/Users/minipro/quantdiff/work/llama-b11869/src/build/bin/llama-server -m /Users/minipro/quantdiff/models/campaign/dd45136a8b26/flint-UD-IQ1_M.gguf --host 127.0.0.1 --port 8091 -c 16384 -np 4 -ngl 999 -fa on --jinja --seed 1234 --chat-template-kwargs "{\"enable_thinking\": false}" --no-webui -a quant 0.00.042.533 W Setting 'enable_thinking' via --chat-template-kwargs is deprecated. Use --reasoning on / --reasoning off instead. 0.00.042.590 I srv llama_server: initializing ... 0.00.042.596 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.042.664 I srv init_listene: The UI is disabled 0.00.042.665 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.042.703 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) 0.00.044.357 I srv load_model: loading model '/Users/minipro/quantdiff/models/campaign/dd45136a8b26/flint-UD-IQ1_M.gguf' 0.00.775.190 I cmn init: llama threadpool init, n_threads = 8 0.00.867.850 I srv load_model: initializing, n_slots = 4, n_ctx_slot = 4096, kv_unified = 'false' 0.00.876.239 W srv init: chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve) 0.00.876.249 I srv server_run_i: model loaded 0.00.876.251 I srv server_on_li: listening on http://127.0.0.1:8091 0.29.758.956 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.29.759.009 I slot launch_slot_: id 0 | task 3 | processing task, is_child = 0 0.29.759.011 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.29.759.049 I slot launch_slot_: id 1 | task 2 | processing task, is_child = 0 0.29.759.050 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.29.759.086 I slot launch_slot_: id 2 | task 0 | processing task, is_child = 0 0.29.759.087 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.29.759.123 I slot launch_slot_: id 3 | task 1 | processing task, is_child = 0 0.30.823.184 I slot print_timing: id 2 | task 0 | prompt eval time = 1023.52 ms / 115 tokens ( 8.90 ms per token, 112.36 tokens per second) 0.30.823.190 I slot print_timing: id 2 | task 0 | eval time = 40.52 ms / 2 tokens ( 40.52 ms per token, 24.68 tokens per second) 0.30.823.190 I slot print_timing: id 2 | task 0 | total time = 1064.04 ms / 117 tokens 0.30.823.191 I slot print_timing: id 2 | task 0 | graphs reused = 1 0.30.823.191 I slot print_timing: id 2 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.30.823.210 I slot release: id 2 | task 0 | stop processing: n_tokens = 116, truncated = 0 0.30.823.306 I slot print_timing: id 3 | task 1 | prompt eval time = 1023.70 ms / 102 tokens ( 10.04 ms per token, 99.64 tokens per second) 0.30.823.308 I slot print_timing: id 3 | task 1 | eval time = 40.45 ms / 2 tokens ( 40.45 ms per token, 24.72 tokens per second) 0.30.823.309 I slot print_timing: id 3 | task 1 | total time = 1064.15 ms / 104 tokens 0.30.823.309 I slot print_timing: id 3 | task 1 | graphs reused = 1 0.30.823.309 I slot print_timing: id 3 | task 1 | graph reallocs = 0 / 0 (same size) / (changed size) 0.30.823.323 I slot release: id 3 | task 1 | stop processing: n_tokens = 103, truncated = 0 0.30.855.283 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.174 (> 0.100 thold), f_keep = 0.224 0.30.856.973 I slot launch_slot_: id 2 | task 8 | processing task, is_child = 0 0.30.858.409 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.186 (> 0.100 thold), f_keep = 0.252 0.30.858.485 I slot launch_slot_: id 3 | task 9 | processing task, is_child = 0 0.31.643.148 I slot print_timing: id 0 | task 3 | prompt eval time = 1023.16 ms / 122 tokens ( 8.39 ms per token, 119.24 tokens per second) 0.31.643.155 I slot print_timing: id 0 | task 3 | eval time = 860.86 ms / 6 tokens ( 172.17 ms per token, 5.81 tokens per second) 0.31.643.156 I slot print_timing: id 0 | task 3 | total time = 1884.02 ms / 128 tokens 0.31.643.156 I slot print_timing: id 0 | task 3 | graphs reused = 1 0.31.643.157 I slot print_timing: id 0 | task 3 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.643.178 I slot release: id 0 | task 3 | stop processing: n_tokens = 127, truncated = 0 0.31.643.268 I slot print_timing: id 1 | task 2 | prompt eval time = 1023.34 ms / 107 tokens ( 9.56 ms per token, 104.56 tokens per second) 0.31.643.270 I slot print_timing: id 1 | task 2 | eval time = 860.79 ms / 6 tokens ( 172.16 ms per token, 5.81 tokens per second) 0.31.643.270 I slot print_timing: id 1 | task 2 | total time = 1884.13 ms / 113 tokens 0.31.643.270 I slot print_timing: id 1 | task 2 | graphs reused = 1 0.31.643.271 I slot print_timing: id 1 | task 2 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.643.282 I slot