ( 57.04 ms per token, 17.53 tokens per second) 9.27.768.424 I slot print_timing: id 2 | task 4987 | total time = 1375.22 ms / 179 tokens 9.27.768.424 I slot print_timing: id 2 | task 4987 | graphs reused = 3659 9.27.768.424 I slot print_timing: id 2 | task 4987 | graph reallocs = 0 / 0 (same size) / (changed size) 9.27.768.453 I slot release: id 2 | task 4987 | stop processing: n_tokens = 1083, truncated = 0 9.27.768.634 I slot print_timing: id 3 | task 4988 | prompt eval time = 1315.20 ms / 183 tokens ( 7.19 ms per token, 139.14 tokens per second) 9.27.768.638 I slot print_timing: id 3 | task 4988 | eval time = 57.01 ms / 2 tokens ( 57.01 ms per token, 17.54 tokens per second) 9.27.768.638 I slot print_timing: id 3 | task 4988 | total time = 1372.21 ms / 185 tokens 9.27.768.638 I slot print_timing: id 3 | task 4988 | graphs reused = 3659 9.27.768.639 I slot print_timing: id 3 | task 4988 | graph reallocs = 0 / 0 (same size) / (changed size) 9.27.768.664 I slot release: id 3 | task 4988 | stop processing: n_tokens = 1089, truncated = 0 9.27.768.670 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.902 (> 0.100 thold), f_keep = 0.910 9.27.768.736 I slot launch_slot_: id 0 | task 4992 | processing task, is_child = 0 9.27.768.803 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 329.710 MiB) 9.27.776.860 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 329.905 MiB) 9.27.786.088 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 330.942 MiB) 9.27.794.026 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.905 9.27.794.074 I slot launch_slot_: id 1 | task 4993 | processing task, is_child = 0 9.27.794.175 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.909 (> 0.100 thold), f_keep = 0.902 9.27.794.198 I slot launch_slot_: id 2 | task 4994 | processing task, is_child = 0 9.27.794.254 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.897 9.27.794.274 I slot launch_slot_: id 3 | task 4995 | processing task, is_child = 0 9.29.301.405 I slot print_timing: id 0 | task 4992 | prompt eval time = 1453.01 ms / 178 tokens ( 8.16 ms per token, 122.50 tokens per second) 9.29.301.410 I slot print_timing: id 0 | task 4992 | eval time = 54.11 ms / 2 tokens ( 54.11 ms per token, 18.48 tokens per second) 9.29.301.410 I slot print_timing: id 0 | task 4992 | total time = 1507.12 ms / 180 tokens 9.29.301.411 I slot print_timing: id 0 | task 4992 | graphs reused = 3659 9.29.301.411 I slot print_timing: id 0 | task 4992 | graph reallocs = 0 / 0 (same size) / (changed size) 9.29.301.453 I slot release: id 0 | task 4992 | stop processing: n_tokens = 1084, truncated = 0 9.29.301.608 I slot print_timing: id 1 | task 4993 | prompt eval time = 1449.86 ms / 171 tokens ( 8.48 ms per token, 117.94 tokens per second) 9.29.301.612 I slot print_timing: id 1 | task 4993 | eval time = 54.12 ms / 2 tokens ( 54.12 ms per token, 18.48 tokens per second) 9.29.301.612 I slot print_timing: id 1 | task 4993 | total time = 1503.98 ms / 173 tokens 9.29.301.612 I slot print_timing: id 1 | task 4993 | graphs reused = 3659 9.29.301.613 I slot print_timing: id 1 | task 4993 | graph reallocs = 0 / 0 (same size) / (changed size) 9.29.301.639 I slot release: id 1 | task 4993 | stop processing: n_tokens = 1077, truncated = 0 9.29.301.809 I slot print_timing: id 2 | task 4994 | prompt eval time = 1446.77 ms / 170 tokens ( 8.51 ms per token, 117.50 tokens per second) 9.29.301.811 I slot print_timing: id 2 | task 4994 | eval time = 54.11 ms / 2 tokens ( 54.11 ms per token, 18.48 tokens per second) 9.29.301.811 I slot print_timing: id 2 | task 4994 | total time = 1500.88 ms / 172 tokens 9.29.301.812 I slot print_timing: id 2 | task 4994 | graphs reused = 3659 9.29.301.812 I slot print_timing: id 2 | task 4994 | graph reallocs = 0 / 0 (same size) / (changed size) 9.29.301.841 I slot release: id 2 | task 4994 | stop processing: n_tokens = 1076, truncated = 0 9.29.302.003 I slot print_timing: id 3 | task 4995 | prompt eval time = 1443.64 ms / 175 tokens ( 8.25 ms per token, 121.22 tokens per second) 9.29.302.006 I slot print_timing: id 3 | task 4995 | eval time = 54.11 ms / 2 tokens ( 54.11 ms per token, 18.48 tokens per second) 9.29.302.006 I slot print_timing: id 3 | task 4995 | total time = 1497.75 ms / 177 tokens 9.29.302.006 I slot print_timing: id 3 | task 4995 | graphs reused = 3659 9.29.302.006 I slot print_timing: id 3 | task 4995 | graph reallocs = 0 / 0 (same size) / (changed size) 9.29.302.027 I slot release: id 3 | task 4995 | stop processing: n_tokens = 1081, truncated = 0 9.29.309.924 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.901 9.29.309.951 I slot launch_slot_: id 0 | task 4999 | processing task, is_child = 0 9.29.310.011 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.704 MiB) 9.29.317.771 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 330.492 MiB) 9.29.330.463 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.880 MiB) 9.29.342.941 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1077, t_last = 390402891769 9.29.343.053 I slot launch_slot_: id 1 | task 5000 | processing task, is_child = 0 9.29.343.178 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.908 9.29.343.198 I slot launch_slot_: id 2 | task 5001 | processing task, is_child = 0 9.29.343.257 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1081, t_last = 390402892157 9.29.343.324 I slot launch_slot_: id 3 | task 5002 | processing task, is_child = 0 9.32.538.707 I slot print_timing: id 0 | task 4999 | prompt eval time = 2522.85 ms / 174 tokens ( 14.50 ms per token, 68.97 tokens per second) 9.32.538.712 I slot print_timing: id 0 | task 4999 | eval time = 672.52 ms / 2 tokens ( 672.52 ms per token, 1.49 tokens per second) 9.32.538.713 I slot print_timing: id 0 | task 4999 | total time = 3195.37 ms / 176 tokens 9.32.538.713 I slot print_timing: id 0 | task 4999 | graphs reused = 3659 9.32.538.714 I slot print_timing: id 0 | task 4999 | graph reallocs = 0 / 0 (same size) / (changed size) 9.32.538.753 I slot release: id 0 | task 4999 | stop processing: n_tokens = 1080, truncated = 0 9.32.538.952 I slot print_timing: id 2 | task 5001 | prompt eval time = 2519.78 ms / 173 tokens ( 14.57 ms per token, 68.66 tokens per second) 9.32.538.955 I slot print_timing: id 2 | task 5001 | eval time = 672.52 ms / 2 tokens ( 672.52 ms per token, 1.49 tokens per second) 9.32.538.955 I slot print_timing: id 2 | task 5001 | total time = 3192.30 ms / 175 tokens 9.32.538.955 I slot print_timing: id 2 | task 5001 | graphs reused = 3659 9.32.538.956 I slot print_timing: id 2 | task 5001 | graph reallocs = 0 / 0 (same size) / (changed size) 9.32.538.988 I slot release: id 2 | task 5001 | stop processing: n_tokens = 1079, truncated = 0 9.32.538.995 I slot print_timing: id 1 | task 5000 | prompt processing, n_tokens = 501, progress = 0.49, t = 3.19 s / 156.96 tokens per second 9.32.542.291 I slot print_timing: id 3 | task 5002 | prompt processing, n_tokens = 515, progress = 0.50, t = 3.19 s / 161.51 tokens per second 9.33.201.959 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1080, t_last = 390406128883 9.33.202.034 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 327.539 MiB) 9.33.846.502 I slot launch_slot_: id 0 | task 5007 | processing task, is_child = 0 9.33.846.585 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 330.218 MiB) 9.33.859.454 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1079, t_last = 390406129118 9.33.859.550 I slot launch_slot_: id 2 | task 5008 | processing task, is_child = 0 9.33.859.638 I slot print_timing: id 1 | task 5000 | prompt processing, n_tokens = 878, progress = 0.86, t = 3.86 s / 227.73 tokens per second 9.33.861.619 I slot print_timing: id 3 | task 5002 | prompt processing, n_tokens = 878, progress = 0.85, t = 3.85 s / 227.93 tokens per second 9.35.528.826 I slot print_timing: id 1 | task 5000 | prompt processing, n_tokens = 1013, progress = 1.00, t = 5.97 s / 169.59 tokens per second 9.35.532.889 I slot print_timing: id 3 | task 5002 | prompt processing, n_tokens = 1027, progress = 1.00, t = 5.97 s / 172.03 tokens per second 9.37.310.480 I slot print_timing: id 1 | task 5000 | prompt eval time = 7098.98 ms / 1017 tokens ( 6.98 ms per token, 143.26 tokens per second) 9.37.310.484 I slot print_timing: id 1 | task 5000 | eval time = 864.92 ms / 2 tokens ( 864.92 ms per token, 1.16 tokens per second) 9.37.310.485 I slot print_timing: id 1 | task 5000 | total time = 7963.89 ms / 1019 tokens 9.37.310.485 I slot print_timing: id 1 | task 5000 | graphs reused = 3659 9.37.310.486 I slot print_timing: id 1 | task 5000 | graph reallocs = 0 / 0 (same size) / (changed size) 9.37.310.531 I slot release: id 1 | task 5000 | stop processing: n_tokens = 1018, truncated = 0 9.37.310.744 I slot print_timing: id 3 | task 5002 | prompt eval time = 7095.92 ms / 1031 tokens ( 6.88 ms per token, 145.29 tokens per second) 9.37.310.747 I slot print_timing: id 3 | task 5002 | eval time = 864.98 ms / 2 tokens ( 864.98 ms per token, 1.16 tokens per second) 9.37.310.747 I slot print_timing: id 3 | task 5002 | total time = 7960.90 ms / 1033 tokens 9.37.310.748 I slot print_timing: id 3 | task 5002 | graphs reused = 3659 9.37.310.748 I slot print_timing: id 3 | task 5002 | graph reallocs = 0 / 0 (same size) / (changed size) 9.37.310.781 I slot release: id 3 | task 5002 | stop processing: n_tokens = 1032, truncated = 0 9.37.310.789 I slot print_timing: id 0 | task 5007 | prompt processing, n_tokens = 590, progress = 0.53, t = 3.45 s / 170.98 tokens per second 9.37.314.604 I slot print_timing: id 2 | task 5008 | prompt processing, n_tokens = 555, progress = 0.52, t = 3.45 s / 160.93 tokens per second 9.37.853.423 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.880 (> 0.100 thold), f_keep = 0.890 9.37.853.488 I slot launch_slot_: id 1 | task 5013 | processing task, is_child = 0 9.37.853.548 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 329.123 MiB) 9.38.450.791 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.867 (> 0.100 thold), f_keep = 0.878 9.38.450.850 I slot launch_slot_: id 3 | task 5014 | processing task, is_child = 0 9.38.450.857 I slot print_timing: id 0 | task 5007 | prompt processing, n_tokens = 878, progress = 0.79, t = 3.99 s / 219.84 tokens per second 9.38.455.966 I slot print_timing: id 2 | task 5008 | prompt processing, n_tokens = 878, progress = 0.82, t = 3.99 s / 219.95 tokens per second 9.40.032.623 I slot print_timing: id 0 | task 5007 | prompt processing, n_tokens = 1102, progress = 1.00, t = 6.17 s / 178.52 tokens per second 9.40.208.024 I slot print_timing: id 2 | task 5008 | prompt processing, n_tokens = 1067, progress = 1.00, t = 6.17 s / 172.90 tokens per second 9.40.391.421 I slot print_timing: id 0 | task 5007 | prompt eval time = 6477.58 ms / 1106 tokens ( 5.86 ms per token, 170.74 tokens per second) 9.40.391.425 I slot print_timing: id 0 | task 5007 | eval time = 54.28 ms / 2 tokens ( 54.28 ms per token, 18.42 tokens per second) 9.40.391.426 I slot print_timing: id 0 | task 5007 | total time = 6531.86 ms / 1108 tokens 9.40.391.426 I slot print_timing: id 0 | task 5007 | graphs reused = 3659 9.40.391.427 I slot print_timing: id 0 | task 5007 | graph reallocs = 0 / 0 (same size) / (changed size) 9.40.391.478 I slot release: id 0 | task 5007 | stop processing: n_tokens = 1107, truncated = 0 9.40.391.629 I slot print_timing: id 1 | task 5013 | prompt eval time = 1884.57 ms / 152 tokens ( 12.40 ms per token, 80.66 tokens per second) 9.40.391.632 I slot print_timing: id 1 | task 5013 | eval time = 54.32 ms / 2 tokens ( 54.32 ms per token, 18.41 tokens per second) 9.40.391.633 I slot print_timing: id 1 | task 5013 | total time = 1938.89 ms / 154 tokens 9.40.391.633 I slot print_timing: id 1 | task 5013 | graphs reused = 3659 9.40.391.633 I slot print_timing: id 1 | task 5013 | graph reallocs = 0 / 0 (same size) / (changed size) 9.40.391.661 I slot release: id 1 | task 5013 | stop processing: n_tokens = 1031, truncated = 0 9.40.391.830 I slot print_timing: id 2 | task 5008 | prompt eval time = 6475.97 ms / 1071 tokens ( 6.05 ms per token, 165.38 tokens per second) 9.40.391.832 I slot print_timing: id 2 | task 5008 | eval time = 54.32 ms / 2 tokens ( 54.32 ms per token, 18.41 tokens per second) 9.40.391.832 I slot print_timing: id 2 | task 5008 | total time = 6530.29 ms / 1073 tokens 9.40.391.832 I slot print_timing: id 2 | task 5008 | graphs reused = 3659 9.40.391.833 I slot print_timing: id 2 | task 5008 | graph reallocs = 0 / 0 (same size) / (changed size) 9.40.391.859 I slot release: id 2 | task 5008 | stop processing: n_tokens = 1072, truncated = 0 9.40.392.016 I slot print_timing: id 3 | task 5014 | prompt eval time = 1879.87 ms / 167 tokens ( 11.26 ms per token, 88.84 tokens per second) 9.40.392.018 I slot print_timing: id 3 | task 5014 | eval time = 54.29 ms / 2 tokens ( 54.29 ms per token, 18.42 tokens per second) 9.40.392.018 I slot print_timing: id 3 | task 5014 | total time = 1934.16 ms / 169 tokens 9.40.392.018 I slot print_timing: id 3 | task 5014 | graphs reused = 3659 9.40.392.018 I slot print_timing: id 3 | task 5014 | graph reallocs = 0 / 0 (same size) / (changed size) 9.40.392.040 I slot release: id 3 | task 5014 | stop processing: n_tokens = 1046, truncated = 0 9.40.400.193 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1107, t_last = 390413981608 9.40.400.252 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 330.726 MiB) 9.40.413.332 I slot launch_slot_: id 0 | task 5018 | processing task, is_child = 0 9.40.413.385 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.791 MiB) 9.40.421.393 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.145 MiB) 9.40.429.302 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.478 MiB) 9.40.437.161 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1031, t_last = 390413981791 9.40.437.254 I slot launch_slot_: id 1 | task 5019 | processing task, is_child = 0 9.40.437.355 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1072, t_last = 390413981989 9.40.437.428 I slot launch_slot_: id 2 | task 5020 | processing task, is_child = 0 9.40.437.479 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1046, t_last = 390413982170 9.40.437.556 I slot launch_slot_: id 3 | task 5021 | processing task, is_child = 0 9.44.563.978 I slot print_timing: id 0 | task 5018 | prompt processing, n_tokens = 623, progress = 0.83, t = 4.13 s / 150.98 tokens per second 9.44.644.834 I slot print_timing: id 1 | task 5019 | prompt processing, n_tokens = 623, progress = 0.85, t = 4.13 s / 150.98 tokens per second 9.44.647.983 I slot print_timing: id 2 | task 5020 | prompt processing, n_tokens = 623, progress = 0.84, t = 4.13 s / 150.99 tokens per second 9.44.650.168 I slot print_timing: id 3 | task 5021 | prompt processing, n_tokens = 281, progress = 0.35, t = 4.13 s / 68.10 tokens per second 9.45.663.534 I slot print_timing: id 0 | task 5018 | prompt processing, n_tokens = 749, progress = 0.99, t = 5.23 s / 143.32 tokens per second 9.46.127.430 I slot print_timing: id 1 | task 5019 | prompt processing, n_tokens = 725, progress = 0.99, t = 5.23 s / 138.73 tokens per second 9.46.129.665 I slot print_timing: id 2 | task 5020 | prompt processing, n_tokens = 736, progress = 0.99, t = 5.23 s / 140.84 tokens per second 9.46.131.880 I slot print_timing: id 3 | task 5021 | prompt processing, n_tokens = 623, progress = 0.78, t = 5.23 s / 119.22 tokens per second 9.46.639.320 I slot print_timing: id 3 | task 5021 | prompt processing, n_tokens = 793, progress = 0.99, t = 6.20 s / 127.89 tokens per second 9.46.732.744 I slot print_timing: id 0 | task 5018 | prompt eval time = 6201.30 ms / 753 tokens ( 8.24 ms per token, 121.43 tokens per second) 9.46.732.746 I slot print_timing: id 0 | task 5018 | eval time = 93.87 ms / 2 tokens ( 93.87 ms per token, 10.65 tokens per second) 9.46.732.747 I slot print_timing: id 0 | task 5018 | total time = 6295.17 ms / 755 tokens 9.46.732.747 I slot print_timing: id 0 | task 5018 | graphs reused = 3659 9.46.732.748 I slot print_timing: id 0 | task 5018 | graph reallocs = 0 / 0 (same size) / (changed size) 9.46.732.790 I slot release: id 0 | task 5018 | stop processing: n_tokens = 754, truncated = 0 9.46.732.933 I slot print_timing: id 1 | task 5019 | prompt eval time = 6201.43 ms / 729 tokens ( 8.51 ms per token, 117.55 tokens per second) 9.46.732.936 I slot print_timing: id 1 | task 5019 | eval time = 93.85 ms / 2 tokens ( 93.85 ms per token, 10.66 tokens per second) 9.46.732.936 I slot print_timing: id 1 | task 5019 | total time = 6295.27 ms / 731 tokens 9.46.732.937 I slot print_timing: id 1 | task 5019 | graphs reused = 3659 9.46.732.937 I slot print_timing: id 1 | task 5019 | graph reallocs = 0 / 0 (same size) / (changed size) 9.46.732.960 I slot release: id 1 | task 5019 | stop processing: n_tokens = 730, truncated = 0 9.46.733.132 I slot print_timing: id 2 | task 5020 | prompt eval time = 6201.58 ms / 740 tokens ( 8.38 ms per token, 119.32 tokens per second) 9.46.733.134 I slot print_timing: id 2 | task 5020 | eval time = 93.82 ms / 2 tokens ( 93.82 ms per token, 10.66 tokens per second) 9.46.733.134 I slot print_timing: id 2 | task 5020 | total time = 6295.40 ms / 742 tokens 9.46.733.134 I slot print_timing: id 2 | task 5020 | graphs reused = 3659 9.46.733.135 I slot print_timing: id 2 | task 5020 | graph reallocs = 0 / 0 (same size) / (changed size) 9.46.733.160 I slot release: id 2 | task 5020 | stop processing: n_tokens = 741, truncated = 0 9.46.756.259 I slot print_timing: id 3 | task 5021 | prompt eval time = 6295.61 ms / 797 tokens ( 7.90 ms per token, 126.60 tokens per second) 9.46.756.263 I slot print_timing: id 3 | task 5021 | eval time = 22.84 ms / 2 tokens ( 22.84 ms per token, 43.79 tokens per second) 9.46.756.263 I slot print_timing: id 3 | task 5021 | total time = 6318.44 ms / 799 tokens 9.46.756.264 I slot print_timing: id 3 | task 5021 | graphs reused = 3659 9.46.756.264 I slot print_timing: id 3 | task 5021 | graph reallocs = 0 / 0 (same size) / (changed size) 9.46.756.304 I slot release: id 3 | task 5021 | stop processing: n_tokens = 798, truncated = 0 9.46.756.312 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.873 (> 0.100 thold), f_keep = 0.863 9.46.756.348 I slot launch_slot_: id 0 | task 5029 | processing task, is_child = 0 9.46.756.402 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 327.911 MiB) 9.46.764.104 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 327.969 MiB) 9.46.771.775 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.067 MiB) 9.46.779.335 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.881 9.46.779.392 I slot launch_slot_: id 2 | task 5030 | processing task, is_child = 0 9.46.779.476 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.892 9.46.779.499 I slot launch_slot_: id 1 | task 5031 | processing task, is_child = 0 9.46.779.550 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 9.46.779.581 I slot launch_slot_: id 3 | task 5032 | processing task, is_child = 0 9.47.991.414 I slot print_timing: id 0 | task 5029 | prompt eval time = 1158.05 ms / 123 tokens ( 9.42 ms per token, 106.21 tokens per second) 9.47.991.417 I slot print_timing: id 0 | task 5029 | eval time = 53.77 ms / 2 tokens ( 53.77 ms per token, 18.60 tokens per second) 9.47.991.417 I slot print_timing: id 0 | task 5029 | total time = 1211.82 ms / 125 tokens 9.47.991.417 I slot print_timing: id 0 | task 5029 | graphs reused = 3659 9.47.991.418 I slot print_timing: id 0 | task 5029 | graph reallocs = 0 / 0 (same size) / (changed size) 9.47.991.456 I slot release: id 0 | task 5029 | stop processing: n_tokens = 747, truncated = 0 9.47.991.606 I slot print_timing: id 1 | task 5031 | prompt eval time = 1154.95 ms / 110 tokens ( 10.50 ms per token, 95.24 tokens per second) 9.47.991.608 I slot print_timing: id 1 | task 5031 | eval time = 53.80 ms / 2 tokens ( 53.80 ms per token, 18.59 tokens per second) 9.47.991.608 I slot print_timing: id 1 | task 5031 | total time = 1208.76 ms / 112 tokens 9.47.991.608 I slot print_timing: id 1 | task 5031 | graphs reused = 3659 9.47.991.609 I slot print_timing: id 1 | task 5031 | graph reallocs = 0 / 0 (same size) / (changed size) 9.47.991.632 I slot release: id 1 | task 5031 | stop processing: n_tokens = 734, truncated = 0 9.47.991.792 I slot print_timing: id 2 | task 5030 | prompt eval time = 1151.92 ms / 116 tokens ( 9.93 ms per token, 100.70 tokens per second) 9.47.991.793 I slot print_timing: id 2 | task 5030 | eval time = 53.79 ms / 2 tokens ( 53.79 ms per token, 18.59 tokens per second) 9.47.991.794 I slot print_timing: id 2 | task 5030 | total time = 1205.71 ms / 118 tokens 9.47.991.794 I slot print_timing: id 2 | task 5030 | graphs reused = 3659 9.47.991.794 I slot print_timing: id 2 | task 5030 | graph reallocs = 0 / 0 (same size) / (changed size) 9.47.991.819 I slot release: id 2 | task 5030 | stop processing: n_tokens = 740, truncated = 0 9.47.991.985 I slot print_timing: id 3 | task 5032 | prompt eval time = 1148.93 ms / 132 tokens ( 8.70 ms per token, 114.89 tokens per second) 9.47.991.989 I slot print_timing: id 3 | task 5032 | eval time = 53.76 ms / 2 tokens ( 53.76 ms per token, 18.60 tokens per second) 9.47.991.990 I slot print_timing: id 3 | task 5032 | total time = 1202.69 ms / 134 tokens 9.47.991.990 I slot print_timing: id 3 | task 5032 | graphs reused = 3659 9.47.991.990 I slot print_timing: id 3 | task 5032 | graph reallocs = 0 / 0 (same size) / (changed size) 9.47.992.009 I slot release: id 3 | task 5032 | stop processing: n_tokens = 756, truncated = 0 9.47.999.486 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.871 (> 0.100 thold), f_keep = 0.871 9.47.999.513 I slot launch_slot_: id 0 | task 5036 | processing task, is_child = 0 9.47.999.560 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.087 MiB) 9.48.007.353 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.106 MiB) 9.48.014.888 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 327.950 MiB) 9.48.022.398 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 734, t_last = 390421581762 9.48.022.494 I slot launch_slot_: id 1 | task 5037 | processing task, is_child = 0 9.48.022.570 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 740, t_last = 390421581949 9.48.022.640 I slot launch_slot_: id 2 | task 5038 | processing task, is_child = 0 9.48.022.684 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 756, t_last = 390421582139 9.48.022.739 I slot launch_slot_: id 3 | task 5039 | processing task, is_child = 0 9.50.910.940 I slot print_timing: id 0 | task 5036 | prompt eval time = 2096.28 ms / 124 tokens ( 16.91 ms per token, 59.15 tokens per second) 9.50.910.947 I slot print_timing: id 0 | task 5036 | eval time = 791.90 ms / 2 tokens ( 791.90 ms per token, 1.26 tokens per second) 9.50.910.947 I slot print_timing: id 0 | task 5036 | total time = 2888.19 ms / 126 tokens 9.50.910.948 I slot print_timing: id 0 | task 5036 | graphs reused = 3659 9.50.910.948 I slot print_timing: id 0 | task 5036 | graph reallocs = 0 / 0 (same size) / (changed size) 9.50.910.984 I slot release: id 0 | task 5036 | stop processing: n_tokens = 748, truncated = 0 9.52.872.176 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 748, t_last = 390424501114 9.52.872.237 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.771 MiB) 9.53.004.155 I slot launch_slot_: id 0 | task 5044 | processing task, is_child = 0 9.53.004.239 I slot print_timing: id 1 | task 5037 | prompt processing, n_tokens = 820, progress = 0.86, t = 4.85 s / 169.21 tokens per second 9.53.006.145 I slot print_timing: id 2 | task 5038 | prompt processing, n_tokens = 820, progress = 0.84, t = 4.85 s / 169.21 tokens per second 9.53.008.076 I slot print_timing: id 3 | task 5039 | prompt processing, n_tokens = 820, progress = 0.83, t = 4.85 s / 169.21 tokens per second 9.54.457.624 I slot print_timing: id 1 | task 5037 | prompt processing, n_tokens = 951, progress = 1.00, t = 6.30 s / 150.84 tokens per second 9.54.460.290 I slot print_timing: id 2 | task 5038 | prompt processing, n_tokens = 969, progress = 1.00, t = 6.30 s / 153.69 tokens per second 9.54.462.253 I slot print_timing: id 3 | task 5039 | prompt processing, n_tokens = 986, progress = 1.00, t = 6.30 s / 156.39 tokens per second 9.55.419.517 I slot print_timing: id 1 | task 5037 | prompt eval time = 6957.98 ms / 955 tokens ( 7.29 ms per token, 137.25 tokens per second) 9.55.419.520 I slot print_timing: id 1 | task 5037 | eval time = 435.53 ms / 2 tokens ( 435.53 ms per token, 2.30 tokens per second) 9.55.419.521 I slot print_timing: id 1 | task 5037 | total time = 7393.50 ms / 957 tokens 9.55.419.522 I slot print_timing: id 1 | task 5037 | graphs reused = 3659 9.55.419.522 I slot print_timing: id 1 | task 5037 | graph reallocs = 0 / 0 (same size) / (changed size) 9.55.419.571 I slot release: id 1 | task 5037 | stop processing: n_tokens = 956, truncated = 0 9.55.419.730 I slot print_timing: id 2 | task 5038 | prompt eval time = 6958.08 ms / 973 tokens ( 7.15 ms per token, 139.84 tokens per second) 9.55.419.732 I slot print_timing: id 2 | task 5038 | eval time = 435.58 ms / 2 tokens ( 435.58 ms per token, 2.30 tokens per second) 9.55.419.732 I slot print_timing: id 2 | task 5038 | total time = 7393.66 ms / 975 tokens 9.55.419.733 I slot print_timing: id 2 | task 5038 | graphs reused = 3659 9.55.419.733 I slot print_timing: id 2 | task 5038 | graph reallocs = 0 / 0 (same size) / (changed size) 9.55.419.762 I slot release: id 2 | task 5038 | stop processing: n_tokens = 974, truncated = 0 9.55.419.967 I slot print_timing: id 3 | task 5039 | prompt eval time = 6958.28 ms / 990 tokens ( 7.03 ms per token, 142.28 tokens per second) 9.55.419.971 I slot print_timing: id 3 | task 5039 | eval time = 435.57 ms / 2 tokens ( 435.57 ms per token, 2.30 tokens per second) 9.55.419.972 I slot print_timing: id 3 | task 5039 | total time = 7393.85 ms / 992 tokens 9.55.419.972 I slot print_timing: id 3 | task 5039 | graphs reused = 3659 9.55.419.976 I slot print_timing: id 3 | task 5039 | graph reallocs = 0 / 0 (same size) / (changed size) 9.55.419.998 I slot release: id 3 | task 5039 | stop processing: n_tokens = 991, truncated = 0 9.55.988.657 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 956, t_last = 390429009701 9.55.988.713 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.294 MiB) 9.56.443.024 I slot launch_slot_: id 1 | task 5050 | processing task, is_child = 0 9.56.443.077 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.606 MiB) 9.56.450.808 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 335.204 MiB) 9.56.458.541 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 974, t_last = 390429009892 9.56.458.636 I slot launch_slot_: id 2 | task 5051 | processing task, is_child = 0 9.56.458.684 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 991, t_last = 390429010128 9.56.458.752 I slot launch_slot_: id 3 | task 5052 | processing task, is_child = 0 9.59.112.261 I slot print_timing: id 0 | task 5044 | prompt eval time = 5010.98 ms / 1044 tokens ( 4.80 ms per token, 208.34 tokens per second) 9.59.112.264 I slot print_timing: id 0 | task 5044 | eval time = 1097.11 ms / 2 tokens ( 1097.11 ms per token, 0.91 tokens per second) 9.59.112.265 I slot print_timing: id 0 | task 5044 | total time = 6108.08 ms / 1046 tokens 9.59.112.266 I slot print_timing: id 0 | task 5044 | graphs reused = 3659 9.59.112.266 I slot print_timing: id 0 | task 5044 | graph reallocs = 0 / 0 (same size) / (changed size) 9.59.112.322 I slot release: id 0 | task 5044 | stop processing: n_tokens = 1045, truncated = 0 10.01.471.200 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1045, t_last = 390432702452 10.01.471.267 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 335.028 MiB) 10.01.843.005 I slot launch_slot_: id 0 | task 5056 | processing task, is_child = 0 10.01.843.123 I slot print_timing: id 1 | task 5050 | prompt processing, n_tokens = 645, progress = 0.56, t = 5.01 s / 128.73 tokens per second 10.01.846.511 I slot print_timing: id 2 | task 5051 | prompt processing, n_tokens = 608, progress = 0.54, t = 5.01 s / 121.35 tokens per second 10.01.848.380 I slot print_timing: id 3 | task 5052 | prompt processing, n_tokens = 1575, progress = 0.75, t = 5.01 s / 314.35 tokens per second 10.04.290.660 I slot print_timing: id 1 | task 5050 | prompt processing, n_tokens = 977, progress = 0.84, t = 7.65 s / 127.71 tokens per second 10.04.292.931 I slot print_timing: id 2 | task 5051 | prompt processing, n_tokens = 977, progress = 0.87, t = 7.65 s / 127.71 tokens per second 10.04.294.798 I slot print_timing: id 3 | task 5052 | prompt processing, n_tokens = 1761, progress = 0.84, t = 7.65 s / 230.20 tokens per second 10.05.913.910 I slot print_timing: id 0 | task 5056 | prompt processing, n_tokens = 640, progress = 0.31, t = 4.07 s / 157.21 tokens per second 10.05.913.940 I slot print_timing: id 1 | task 5050 | prompt processing, n_tokens = 1157, progress = 1.00, t = 9.45 s / 122.39 tokens per second 10.06.322.263 I slot print_timing: id 2 | task 5051 | prompt processing, n_tokens = 1120, progress = 1.00, t = 9.45 s / 118.48 tokens per second 10.06.325.243 I slot print_timing: id 3 | task 5052 | prompt processing, n_tokens = 2087, progress = 1.00, t = 9.45 s / 220.78 tokens per second 10.08.042.181 I slot print_timing: id 0 | task 5056 | prompt processing, n_tokens = 1578, progress = 0.75, t = 6.20 s / 254.58 tokens per second 10.08.500.953 I slot print_timing: id 1 | task 5050 | prompt eval time = 11580.97 ms / 1161 tokens ( 9.97 ms per token, 100.25 tokens per second) 10.08.500.958 I slot print_timing: id 1 | task 5050 | eval time = 459.23 ms / 2 tokens ( 459.23 ms per token, 2.18 tokens per second) 10.08.500.958 I slot print_timing: id 1 | task 5050 | total time = 12040.20 ms / 1163 tokens 10.08.500.959 I slot print_timing: id 1 | task 5050 | graphs reused = 3659 10.08.500.959 I slot print_timing: id 1 | task 5050 | graph reallocs = 0 / 0 (same size) / (changed size) 10.08.501.006 I slot release: id 1 | task 5050 | stop processing: n_tokens = 1162, truncated = 0 10.08.501.158 I slot print_timing: id 2 | task 5051 | prompt eval time = 11581.11 ms / 1124 tokens ( 10.30 ms per token, 97.05 tokens per second) 10.08.501.160 I slot print_timing: id 2 | task 5051 | eval time = 459.23 ms / 2 tokens ( 459.23 ms per token, 2.18 tokens per second) 10.08.501.160 I slot print_timing: id 2 | task 5051 | total time = 12040.34 ms / 1126 tokens 10.08.501.161 I slot print_timing: id 2 | task 5051 | graphs reused = 3659 10.08.501.161 I slot print_timing: id 2 | task 5051 | graph reallocs = 0 / 0 (same size) / (changed size) 10.08.501.191 I slot release: id 2 | task 5051 | stop processing: n_tokens = 1125, truncated = 0 10.08.501.410 I slot print_timing: id 3 | task 5052 | prompt eval time = 11581.26 ms / 2091 tokens ( 5.54 ms per token, 180.55 tokens per second) 10.08.501.411 I slot print_timing: id 3 | task 5052 | eval time = 459.25 ms / 2 tokens ( 459.25 ms per token, 2.18 tokens per second) 10.08.501.412 I slot print_timing: id 3 | task 5052 | total time = 12040.52 ms / 2093 tokens 10.08.501.412 I slot print_timing: id 3 | task 5052 | graphs reused = 3659 10.08.501.412 I slot print_timing: id 3 | task 5052 | graph reallocs = 0 / 0 (same size) / (changed size) 10.08.501.483 I slot release: id 3 | task 5052 | stop processing: n_tokens = 2092, truncated = 0 10.08.501.492 I slot print_timing: id 0 | task 5056 | prompt processing, n_tokens = 1761, progress = 0.84, t = 6.66 s / 264.50 tokens per second 10.08.510.275 I slot print_timing: id 0 | task 5056 | prompt processing, n_tokens = 2090, progress = 1.00, t = 6.67 s / 313.47 tokens per second 10.09.178.227 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 10.09.178.279 I slot launch_slot_: id 3 | task 5063 | processing task, is_child = 0 10.09.178.351 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 335.185 MiB) 10.09.186.661 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 335.243 MiB) 10.09.194.470 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1162, t_last = 390442091136 10.09.194.572 I slot launch_slot_: id 1 | task 5064 | processing task, is_child = 0 10.09.194.626 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1125, t_last = 390442091321 10.09.194.694 I slot launch_slot_: id 2 | task 5065 | processing task, is_child = 0 10.11.063.282 I slot print_timing: id 0 | task 5056 | prompt eval time = 7335.19 ms / 2094 tokens ( 3.50 ms per token, 285.47 tokens per second) 10.11.063.284 I slot print_timing: id 0 | task 5056 | eval time = 1885.05 ms / 2 tokens ( 1885.05 ms per token, 0.53 tokens per second) 10.11.063.284 I slot print_timing: id 0 | task 5056 | total time = 9220.25 ms / 2096 tokens 10.11.063.285 I slot print_timing: id 0 | task 5056 | graphs reused = 3659 10.11.063.285 I slot print_timing: id 0 | task 5056 | graph reallocs = 0 / 0 (same size) / (changed size) 10.11.063.370 I slot release: id 0 | task 5056 | stop processing: n_tokens = 2095, truncated = 0 10.12.092.718 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 10.12.092.788 I slot launch_slot_: id 0 | task 5068 | processing task, is_child = 0 10.15.732.816 I slot print_timing: id 3 | task 5063 | prompt eval time = 2897.84 ms / 296 tokens ( 9.79 ms per token, 102.15 tokens per second) 10.15.732.821 I slot print_timing: id 3 | task 5063 | eval time = 3640.10 ms / 2 tokens ( 3640.10 ms per token, 0.27 tokens per second) 10.15.732.821 I slot print_timing: id 3 | task 5063 | total time = 6537.94 ms / 298 tokens 10.15.732.822 I slot print_timing: id 3 | task 5063 | graphs reused = 3659 10.15.732.822 I slot print_timing: id 3 | task 5063 | graph reallocs = 0 / 0 (same size) / (changed size) 10.15.732.902 I slot release: id 3 | task 5063 | stop processing: n_tokens = 2058, truncated = 0 10.15.732.917 I slot print_timing: id 0 | task 5068 | prompt processing, n_tokens = 365, progress = 1.00, t = 3.64 s / 100.28 tokens per second 10.15.735.951 I slot print_timing: id 1 | task 5064 | prompt processing, n_tokens = 1589, progress = 0.75, t = 6.54 s / 243.04 tokens per second 10.15.738.146 I slot print_timing: id 2 | task 5065 | prompt processing, n_tokens = 1373, progress = 0.67, t = 6.54 s / 210.01 tokens per second 10.16.547.775 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 10.16.547.846 I slot launch_slot_: id 3 | task 5071 | processing task, is_child = 0 10.16.547.852 I slot print_timing: id 1 | task 5064 | prompt processing, n_tokens = 1761, progress = 0.84, t = 7.35 s / 239.50 tokens per second 10.16.550.816 I slot print_timing: id 2 | task 5065 | prompt processing, n_tokens = 1525, progress = 0.75, t = 7.35 s / 207.40 tokens per second 10.18.445.416 I slot print_timing: id 0 | task 5068 | prompt eval time = 4454.97 ms / 369 tokens ( 12.07 ms per token, 82.83 tokens per second) 10.18.445.418 I slot print_timing: id 0 | task 5068 | eval time = 1897.64 ms / 2 tokens ( 1897.64 ms per token, 0.53 tokens per second) 10.18.445.419 I slot print_timing: id 0 | task 5068 | total time = 6352.61 ms / 371 tokens 10.18.445.419 I slot print_timing: id 0 | task 5068 | graphs reused = 3659 10.18.445.420 I slot print_timing: id 0 | task 5068 | graph reallocs = 0 / 0 (same size) / (changed size) 10.18.445.500 I slot release: id 0 | task 5068 | stop processing: n_tokens = 2131, truncated = 0 10.18.445.514 I slot print_timing: id 1 | task 5064 | prompt processing, n_tokens = 2101, progress = 1.00, t = 9.25 s / 227.12 tokens per second 10.18.448.371 I slot print_timing: id 2 | task 5065 | prompt processing, n_tokens = 1761, progress = 0.86, t = 9.25 s / 190.37 tokens per second 10.19.097.011 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 10.19.097.085 I slot launch_slot_: id 0 | task 5074 | processing task, is_child = 0 10.19.101.628 I slot print_timing: id 2 | task 5065 | prompt processing, n_tokens = 2037, progress = 1.00, t = 9.90 s / 205.72 tokens per second 10.19.876.138 I slot print_timing: id 1 | task 5064 | prompt eval time = 9902.09 ms / 2105 tokens ( 4.70 ms per token, 212.58 tokens per second) 10.19.876.141 I slot print_timing: id 1 | task 5064 | eval time = 779.34 ms / 2 tokens ( 779.34 ms per token, 1.28 tokens per second) 10.19.876.141 I slot print_timing: id 1 | task 5064 | total time = 10681.43 ms / 2107 tokens 10.19.876.142 I slot print_timing: id 1 | task 5064 | graphs reused = 3659 10.19.876.142 I slot print_timing: id 1 | task 5064 | graph reallocs = 0 / 0 (same size) / (changed size) 10.19.876.226 I slot release: id 1 | task 5064 | stop processing: n_tokens = 2106, truncated = 0 10.19.876.645 I slot print_timing: id 3 | task 5071 | prompt eval time = 2544.32 ms / 300 tokens ( 8.48 ms per token, 117.91 tokens per second) 10.19.876.651 I slot print_timing: id 3 | task 5071 | eval time = 779.64 ms / 2 tokens ( 779.64 ms per token, 1.28 tokens per second) 10.19.876.652 I slot print_timing: id 3 | task 5071 | total time = 3323.97 ms / 302 tokens 10.19.876.652 I slot print_timing: id 3 | task 5071 | graphs reused = 3659 10.19.876.653 I slot print_timing: id 3 | task 5071 | graph reallocs = 0 / 0 (same size) / (changed size) 10.19.876.714 I slot release: id 3 | task 5071 | stop processing: n_tokens = 2062, truncated = 0 10.19.947.470 I slot print_timing: id 2 | task 5065 | prompt eval time = 10681.66 ms / 2041 tokens ( 5.23 ms per token, 191.08 tokens per second) 10.19.947.479 I slot print_timing: id 2 | task 5065 | eval time = 71.02 ms / 2 tokens ( 71.02 ms per token, 14.08 tokens per second) 10.19.947.480 I slot print_timing: id 2 | task 5065 | total time = 10752.68 ms / 2043 tokens 10.19.947.480 I slot print_timing: id 2 | task 5065 | graphs reused = 3659 10.19.947.480 I slot print_timing: id 2 | task 5065 | graph reallocs = 0 / 0 (same size) / (changed size) 10.19.947.553 I slot release: id 2 | task 5065 | stop processing: n_tokens = 2042, truncated = 0 10.19.947.563 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 10.19.947.603 I slot launch_slot_: id 1 | task 5077 | processing task, is_child = 0 10.19.947.693 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 335.361 MiB) 10.19.957.249 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 335.126 MiB) 10.19.965.971 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.803 (> 0.100 thold), f_keep = 0.877 10.19.966.028 I slot launch_slot_: id 2 | task 5078 | processing task, is_child = 0 10.19.966.116 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 10.19.966.138 I slot launch_slot_: id 3 | task 5079 | processing task, is_child = 0 10.21.946.969 I slot print_timing: id 0 | task 5074 | prompt eval time = 850.22 ms / 380 tokens ( 2.24 ms per token, 446.95 tokens per second) 10.21.946.972 I slot print_timing: id 0 | task 5074 | eval time = 1999.66 ms / 2 tokens ( 1999.66 ms per token, 0.50 tokens per second) 10.21.946.973 I slot print_timing: id 0 | task 5074 | total time = 2849.87 ms / 382 tokens 10.21.946.973 I slot print_timing: id 0 | task 5074 | graphs reused = 3659 10.21.946.974 I slot print_timing: id 0 | task 5074 | graph reallocs = 0 / 0 (same size) / (changed size) 10.21.947.054 I slot release: id 0 | task 5074 | stop processing: n_tokens = 2142, truncated = 0 10.22.058.059 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 10.22.058.126 I slot launch_slot_: id 0 | task 5082 | processing task, is_child = 0 10.22.613.424 I slot print_timing: id 1 | task 5077 | prompt eval time = 2091.51 ms / 210 tokens ( 9.96 ms per token, 100.41 tokens per second) 10.22.613.427 I slot print_timing: id 1 | task 5077 | eval time = 555.76 ms / 2 tokens ( 555.76 ms per token, 1.80 tokens per second) 10.22.613.427 I slot print_timing: id 1 | task 5077 | total time = 2647.27 ms / 212 tokens 10.22.613.428 I slot print_timing: id 1 | task 5077 | graphs reused = 3659 10.22.613.428 I slot print_timing: id 1 | task 5077 | graph reallocs = 0 / 0 (same size) / (changed size) 10.22.613.508 I slot release: id 1 | task 5077 | stop processing: n_tokens = 1972, truncated = 0 10.22.613.716 I slot print_timing: id 2 | task 5078 | prompt eval time = 2088.39 ms / 467 tokens ( 4.47 ms per token, 223.62 tokens per second) 10.22.613.722 I slot print_timing: id 2 | task 5078 | eval time = 555.88 ms / 2 tokens ( 555.88 ms per token, 1.80 tokens per second) 10.22.613.722 I slot print_timing: id 2 | task 5078 | total time = 2644.26 ms / 469 tokens 10.22.613.722 I slot print_timing: id 2 | task 5078 | graphs reused = 3659 10.22.613.723 I slot print_timing: id 2 | task 5078 | graph reallocs = 0 / 0 (same size) / (changed size) 10.22.613.783 I slot release: id 2 | task 5078 | stop processing: n_tokens = 2229, truncated = 0 10.22.614.010 I slot print_timing: id 3 | task 5079 | prompt eval time = 2085.39 ms / 258 tokens ( 8.08 ms per token, 123.72 tokens per second) 10.22.614.013 I slot print_timing: id 3 | task 5079 | eval time = 555.96 ms / 2 tokens ( 555.96 ms per token, 1.80 tokens per second) 10.22.614.013 I slot print_timing: id 3 | task 5079 | total time = 2641.34 ms / 260 tokens 10.22.614.013 I slot print_timing: id 3 | task 5079 | graphs reused = 3659 10.22.614.016 I slot print_timing: id 3 | task 5079 | graph reallocs = 0 / 0 (same size) / (changed size) 10.22.614.067 I slot release: id 3 | task 5079 | stop processing: n_tokens = 2020, truncated = 0 10.22.663.287 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.907 10.22.663.323 I slot launch_slot_: id 1 | task 5085 | processing task, is_child = 0 10.22.663.441 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 335.107 MiB) 10.22.672.632 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 335.204 MiB) 10.22.681.405 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.850 (> 0.100 thold), f_keep = 0.803 10.22.681.452 I slot launch_slot_: id 2 | task 5086 | processing task, is_child = 0 10.22.681.537 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.867 (> 0.100 thold), f_keep = 0.886 10.22.681.558 I slot launch_slot_: id 3 | task 5087 | processing task, is_child = 0 10.24.523.124 I slot print_timing: id 0 | task 5082 | prompt eval time = 605.14 ms / 253 tokens ( 2.39 ms per token, 418.08 tokens per second) 10.24.523.127 I slot print_timing: id 0 | task 5082 | eval time = 1859.84 ms / 2 tokens ( 1859.84 ms per token, 0.54 tokens per second) 10.24.523.127 I slot print_timing: id 0 | task 5082 | total time = 2464.98 ms / 255 tokens 10.24.523.128 I slot print_timing: id 0 | task 5082 | graphs reused = 3659 10.24.523.128 I slot print_timing: id 0 | task 5082 | graph reallocs = 0 / 0 (same size) / (changed size) 10.24.523.206 I slot release: id 0 | task 5082 | stop processing: n_tokens = 2015, truncated = 0 10.24.633.784 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 10.24.633.850 I slot launch_slot_: id 0 | task 5090 | processing task, is_child = 0 10.25.269.823 I slot print_timing: id 1 | task 5085 | prompt eval time = 1951.88 ms / 212 tokens ( 9.21 ms per token, 108.61 tokens per second) 10.25.269.826 I slot print_timing: id 1 | task 5085 | eval time = 636.38 ms / 2 tokens ( 636.38 ms per token, 1.57 tokens per second) 10.25.269.827 I slot print_timing: id 1 | task 5085 | total time = 2588.26 ms / 214 tokens 10.25.269.827 I slot print_timing: id 1 | task 5085 | graphs reused = 3659 10.25.269.828 I slot print_timing: id 1 | task 5085 | graph reallocs = 0 / 0 (same size) / (changed size) 10.25.269.903 I slot release: id 1 | task 5085 | stop processing: n_tokens = 1974, truncated = 0 10.25.270.062 I slot print_timing: id 2 | task 5086 | prompt eval time = 1948.80 ms / 345 tokens ( 5.65 ms per token, 177.03 tokens per second) 10.25.270.064 I slot print_timing: id 2 | task 5086 | eval time = 636.45 ms / 2 tokens ( 636.45 ms per token, 1.57 tokens per second) 10.25.270.065 I slot print_timing: id 2 | task 5086 | total time = 2585.25 ms / 347 tokens 10.25.270.065 I slot print_timing: id 2 | task 5086 | graphs reused = 3659 10.25.270.065 I slot print_timing: id 2 | task 5086 | graph reallocs = 0 / 0 (same size) / (changed size) 10.25.270.131 I slot release: id 2 | task 5086 | stop processing: n_tokens = 2107, truncated = 0 10.25.270.296 I slot print_timing: id 3 | task 5087 | prompt eval time = 1945.77 ms / 304 tokens ( 6.40 ms per token, 156.24 tokens per second) 10.25.270.298 I slot print_timing: id 3 | task 5087 | eval time = 636.52 ms / 2 tokens ( 636.52 ms per token, 1.57 tokens per second) 10.25.270.298 I slot print_timing: id 3 | task 5087 | total time = 2582.29 ms / 306 tokens 10.25.270.299 I slot print_timing: id 3 | task 5087 | graphs reused = 3659 10.25.270.299 I slot print_timing: id 3 | task 5087 | graph reallocs = 0 / 0 (same size) / (changed size) 10.25.270.344 I slot release: id 3 | task 5087 | stop processing: n_tokens = 2066, truncated = 0 10.25.319.349 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 10.25.319.382 I slot launch_slot_: id 2 | task 5093 | processing task, is_child = 0 10.25.319.475 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 335.185 MiB) 10.25.327.905 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 335.165 MiB) 10.25.342.252 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.826 (> 0.100 thold), f_keep = 0.906 10.25.342.303 I slot launch_slot_: id 1 | task 5094 | processing task, is_child = 0 10.25.342.390 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.847 (> 0.100 thold), f_keep = 0.866 10.25.342.410 I slot launch_slot_: id 3 | task 5095 | processing task, is_child = 0 10.27.383.378 I slot print_timing: id 0 | task 5090 | prompt eval time = 685.49 ms / 304 tokens ( 2.25 ms per token, 443.48 tokens per second) 10.27.383.381 I slot print_timing: id 0 | task 5090 | eval time = 2064.03 ms / 2 tokens ( 2064.03 ms per token, 0.48 tokens per second) 10.27.383.382 I slot print_timing: id 0 | task 5090 | total time = 2749.52 ms / 306 tokens 10.27.383.382 I slot print_timing: id 0 | task 5090 | graphs reused = 3659 10.27.383.383 I slot print_timing: id 0 | task 5090 | graph reallocs = 0 / 0 (same size) / (changed size) 10.27.383.465 I slot release: id 0 | task 5090 | stop processing: n_tokens = 2066, truncated = 0 10.27.494.600 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 10.27.494.666 I slot launch_slot_: id 0 | task 5098 | processing task, is_child = 0 10.28.270.246 I slot print_timing: id 1 | task 5094 | prompt eval time = 2151.84 ms / 405 tokens ( 5.31 ms per token, 188.21 tokens per second) 10.28.270.249 I slot print_timing: id 1 | task 5094 | eval time = 775.99 ms / 2 tokens ( 775.99 ms per token, 1.29 tokens per second) 10.28.270.249 I slot print_timing: id 1 | task 5094 | total time = 2927.82 ms / 407 tokens 10.28.270.250 I slot print_timing: id 1 | task 5094 | graphs reused = 3659 10.28.270.250 I slot print_timing: id 1 | task 5094 | graph reallocs = 0 / 0 (same size) / (changed size) 10.28.270.334 I slot release: id 1 | task 5094 | stop processing: n_tokens = 2167, truncated = 0 10.28.270.500 I slot print_timing: id 2 | task 5093 | prompt eval time = 2148.77 ms / 210 tokens ( 10.23 ms per token, 97.73 tokens per second) 10.28.270.502 I slot print_timing: id 2 | task 5093 | eval time = 776.08 ms / 2 tokens ( 776.08 ms per token, 1.29 tokens per second) 10.28.270.503 I slot print_timing: id 2 | task 5093 | total time = 2924.84 ms / 212 tokens 10.28.270.503 I slot print_timing: id 2 | task 5093 | graphs reused = 3659 10.28.270.503 I slot print_timing: id 2 | task 5093 | graph reallocs = 0 / 0 (same size) / (changed size) 10.28.270.556 I slot release: id 2 | task 5093 | stop processing: n_tokens = 1972, truncated = 0 10.28.270.735 I slot print_timing: id 3 | task 5095 | prompt eval time = 2145.72 ms / 353 tokens ( 6.08 ms per token, 164.51 tokens per second) 10.28.270.738 I slot print_timing: id 3 | task 5095 | eval time = 776.14 ms / 2 tokens ( 776.14 ms per token, 1.29 tokens per second) 10.28.270.738 I slot print_timing: id 3 | task 5095 | total time = 2921.87 ms / 355 tokens 10.28.270.739 I slot print_timing: id 3 | task 5095 | graphs reused = 3659 10.28.270.739 I slot print_timing: id 3 | task 5095 | graph reallocs = 0 / 0 (same size) / (changed size) 10.28.270.786 I slot release: id 3 | task 5095 | stop processing: n_tokens = 2115, truncated = 0 10.28.319.502 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.880 (> 0.100 thold), f_keep = 0.826 10.28.319.547 I slot launch_slot_: id 1 | task 5101 | processing task, is_child = 0 10.28.319.652 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 334.246 MiB) 10.28.334.330 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 335.713 MiB) 10.28.348.738 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.908 10.28.348.791 I slot launch_slot_: id 2 | task 5102 | processing task, is_child = 0 10.28.348.882 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.896 (> 0.100 thold), f_keep = 0.846 10.28.348.909 I slot launch_slot_: id 3 | task 5103 | processing task, is_child = 0 10.29.951.792 I slot print_timing: id 0 | task 5098 | prompt eval time = 824.82 ms / 413 tokens ( 2.00 ms per token, 500.72 tokens per second) 10.29.951.794 I slot print_timing: id 0 | task 5098 | eval time = 1632.29 ms / 2 tokens ( 1632.29 ms per token, 0.61 tokens per second) 10.29.951.794 I slot print_timing: id 0 | task 5098 | total time = 2457.11 ms / 415 tokens 10.29.951.795 I slot print_timing: id 0 | task 5098 | graphs reused = 3659 10.29.951.795 I slot print_timing: id 0 | task 5098 | graph reallocs = 0 / 0 (same size) / (changed size) 10.29.951.881 I slot release: id 0 | task 5098 | stop processing: n_tokens = 2175, truncated = 0 10.30.061.609 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 10.30.061.677 I slot launch_slot_: id 0 | task 5106 | processing task, is_child = 0 10.30.467.897 I slot print_timing: id 1 | task 5101 | prompt eval time = 1712.37 ms / 272 tokens ( 6.30 ms per token, 158.84 tokens per second) 10.30.467.899 I slot print_timing: id 1 | task 5101 | eval time = 406.61 ms / 2 tokens ( 406.61 ms per token, 2.46 tokens per second) 10.30.467.899 I slot print_timing: id 1 | task 5101 | total time = 2118.98 ms / 274 tokens 10.30.467.900 I slot print_timing: id 1 | task 5101 | graphs reused = 3659 10.30.467.900 I slot print_timing: id 1 | task 5101 | graph reallocs = 0 / 0 (same size) / (changed size) 10.30.467.976 I slot release: id 1 | task 5101 | stop processing: n_tokens = 2034, truncated = 0 10.30.468.128 I slot print_timing: id 2 | task 5102 | prompt eval time = 1709.25 ms / 264 tokens ( 6.47 ms per token, 154.45 tokens per second) 10.30.468.131 I slot print_timing: id 2 | task 5102 | eval time = 406.69 ms / 2 tokens ( 406.69 ms per token, 2.46 tokens per second) 10.30.468.132 I slot print_timing: id 2 | task 5102 | total time = 2115.93 ms / 266 tokens 10.30.468.132 I slot print_timing: id 2 | task 5102 | graphs reused = 3659 10.30.468.133 I slot print_timing: id 2 | task 5102 | graph reallocs = 0 / 0 (same size) / (changed size) 10.30.468.183 I slot release: id 2 | task 5102 | stop processing: n_tokens = 2026, truncated = 0 10.30.468.402 I slot print_timing: id 3 | task 5103 | prompt eval time = 1706.18 ms / 236 tokens ( 7.23 ms per token, 138.32 tokens per second) 10.30.468.406 I slot print_timing: id 3 | task 5103 | eval time = 406.80 ms / 2 tokens ( 406.80 ms per token, 2.46 tokens per second) 10.30.468.406 I slot print_timing: id 3 | task 5103 | total time = 2112.98 ms / 238 tokens 10.30.468.406 I slot print_timing: id 3 | task 5103 | graphs reused = 3659 10.30.468.407 I slot print_timing: id 3 | task 5103 | graph reallocs = 0 / 0 (same size) / (changed size) 10.30.468.449 I slot release: id 3 | task 5103 | stop processing: n_tokens = 1998, truncated = 0 10.30.517.418 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 2034, t_last = 390464058107 10.30.517.526 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 334.227 MiB) 10.30.531.920 I slot launch_slot_: id 1 | task 5109 | processing task, is_child = 0 10.30.532.017 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 335.028 MiB) 10.30.546.289 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 334.520 MiB) 10.30.546.299 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.341 MiB) 10.30.560.460 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 10.30.560.515 I slot launch_slot_: id 2 | task 5110 | processing task, is_child = 0 10.30.560.620 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.899 (> 0.100 thold), f_keep = 0.895 10.30.560.642 I slot launch_slot_: id 3 | task 5111 | processing task, is_child = 0 10.32.278.415 I slot print_timing: id 0 | task 5106 | prompt eval time = 455.73 ms / 149 tokens ( 3.06 ms per token, 326.95 tokens per second) 10.32.278.417 I slot print_timing: id 0 | task 5106 | eval time = 1760.99 ms / 2 tokens ( 1760.99 ms per token, 0.57 tokens per second) 10.32.278.417 I slot print_timing: id 0 | task 5106 | total time = 2216.72 ms / 151 tokens 10.32.278.418 I slot print_timing: id 0 | task 5106 | graphs reused = 3659 10.32.278.418 I slot print_timing: id 0 | task 5106 | graph reallocs = 0 / 0 (same size) / (changed size) 10.32.278.491 I slot release: id 0 | task 5106 | stop processing: n_tokens = 1911, truncated = 0 10.32.829.391 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1911, t_last = 390465868622 10.32.829.494 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.556 MiB) 10.32.842.016 I slot launch_slot_: id 0 | task 5114 | processing task, is_child = 0 10.34.305.408 I slot print_timing: id 2 | task 5110 | prompt eval time = 2268.36 ms / 196 tokens ( 11.57 ms per token, 86.41 tokens per second) 10.34.305.411 I slot print_timing: id 2 | task 5110 | eval time = 1476.22 ms / 2 tokens ( 1476.22 ms per token, 0.68 tokens per second) 10.34.305.411 I slot print_timing: id 2 | task 5110 | total time = 3744.57 ms / 198 tokens 10.34.305.412 I slot print_timing: id 2 | task 5110 | graphs reused = 3659 10.34.305.412 I slot print_timing: id 2 | task 5110 | graph reallocs = 0 / 0 (same size) / (changed size) 10.34.305.499 I slot release: id 2 | task 5110 | stop processing: n_tokens = 1958, truncated = 0 10.34.305.731 I slot print_timing: id 3 | task 5111 | prompt eval time = 2265.34 ms / 230 tokens ( 9.85 ms per token, 101.53 tokens per second) 10.34.305.735 I slot print_timing: id 3 | task 5111 | eval time = 1476.34 ms / 2 tokens ( 1476.34 ms per token, 0.68 tokens per second) 10.34.305.735 I slot print_timing: id 3 | task 5111 | total time = 3741.68 ms / 232 tokens 10.34.305.736 I slot print_timing: id 3 | task 5111 | graphs reused = 3659 10.34.305.736 I slot print_timing: id 3 | task 5111 | graph reallocs = 0 / 0 (same size) / (changed size) 10.34.305.795 I slot release: id 3 | task 5111 | stop processing: n_tokens = 1992, truncated = 0 10.34.309.398 I slot print_timing: id 1 | task 5109 | prompt processing, n_tokens = 959, progress = 0.65, t = 3.74 s / 256.11 tokens per second 10.35.052.265 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1958, t_last = 390467895629 10.35.052.389 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 329.671 MiB) 10.35.352.165 I slot launch_slot_: id 2 | task 5117 | processing task, is_child = 0 10.35.352.265 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.419 MiB) 10.35.366.403 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1992, t_last = 390467895925 10.35.366.540 I slot launch_slot_: id 3 | task 5118 | processing task, is_child = 0 10.35.366.562 I slot print_timing: id 1 | task 5109 | prompt processing, n_tokens = 1275, progress = 0.86, t = 4.49 s / 283.86 tokens per second 10.37.777.865 I slot print_timing: id 0 | task 5114 | prompt processing, n_tokens = 1161, progress = 0.69, t = 4.94 s / 235.22 tokens per second 10.38.065.786 I slot print_timing: id 1 | task 5109 | prompt processing, n_tokens = 1471, progress = 1.00, t = 7.22 s / 203.82 tokens per second 10.39.258.463 I slot print_timing: id 0 | task 5114 | prompt processing, n_tokens = 1275, progress = 0.76, t = 6.42 s / 198.72 tokens per second 10.39.260.733 I slot print_timing: id 2 | task 5117 | prompt processing, n_tokens = 575, progress = 0.37, t = 3.89 s / 147.82 tokens per second 10.39.260.750 I slot print_timing: id 3 | task 5118 | prompt processing, n_tokens = 409, progress = 0.41, t = 3.89 s / 105.15 tokens per second 10.41.052.287 I slot print_timing: id 1 | task 5109 | prompt eval time = 8697.80 ms / 1475 tokens ( 5.90 ms per token, 169.58 tokens per second) 10.41.052.289 I slot print_timing: id 1 | task 5109 | eval time = 1793.83 ms / 2 tokens ( 1793.83 ms per token, 0.56 tokens per second) 10.41.052.290 I slot print_timing: id 1 | task 5109 | total time = 10491.63 ms / 1477 tokens 10.41.052.290 I slot print_timing: id 1 | task 5109 | graphs reused = 3659 10.41.052.291 I slot print_timing: id 1 | task 5109 | graph reallocs = 0 / 0 (same size) / (changed size) 10.41.052.357 I slot release: id 1 | task 5109 | stop processing: n_tokens = 1476, truncated = 0 10.41.052.374 I slot print_timing: id 0 | task 5114 | prompt processing, n_tokens = 1673, progress = 1.00, t = 8.21 s / 203.77 tokens per second 10.41.056.052 I slot print_timing: id 2 | task 5117 | prompt processing, n_tokens = 1039, progress = 0.67, t = 5.68 s / 182.81 tokens per second 10.41.058.283 I slot print_timing: id 3 | task 5118 | prompt processing, n_tokens = 483, progress = 0.48, t = 5.68 s / 84.98 tokens per second 10.42.239.432 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1476, t_last = 390474642489 10.42.239.510 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.536 MiB) 10.42.249.596 I slot launch_slot_: id 1 | task 5123 | processing task, is_child = 0 10.42.249.730 I slot print_timing: id 2 | task 5117 | prompt processing, n_tokens = 1275, progress = 0.82, t = 6.87 s / 185.57 tokens per second 10.42.251.615 I slot print_timing: id 3 | task 5118 | prompt processing, n_tokens = 853, progress = 0.85, t = 6.87 s / 124.15 tokens per second 10.43.646.030 I slot print_timing: id 0 | task 5114 | prompt eval time = 9397.40 ms / 1677 tokens ( 5.60 ms per token, 178.45 tokens per second) 10.43.646.032 I slot print_timing: id 0 | task 5114 | eval time = 1406.60 ms / 2 tokens ( 1406.60 ms per token, 0.71 tokens per second) 10.43.646.033 I slot print_timing: id 0 | task 5114 | total time = 10804.00 ms / 1679 tokens 10.43.646.033 I slot print_timing: id 0 | task 5114 | graphs reused = 3659 10.43.646.034 I slot print_timing: id 0 | task 5114 | graph reallocs = 0 / 0 (same size) / (changed size) 10.43.646.106 I slot release: id 0 | task 5114 | stop processing: n_tokens = 1678, truncated = 0 10.43.648.812 I slot print_timing: id 2 | task 5117 | prompt processing, n_tokens = 1551, progress = 1.00, t = 8.28 s / 187.38 tokens per second 10.43.652.605 I slot print_timing: id 3 | task 5118 | prompt processing, n_tokens = 995, progress = 1.00, t = 8.28 s / 120.21 tokens per second 10.44.103.137 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1678, t_last = 390477236236 10.44.103.223 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.849 MiB) 10.44.111.878 I slot launch_slot_: id 0 | task 5126 | processing task, is_child = 0 10.44.881.189 I slot print_timing: id 2 | task 5117 | prompt eval time = 8734.52 ms / 1555 tokens ( 5.62 ms per token, 178.03 tokens per second) 10.44.881.195 I slot print_timing: id 2 | task 5117 | eval time = 778.23 ms / 2 tokens ( 778.23 ms per token, 1.28 tokens per second) 10.44.881.196 I slot print_timing: id 2 | task 5117 | total time = 9512.75 ms / 1557 tokens 10.44.881.196 I slot print_timing: id 2 | task 5117 | graphs reused = 3659 10.44.881.196 I slot print_timing: id 2 | task 5117 | graph reallocs = 0 / 0 (same size) / (changed size) 10.44.881.266 I slot release: id 2 | task 5117 | stop processing: n_tokens = 1556, truncated = 0 10.44.881.511 I slot print_timing: id 3 | task 5118 | prompt eval time = 8734.55 ms / 999 tokens ( 8.74 ms per token, 114.37 tokens per second) 10.44.881.520 I slot print_timing: id 3 | task 5118 | eval time = 778.38 ms / 2 tokens ( 778.38 ms per token, 1.28 tokens per second) 10.44.881.520 I slot print_timing: id 3 | task 5118 | total time = 9512.93 ms / 1001 tokens 10.44.881.520 I slot print_timing: id 3 | task 5118 | graphs reused = 3659 10.44.881.521 I slot print_timing: id 3 | task 5118 | graph reallocs = 0 / 0 (same size) / (changed size) 10.44.881.556 I slot release: id 3 | task 5118 | stop processing: n_tokens = 1000, truncated = 0 10.45.449.909 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.896 (> 0.100 thold), f_keep = 0.881 10.45.449.960 I slot launch_slot_: id 3 | task 5129 | processing task, is_child = 0 10.45.450.034 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.693 MiB) 10.45.923.581 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1556, t_last = 390478471396 10.45.923.744 I slot launch_slot_: id 2 | task 5130 | processing task, is_child = 0 10.45.923.764 I slot print_timing: id 1 | task 5123 | prompt processing, n_tokens = 853, progress = 0.86, t = 3.20 s / 266.54 tokens per second 10.47.243.849 I slot print_timing: id 1 | task 5123 | prompt processing, n_tokens = 985, progress = 1.00, t = 4.67 s / 211.02 tokens per second 10.48.400.829 I slot print_timing: id 0 | task 5126 | prompt processing, n_tokens = 853, progress = 0.87, t = 4.29 s / 198.90 tokens per second 10.48.939.609 I slot print_timing: id 1 | task 5123 | prompt eval time = 6150.99 ms / 989 tokens ( 6.22 ms per token, 160.79 tokens per second) 10.48.939.612 I slot print_timing: id 1 | task 5123 | eval time = 539.01 ms / 2 tokens ( 539.01 ms per token, 1.86 tokens per second) 10.48.939.612 I slot print_timing: id 1 | task 5123 | total time = 6690.00 ms / 991 tokens 10.48.939.613 I slot print_timing: id 1 | task 5123 | graphs reused = 3659 10.48.939.613 I slot print_timing: id 1 | task 5123 | graph reallocs = 0 / 0 (same size) / (changed size) 10.48.939.661 I slot release: id 1 | task 5123 | stop processing: n_tokens = 990, truncated = 0 10.48.939.904 I slot print_timing: id 3 | task 5129 | prompt eval time = 2473.63 ms / 130 tokens ( 19.03 ms per token, 52.55 tokens per second) 10.48.939.906 I slot print_timing: id 3 | task 5129 | eval time = 539.08 ms / 2 tokens ( 539.08 ms per token, 1.86 tokens per second) 10.48.939.906 I slot print_timing: id 3 | task 5129 | total time = 3012.71 ms / 132 tokens 10.48.939.906 I slot print_timing: id 3 | task 5129 | graphs reused = 3659 10.48.939.907 I slot print_timing: id 3 | task 5129 | graph reallocs = 0 / 0 (same size) / (changed size) 10.48.939.941 I slot release: id 3 | task 5129 | stop processing: n_tokens = 984, truncated = 0 10.48.939.948 I slot print_timing: id 0 | task 5126 | prompt processing, n_tokens = 973, progress = 1.00, t = 4.83 s / 201.55 tokens per second 10.48.944.244 I slot print_timing: id 2 | task 5130 | prompt processing, n_tokens = 444, progress = 0.46, t = 3.01 s / 147.39 tokens per second 10.49.701.600 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.890 10.49.701.670 I slot launch_slot_: id 1 | task 5135 | processing task, is_child = 0 10.49.701.731 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 332.760 MiB) 10.49.709.612 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.895 10.49.709.647 I slot launch_slot_: id 3 | task 5136 | processing task, is_child = 0 10.49.712.875 I slot print_timing: id 2 | task 5130 | prompt processing, n_tokens = 853, progress = 0.89, t = 3.76 s / 227.09 tokens per second 10.50.526.479 I slot print_timing: id 0 | task 5126 | prompt eval time = 5589.70 ms / 977 tokens ( 5.72 ms per token, 174.79 tokens per second) 10.50.526.485 I slot print_timing: id 0 | task 5126 | eval time = 824.89 ms / 2 tokens ( 824.89 ms per token, 1.21 tokens per second) 10.50.526.485 I slot print_timing: id 0 | task 5126 | total time = 6414.59 ms / 979 tokens 10.50.526.486 I slot print_timing: id 0 | task 5126 | graphs reused = 3659 10.50.526.486 I slot print_timing: id 0 | task 5126 | graph reallocs = 0 / 0 (same size) / (changed size) 10.50.526.534 I slot release: id 0 | task 5126 | stop processing: n_tokens = 978, truncated = 0 10.50.529.237 I slot print_timing: id 2 | task 5130 | prompt processing, n_tokens = 956, progress = 1.00, t = 4.60 s / 207.86 tokens per second 10.50.634.978 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 978, t_last = 390484116664 10.50.635.042 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 333.112 MiB) 10.50.644.100 I slot launch_slot_: id 0 | task 5139 | processing task, is_child = 0 10.51.063.309 I slot print_timing: id 1 | task 5135 | prompt eval time = 924.79 ms / 119 tokens ( 7.77 ms per token, 128.68 tokens per second) 10.51.063.312 I slot print_timing: id 1 | task 5135 | eval time = 428.86 ms / 2 tokens ( 428.86 ms per token, 2.33 tokens per second) 10.51.063.312 I slot print_timing: id 1 | task 5135 | total time = 1353.65 ms / 121 tokens 10.51.063.312 I slot print_timing: id 1 | task 5135 | graphs reused = 3659 10.51.063.313 I slot print_timing: id 1 | task 5135 | graph reallocs = 0 / 0 (same size) / (changed size) 10.51.063.357 I slot release: id 1 | task 5135 | stop processing: n_tokens = 973, truncated = 0 10.51.063.509 I slot print_timing: id 2 | task 5130 | prompt eval time = 4707.53 ms / 960 tokens ( 4.90 ms per token, 203.93 tokens per second) 10.51.063.512 I slot print_timing: id 2 | task 5130 | eval time = 428.90 ms / 2 tokens ( 428.90 ms per token, 2.33 tokens per second) 10.51.063.512 I slot print_timing: id 2 | task 5130 | total time = 5136.43 ms / 962 tokens 10.51.063.512 I slot print_timing: id 2 | task 5130 | graphs reused = 3659 10.51.063.513 I slot print_timing: id 2 | task 5130 | graph reallocs = 0 / 0 (same size) / (changed size) 10.51.063.542 I slot release: id 2 | task 5130 | stop processing: n_tokens = 961, truncated = 0 10.51.063.704 I slot print_timing: id 3 | task 5136 | prompt eval time = 920.21 ms / 123 tokens ( 7.48 ms per token, 133.67 tokens per second) 10.51.063.705 I slot print_timing: id 3 | task 5136 | eval time = 428.73 ms / 2 tokens ( 428.73 ms per token, 2.33 tokens per second) 10.51.063.706 I slot print_timing: id 3 | task 5136 | total time = 1348.94 ms / 125 tokens 10.51.063.706 I slot print_timing: id 3 | task 5136 | graphs reused = 3659 10.51.063.707 I slot print_timing: id 3 | task 5136 | graph reallocs = 0 / 0 (same size) / (changed size) 10.51.063.730 I slot release: id 3 | task 5136 | stop processing: n_tokens = 977, truncated = 0 10.51.414.995 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 973, t_last = 390484653487 10.51.415.052 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 333.444 MiB) 10.52.097.011 I slot launch_slot_: id 1 | task 5143 | processing task, is_child = 0 10.52.097.072 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 334.500 MiB) 10.52.106.483 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 336.788 MiB) 10.52.116.444 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 961, t_last = 390484653672 10.52.116.545 I slot launch_slot_: id 2 | task 5144 | processing task, is_child = 0 10.52.116.593 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 977, t_last = 390484653860 10.52.116.669 I slot launch_slot_: id 3 | task 5145 | processing task, is_child = 0 10.53.662.141 I slot print_timing: id 0 | task 5139 | prompt processing, n_tokens = 821, progress = 1.00, t = 3.02 s / 272.03 tokens per second 10.55.122.662 I slot print_timing: id 1 | task 5143 | prompt processing, n_tokens = 533, progress = 0.34, t = 3.00 s / 177.43 tokens per second 10.55.122.687 I slot print_timing: id 2 | task 5144 | prompt processing, n_tokens = 533, progress = 0.33, t = 3.00 s / 177.44 tokens per second 10.55.122.700 I slot print_timing: id 3 | task 5145 | prompt processing, n_tokens = 533, progress = 0.33, t = 3.00 s / 177.44 tokens per second 10.58.062.136 I slot print_timing: id 0 | task 5139 | prompt eval time = 4478.54 ms / 825 tokens ( 5.43 ms per token, 184.21 tokens per second) 10.58.062.139 I slot print_timing: id 0 | task 5139 | eval time = 2939.48 ms / 2 tokens ( 2939.48 ms per token, 0.34 tokens per second) 10.58.062.139 I slot print_timing: id 0 | task 5139 | total time = 7418.02 ms / 827 tokens 10.58.062.140 I slot print_timing: id 0 | task 5139 | graphs reused = 3659 10.58.062.140 I slot print_timing: id 0 | task 5139 | graph reallocs = 0 / 0 (same size) / (changed size) 10.58.062.182 I slot release: id 0 | task 5139 | stop processing: n_tokens = 826, truncated = 0 10.58.062.197 I slot print_timing: id 1 | task 5143 | prompt processing, n_tokens = 1071, progress = 0.67, t = 5.94 s / 180.20 tokens per second 10.58.065.121 I slot print_timing: id 2 | task 5144 | prompt processing, n_tokens = 1113, progress = 0.68, t = 5.94 s / 187.27 tokens per second 10.58.068.545 I slot print_timing: id 3 | task 5145 | prompt processing, n_tokens = 1099, progress = 0.68, t = 5.94 s / 184.91 tokens per second 10.59.585.347 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 826, t_last = 390491652312 10.59.585.409 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 336.065 MiB) 10.59.683.370 I slot launch_slot_: id 0 | task 5150 | processing task, is_child = 0 10.59.683.454 I slot print_timing: id 1 | task 5143 | prompt processing, n_tokens = 1374, progress = 0.87, t = 7.47 s / 184.01 tokens per second 10.59.685.519 I slot print_timing: id 2 | task 5144 | prompt processing, n_tokens = 1374, progress = 0.84, t = 7.47 s / 184.02 tokens per second 10.59.687.401 I slot print_timing: id 3 | task 5145 | prompt processing, n_tokens = 1374, progress = 0.85, t = 7.47 s / 184.02 tokens per second 11.01.786.263 I slot print_timing: id 1 | task 5143 | prompt processing, n_tokens = 1583, progress = 1.00, t = 9.57 s / 165.43 tokens per second 11.01.789.141 I slot print_timing: id 2 | task 5144 | prompt processing, n_tokens = 1625, progress = 1.00, t = 9.57 s / 169.82 tokens per second 11.01.791.436 I slot print_timing: id 3 | task 5145 | prompt processing, n_tokens = 1611, progress = 1.00, t = 9.57 s / 168.36 tokens per second 11.03.416.410 I slot print_timing: id 1 | task 5143 | prompt eval time = 10188.39 ms / 1587 tokens ( 6.42 ms per token, 155.77 tokens per second) 11.03.416.416 I slot print_timing: id 1 | task 5143 | eval time = 1109.49 ms / 2 tokens ( 1109.49 ms per token, 0.90 tokens per second) 11.03.416.417 I slot print_timing: id 1 | task 5143 | total time = 11297.88 ms / 1589 tokens 11.03.416.417 I slot print_timing: id 1 | task 5143 | graphs reused = 3659 11.03.416.418 I slot print_timing: id 1 | task 5143 | graph reallocs = 0 / 0 (same size) / (changed size) 11.03.416.486 I slot release: id 1 | task 5143 | stop processing: n_tokens = 1588, truncated = 0 11.03.416.648 I slot print_timing: id 2 | task 5144 | prompt eval time = 10188.50 ms / 1629 tokens ( 6.25 ms per token, 159.89 tokens per second) 11.03.416.652 I slot print_timing: id 2 | task 5144 | eval time = 1109.55 ms / 2 tokens ( 1109.55 ms per token, 0.90 tokens per second) 11.03.416.652 I slot print_timing: id 2 | task 5144 | total time = 11298.05 ms / 1631 tokens 11.03.416.653 I slot print_timing: id 2 | task 5144 | graphs reused = 3659 11.03.416.653 I slot print_timing: id 2 | task 5144 | graph reallocs = 0 / 0 (same size) / (changed size) 11.03.416.695 I slot release: id 2 | task 5144 | stop processing: n_tokens = 1630, truncated = 0 11.03.416.857 I slot print_timing: id 3 | task 5145 | prompt eval time = 10188.60 ms / 1615 tokens ( 6.31 ms per token, 158.51 tokens per second) 11.03.416.860 I slot print_timing: id 3 | task 5145 | eval time = 1109.59 ms / 2 tokens ( 1109.59 ms per token, 0.90 tokens per second) 11.03.416.860 I slot print_timing: id 3 | task 5145 | total time = 11298.19 ms / 1617 tokens 11.03.416.861 I slot print_timing: id 3 | task 5145 | graphs reused = 3659 11.03.416.861 I slot print_timing: id 3 | task 5145 | graph reallocs = 0 / 0 (same size) / (changed size) 11.03.416.905 I slot release: id 3 | task 5145 | stop processing: n_tokens = 1616, truncated = 0 11.03.416.913 I slot print_timing: id 0 | task 5150 | prompt processing, n_tokens = 1113, progress = 0.68, t = 3.73 s / 298.16 tokens per second 11.03.425.046 I slot print_timing: id 0 | task 5150 | prompt processing, n_tokens = 1374, progress = 0.84, t = 3.74 s / 367.22 tokens per second 11.03.950.025 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1588, t_last = 390497006616 11.03.950.102 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 353.996 MiB) 11.04.448.754 I slot launch_slot_: id 1 | task 5156 | processing task, is_child = 0 11.04.448.836 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 354.387 MiB) 11.04.457.915 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 357.653 MiB) 11.04.465.975 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1630, t_last = 390497006825 11.04.466.095 I slot launch_slot_: id 2 | task 5157 | processing task, is_child = 0 11.04.466.168 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.816 (> 0.100 thold), f_keep = 0.868 11.04.466.189 I slot launch_slot_: id 3 | task 5158 | processing task, is_child = 0 11.04.466.196 I slot print_timing: id 0 | task 5150 | prompt processing, n_tokens = 1625, progress = 1.00, t = 4.27 s / 380.86 tokens per second 11.06.263.751 I slot print_timing: id 0 | task 5150 | prompt eval time = 5999.36 ms / 1629 tokens ( 3.68 ms per token, 271.53 tokens per second) 11.06.263.754 I slot print_timing: id 0 | task 5150 | eval time = 581.00 ms / 2 tokens ( 581.00 ms per token, 1.72 tokens per second) 11.06.263.754 I slot print_timing: id 0 | task 5150 | total time = 6580.36 ms / 1631 tokens 11.06.263.755 I slot print_timing: id 0 | task 5150 | graphs reused = 3659 11.06.263.755 I slot print_timing: id 0 | task 5150 | graph reallocs = 0 / 0 (same size) / (changed size) 11.06.263.822 I slot release: id 0 | task 5150 | stop processing: n_tokens = 1630, truncated = 0 11.06.784.855 I slot print_timing: id 3 | task 5158 | prompt eval time = 1795.56 ms / 344 tokens ( 5.22 ms per token, 191.58 tokens per second) 11.06.784.858 I slot print_timing: id 3 | task 5158 | eval time = 520.84 ms / 2 tokens ( 520.84 ms per token, 1.92 tokens per second) 11.06.784.858 I slot print_timing: id 3 | task 5158 | total time = 2316.39 ms / 346 tokens 11.06.784.859 I slot print_timing: id 3 | task 5158 | graphs reused = 3659 11.06.784.859 I slot print_timing: id 3 | task 5158 | graph reallocs = 0 / 0 (same size) / (changed size) 11.06.784.937 I slot release: id 3 | task 5158 | stop processing: n_tokens = 1719, truncated = 0 11.06.784.946 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1630, t_last = 390499853952 11.06.785.032 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 353.566 MiB) 11.06.795.943 I slot launch_slot_: id 0 | task 5162 | processing task, is_child = 0 11.06.796.024 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 352.666 MiB) 11.06.804.236 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1719, t_last = 390500375067 11.06.804.348 I slot launch_slot_: id 3 | task 5163 | processing task, is_child = 0 11.08.807.326 I slot print_timing: id 1 | task 5156 | prompt processing, n_tokens = 725, progress = 0.87, t = 4.16 s / 174.12 tokens per second 11.08.810.790 I slot print_timing: id 2 | task 5157 | prompt processing, n_tokens = 725, progress = 0.84, t = 4.16 s / 174.13 tokens per second 11.09.876.651 I slot print_timing: id 0 | task 5162 | prompt processing, n_tokens = 277, progress = 0.33, t = 3.07 s / 90.16 tokens per second 11.09.876.663 I slot print_timing: id 1 | task 5156 | prompt processing, n_tokens = 834, progress = 1.00, t = 5.41 s / 154.20 tokens per second 11.09.936.635 I slot print_timing: id 2 | task 5157 | prompt processing, n_tokens = 861, progress = 1.00, t = 5.41 s / 159.20 tokens per second 11.09.938.878 I slot print_timing: id 3 | task 5163 | prompt processing, n_tokens = 277, progress = 0.32, t = 3.07 s / 90.28 tokens per second 11.10.451.501 I slot print_timing: id 0 | task 5162 | prompt processing, n_tokens = 326, progress = 0.39, t = 3.65 s / 89.39 tokens per second 11.10.454.185 I slot print_timing: id 3 | task 5163 | prompt processing, n_tokens = 343, progress = 0.40, t = 3.64 s / 94.16 tokens per second 11.11.816.963 I slot print_timing: id 1 | task 5156 | prompt eval time = 5983.07 ms / 838 tokens ( 7.14 ms per token, 140.06 tokens per second) 11.11.816.968 I slot print_timing: id 1 | task 5156 | eval time = 1365.65 ms / 2 tokens ( 1365.65 ms per token, 0.73 tokens per second) 11.11.816.969 I slot print_timing: id 1 | task 5156 | total time = 7348.71 ms / 840 tokens 11.11.816.969 I slot print_timing: id 1 | task 5156 | graphs reused = 3659 11.11.816.970 I slot print_timing: id 1 | task 5156 | graph reallocs = 0 / 0 (same size) / (changed size) 11.11.817.016 I slot release: id 1 | task 5156 | stop processing: n_tokens = 839, truncated = 0 11.11.817.172 I slot print_timing: id 2 | task 5157 | prompt eval time = 5983.13 ms / 865 tokens ( 6.92 ms per token, 144.57 tokens per second) 11.11.817.175 I slot print_timing: id 2 | task 5157 | eval time = 1365.68 ms / 2 tokens ( 1365.68 ms per token, 0.73 tokens per second) 11.11.817.175 I slot print_timing: id 2 | task 5157 | total time = 7348.81 ms / 867 tokens 11.11.817.175 I slot print_timing: id 2 | task 5157 | graphs reused = 3659 11.11.817.176 I slot print_timing: id 2 | task 5157 | graph reallocs = 0 / 0 (same size) / (changed size) 11.11.817.206 I slot release: id 2 | task 5157 | stop processing: n_tokens = 866, truncated = 0 11.11.817.216 I slot print_timing: id 0 | task 5162 | prompt processing, n_tokens = 716, progress = 0.85, t = 5.01 s / 142.84 tokens per second 11.11.820.781 I slot print_timing: id 3 | task 5163 | prompt processing, n_tokens = 716, progress = 0.83, t = 5.01 s / 142.96 tokens per second 11.12.136.289 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 839, t_last = 390505407146 11.12.136.347 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 354.465 MiB) 11.12.478.206 I slot launch_slot_: id 1 | task 5169 | processing task, is_child = 0 11.12.478.269 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 352.627 MiB) 11.12.485.913 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 866, t_last = 390505407336 11.12.486.001 I slot launch_slot_: id 2 | task 5170 | processing task, is_child = 0 11.12.486.008 I slot print_timing: id 0 | task 5162 | prompt processing, n_tokens = 838, progress = 1.00, t = 5.33 s / 157.17 tokens per second 11.12.488.098 I slot print_timing: id 3 | task 5163 | prompt processing, n_tokens = 855, progress = 1.00, t = 5.33 s / 160.47 tokens per second 11.13.861.200 I slot print_timing: id 0 | task 5162 | prompt eval time = 6442.47 ms / 842 tokens ( 7.65 ms per token, 130.70 tokens per second) 11.13.861.203 I slot print_timing: id 0 | task 5162 | eval time = 614.37 ms / 2 tokens ( 614.37 ms per token, 1.63 tokens per second) 11.13.861.204 I slot print_timing: id 0 | task 5162 | total time = 7056.83 ms / 844 tokens 11.13.861.204 I slot print_timing: id 0 | task 5162 | graphs reused = 3659 11.13.861.205 I slot print_timing: id 0 | task 5162 | graph reallocs = 0 / 0 (same size) / (changed size) 11.13.861.246 I slot release: id 0 | task 5162 | stop processing: n_tokens = 843, truncated = 0 11.13.861.400 I slot print_timing: id 3 | task 5163 | prompt eval time = 6438.68 ms / 859 tokens ( 7.50 ms per token, 133.41 tokens per second) 11.13.861.402 I slot print_timing: id 3 | task 5163 | eval time = 614.40 ms / 2 tokens ( 614.40 ms per token, 1.63 tokens per second) 11.13.861.402 I slot print_timing: id 3 | task 5163 | total time = 7053.08 ms / 861 tokens 11.13.861.402 I slot print_timing: id 3 | task 5163 | graphs reused = 3659 11.13.861.403 I slot print_timing: id 3 | task 5163 | graph reallocs = 0 / 0 (same size) / (changed size) 11.13.861.428 I slot release: id 3 | task 5163 | stop processing: n_tokens = 860, truncated = 0 11.13.927.886 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 843, t_last = 390507451376 11.13.927.942 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 355.423 MiB) 11.14.181.385 I slot launch_slot_: id 0 | task 5174 | processing task, is_child = 0 11.14.181.441 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 353.839 MiB) 11.14.191.721 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 860, t_last = 390507451558 11.14.191.799 I slot launch_slot_: id 3 | task 5175 | processing task, is_child = 0 11.16.026.961 I slot print_timing: id 1 | task 5169 | prompt processing, n_tokens = 716, progress = 0.81, t = 3.41 s / 210.10 tokens per second 11.16.029.644 I slot print_timing: id 2 | task 5170 | prompt processing, n_tokens = 628, progress = 0.81, t = 3.41 s / 184.28 tokens per second 11.17.260.700 I slot print_timing: id 1 | task 5169 | prompt processing, n_tokens = 882, progress = 1.00, t = 4.64 s / 190.04 tokens per second 11.17.264.044 I slot print_timing: id 2 | task 5170 | prompt processing, n_tokens = 776, progress = 0.99, t = 4.64 s / 167.20 tokens per second 11.18.733.802 I slot print_timing: id 0 | task 5174 | prompt processing, n_tokens = 571, progress = 0.83, t = 4.54 s / 125.73 tokens per second 11.18.736.659 I slot print_timing: id 3 | task 5175 | prompt processing, n_tokens = 628, progress = 0.84, t = 4.54 s / 138.39 tokens per second 11.19.396.547 I slot print_timing: id 1 | task 5169 | prompt eval time = 6245.64 ms / 886 tokens ( 7.05 ms per token, 141.86 tokens per second) 11.19.396.550 I slot print_timing: id 1 | task 5169 | eval time = 662.92 ms / 2 tokens ( 662.92 ms per token, 1.51 tokens per second) 11.19.396.550 I slot print_timing: id 1 | task 5169 | total time = 6908.56 ms / 888 tokens 11.19.396.551 I slot print_timing: id 1 | task 5169 | graphs reused = 3659 11.19.396.551 I slot print_timing: id 1 | task 5169 | graph reallocs = 0 / 0 (same size) / (changed size) 11.19.396.593 I slot release: id 1 | task 5169 | stop processing: n_tokens = 887, truncated = 0 11.19.396.749 I slot print_timing: id 2 | task 5170 | prompt eval time = 6245.75 ms / 780 tokens ( 8.01 ms per token, 124.88 tokens per second) 11.19.396.753 I slot print_timing: id 2 | task 5170 | eval time = 662.96 ms / 2 tokens ( 662.96 ms per token, 1.51 tokens per second) 11.19.396.753 I slot print_timing: id 2 | task 5170 | total time = 6908.71 ms / 782 tokens 11.19.396.753 I slot print_timing: id 2 | task 5170 | graphs reused = 3659 11.19.396.754 I slot print_timing: id 2 | task 5170 | graph reallocs = 0 / 0 (same size) / (changed size) 11.19.396.784 I slot release: id 2 | task 5170 | stop processing: n_tokens = 781, truncated = 0 11.19.396.791 I slot print_timing: id 0 | task 5174 | prompt processing, n_tokens = 687, progress = 0.99, t = 5.20 s / 132.00 tokens per second 11.19.399.406 I slot print_timing: id 3 | task 5175 | prompt processing, n_tokens = 745, progress = 0.99, t = 5.20 s / 143.25 tokens per second 11.19.488.185 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 887, t_last = 390512986723 11.19.497.655 I slot launch_slot_: id 1 | task 5181 | processing task, is_child = 0 11.19.497.706 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 353.683 MiB) 11.19.507.390 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 781, t_last = 390512986914 11.19.507.464 I slot launch_slot_: id 2 | task 5182 | processing task, is_child = 0 11.19.985.936 I slot print_timing: id 0 | task 5174 | prompt eval time = 5296.21 ms / 691 tokens ( 7.66 ms per token, 130.47 tokens per second) 11.19.985.938 I slot print_timing: id 0 | task 5174 | eval time = 497.92 ms / 2 tokens ( 497.92 ms per token, 2.01 tokens per second) 11.19.985.939 I slot print_timing: id 0 | task 5174 | total time = 5794.13 ms / 693 tokens 11.19.985.939 I slot print_timing: id 0 | task 5174 | graphs reused = 3659 11.19.985.939 I slot print_timing: id 0 | task 5174 | graph reallocs = 0 / 0 (same size) / (changed size) 11.19.985.978 I slot release: id 0 | task 5174 | stop processing: n_tokens = 692, truncated = 0 11.19.986.129 I slot print_timing: id 3 | task 5175 | prompt eval time = 5292.56 ms / 749 tokens ( 7.07 ms per token, 141.52 tokens per second) 11.19.986.132 I slot print_timing: id 3 | task 5175 | eval time = 497.95 ms / 2 tokens ( 497.95 ms per token, 2.01 tokens per second) 11.19.986.132 I slot print_timing: id 3 | task 5175 | total time = 5790.51 ms / 751 tokens 11.19.986.132 I slot print_timing: id 3 | task 5175 | graphs reused = 3659 11.19.986.133 I slot print_timing: id 3 | task 5175 | graph reallocs = 0 / 0 (same size) / (changed size) 11.19.986.163 I slot release: id 3 | task 5175 | stop processing: n_tokens = 750, truncated = 0 11.22.570.838 I slot print_timing: id 1 | task 5181 | prompt eval time = 3027.93 ms / 712 tokens ( 4.25 ms per token, 235.14 tokens per second) 11.22.570.840 I slot print_timing: id 1 | task 5181 | eval time = 35.43 ms / 2 tokens ( 35.43 ms per token, 28.22 tokens per second) 11.22.570.841 I slot print_timing: id 1 | task 5181 | total time = 3063.36 ms / 714 tokens 11.22.570.841 I slot print_timing: id 1 | task 5181 | graphs reused = 3659 11.22.570.842 I slot print_timing: id 1 | task 5181 | graph reallocs = 0 / 0 (same size) / (changed size) 11.22.570.878 I slot release: id 1 | task 5181 | stop processing: n_tokens = 713, truncated = 0 11.22.571.009 I slot print_timing: id 2 | task 5182 | prompt eval time = 3028.02 ms / 678 tokens ( 4.47 ms per token, 223.91 tokens per second) 11.22.571.011 I slot print_timing: id 2 | task 5182 | eval time = 35.45 ms / 2 tokens ( 35.45 ms per token, 28.21 tokens per second) 11.22.571.011 I slot print_timing: id 2 | task 5182 | total time = 3063.47 ms / 680 tokens 11.22.571.012 I slot print_timing: id 2 | task 5182 | graphs reused = 3659 11.22.571.012 I slot print_timing: id 2 | task 5182 | graph reallocs = 0 / 0 (same size) / (changed size) 11.22.571.035 I slot release: id 2 | task 5182 | stop processing: n_tokens = 679, truncated = 0 11.25.424.687 I srv operator(): operator(): cleaning up before exit...