release: id 1 | task 2 | stop processing: n_tokens = 112, truncated = 0 0.31.643.373 I slot print_timing: id 2 | task 8 | prompt eval time = 744.53 ms / 149 tokens ( 5.00 ms per token, 200.13 tokens per second) 0.31.643.375 I slot print_timing: id 2 | task 8 | eval time = 40.35 ms / 2 tokens ( 40.35 ms per token, 24.78 tokens per second) 0.31.643.375 I slot print_timing: id 2 | task 8 | total time = 784.88 ms / 151 tokens 0.31.643.375 I slot print_timing: id 2 | task 8 | graphs reused = 1 0.31.643.376 I slot print_timing: id 2 | task 8 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.643.387 I slot release: id 2 | task 8 | stop processing: n_tokens = 150, truncated = 0 0.31.643.484 I slot print_timing: id 3 | task 9 | prompt eval time = 744.60 ms / 140 tokens ( 5.32 ms per token, 188.02 tokens per second) 0.31.643.486 I slot print_timing: id 3 | task 9 | eval time = 40.37 ms / 2 tokens ( 40.37 ms per token, 24.77 tokens per second) 0.31.643.487 I slot print_timing: id 3 | task 9 | total time = 784.97 ms / 142 tokens 0.31.643.487 I slot print_timing: id 3 | task 9 | graphs reused = 1 0.31.643.487 I slot print_timing: id 3 | task 9 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.643.494 I slot release: id 3 | task 9 | stop processing: n_tokens = 141, truncated = 0 0.31.648.637 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.303 (> 0.100 thold), f_keep = 0.213 0.31.650.553 I slot launch_slot_: id 3 | task 13 | processing task, is_child = 0 0.31.655.140 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.252 (> 0.100 thold), f_keep = 0.213 0.31.655.219 I slot launch_slot_: id 0 | task 14 | processing task, is_child = 0 0.31.655.268 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.232 0.31.655.327 I slot launch_slot_: id 1 | task 15 | processing task, is_child = 0 0.31.655.352 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.138 (> 0.100 thold), f_keep = 0.173 0.31.655.411 I slot launch_slot_: id 2 | task 16 | processing task, is_child = 0 0.33.127.559 I slot print_timing: id 1 | task 15 | prompt eval time = 1431.79 ms / 138 tokens ( 10.38 ms per token, 96.38 tokens per second) 0.33.127.564 I slot print_timing: id 1 | task 15 | eval time = 40.33 ms / 2 tokens ( 40.33 ms per token, 24.80 tokens per second) 0.33.127.565 I slot print_timing: id 1 | task 15 | total time = 1472.12 ms / 140 tokens 0.33.127.566 I slot print_timing: id 1 | task 15 | graphs reused = 1 0.33.127.566 I slot print_timing: id 1 | task 15 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.127.593 I slot release: id 1 | task 15 | stop processing: n_tokens = 139, truncated = 0 0.33.127.681 I slot print_timing: id 2 | task 16 | prompt eval time = 1431.87 ms / 189 tokens ( 7.58 ms per token, 132.00 tokens per second) 0.33.127.684 I slot print_timing: id 2 | task 16 | eval time = 40.35 ms / 2 tokens ( 40.35 ms per token, 24.78 tokens per second) 0.33.127.684 I slot print_timing: id 2 | task 16 | total time = 1472.22 ms / 191 tokens 0.33.127.685 I slot print_timing: id 2 | task 16 | graphs reused = 1 0.33.127.685 I slot print_timing: id 2 | task 16 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.127.701 I slot release: id 2 | task 16 | stop processing: n_tokens = 190, truncated = 0 0.33.167.004 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.222 (> 0.100 thold), f_keep = 0.187 0.33.168.593 I slot launch_slot_: id 1 | task 21 | processing task, is_child = 0 0.33.171.090 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.239 (> 0.100 thold), f_keep = 0.137 0.33.171.165 I slot launch_slot_: id 2 | task 22 | processing task, is_child = 0 0.33.899.258 I slot print_timing: id 0 | task 14 | prompt eval time = 1431.71 ms / 107 tokens ( 13.38 ms per token, 74.74 tokens per second) 0.33.899.265 I slot print_timing: id 0 | task 14 | eval time = 812.12 ms / 6 tokens ( 162.43 ms per token, 6.16 tokens per second) 0.33.899.265 I slot print_timing: id 0 | task 14 | total time = 2243.84 ms / 113 tokens 0.33.899.266 I slot print_timing: id 0 | task 14 | graphs reused = 1 0.33.899.266 I slot print_timing: id 0 | task 14 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.899.283 I slot release: id 0 | task 14 | stop processing: n_tokens = 112, truncated = 0 0.33.937.089 I slot print_timing: id 3 | task 13 | prompt eval time = 1431.95 ms / 99 tokens ( 14.46 ms per token, 69.14 tokens per second) 0.33.937.096 I slot print_timing: id 3 | task 13 | eval time = 849.66 ms / 7 tokens ( 141.61 ms per token, 7.06 tokens per second) 0.33.937.097 I slot print_timing: id 3 | task 13 | total time = 2281.61 ms / 106 tokens 0.33.937.097 I slot print_timing: id 3 | task 13 | graphs reused = 1 0.33.937.098 I slot print_timing: id 3 | task 13 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.937.113 I slot release: id 3 | task 13 | stop processing: n_tokens = 105, truncated = 0 0.33.937.120 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.150 (> 0.100 thold), f_keep = 0.232 0.33.938.619 I slot launch_slot_: id 0 | task 27 | processing task, is_child = 0 0.34.425.050 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.193 (> 0.100 thold), f_keep = 0.248 0.34.425.159 I slot launch_slot_: id 3 | task 29 | processing task, is_child = 0 0.34.966.593 I slot print_timing: id 0 | task 27 | prompt eval time = 951.83 ms / 173 tokens ( 5.50 ms per token, 181.75 tokens per second) 0.34.966.598 I slot print_timing: id 0 | task 27 | eval time = 74.17 ms / 2 tokens ( 74.17 ms per token, 13.48 tokens per second) 0.34.966.599 I slot print_timing: id 0 | task 27 | total time = 1026.00 ms / 175 tokens 0.34.966.599 I slot print_timing: id 0 | task 27 | graphs reused = 1 0.34.966.599 I slot print_timing: id 0 | task 27 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.966.622 I slot release: id 0 | task 27 | stop processing: n_tokens = 174, truncated = 0 0.34.966.711 I slot print_timing: id 1 | task 21 | prompt eval time = 686.82 ms / 117 tokens ( 5.87 ms per token, 170.35 tokens per second) 0.34.966.713 I slot print_timing: id 1 | task 21 | eval time = 1108.72 ms / 6 tokens ( 221.74 ms per token, 4.51 tokens per second) 0.34.966.713 I slot print_timing: id 1 | task 21 | total time = 1795.54 ms / 123 tokens 0.34.966.713 I slot print_timing: id 1 | task 21 | graphs reused = 1 0.34.966.714 I slot print_timing: id 1 | task 21 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.966.724 I slot release: id 1 | task 21 | stop processing: n_tokens = 122, truncated = 0 0.34.966.815 I slot print_timing: id 2 | task 22 | prompt eval time = 686.92 ms / 109 tokens ( 6.30 ms per token, 158.68 tokens per second) 0.34.966.816 I slot print_timing: id 2 | task 22 | eval time = 1108.70 ms / 6 tokens ( 221.74 ms per token, 4.51 tokens per second) 0.34.966.817 I slot print_timing: id 2 | task 22 | total time = 1795.62 ms / 115 tokens 0.34.966.817 I slot print_timing: id 2 | task 22 | graphs reused = 1 0.34.966.817 I slot print_timing: id 2 | task 22 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.966.823 I slot release: id 2 | task 22 | stop processing: n_tokens = 114, truncated = 0 0.34.988.233 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.218 (> 0.100 thold), f_keep = 0.149 0.34.991.053 I slot launch_slot_: id 0 | task 33 | processing task, is_child = 0 0.34.993.352 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.203 (> 0.100 thold), f_keep = 0.213 0.34.993.427 I slot launch_slot_: id 1 | task 34 | processing task, is_child = 0 0.34.993.454 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.236 (> 0.100 thold), f_keep = 0.228 0.34.993.517 I slot launch_slot_: id 2 | task 35 | processing task, is_child = 0 0.35.876.245 I slot print_timing: id 3 | task 29 | prompt eval time = 540.44 ms / 135 tokens ( 4.00 ms per token, 249.80 tokens per second) 0.35.876.248 I slot print_timing: id 3 | task 29 | eval time = 909.31 ms / 4 tokens ( 303.10 ms per token, 3.30 tokens per second) 0.35.876.249 I slot print_timing: id 3 | task 29 | total time = 1449.75 ms / 139 tokens 0.35.876.249 I slot print_timing: id 3 | task 29 | graphs reused = 2 0.35.876.250 I slot print_timing: id 3 | task 29 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.876.273 I slot release: id 3 | task 29 | stop processing: n_tokens = 138, truncated = 0 0.35.913.078 I slot print_timing: id 0 | task 33 | prompt eval time = 882.45 ms / 119 tokens ( 7.42 ms per token, 134.85 tokens per second) 0.35.913.083 I slot print_timing: id 0 | task 33 | eval time = 37.10 ms / 2 tokens ( 37.10 ms per token, 26.95 tokens per second) 0.35.913.083 I slot print_timing: id 0 | task 33 | total time = 919.55 ms / 121 tokens 0.35.913.083 I slot print_timing: id 0 | task 33 | graphs reused = 2 0.35.913.084 I slot print_timing: id 0 | task 33 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.913.097 I slot release: id 0 | task 33 | stop processing: n_tokens = 120, truncated = 0 0.35.913.192 I slot print_timing: id 1 | task 34 | prompt eval time = 882.53 ms / 128 tokens ( 6.89 ms per token, 145.04 tokens per second) 0.35.913.196 I slot print_timing: id 1 | task 34 | eval time = 37.12 ms / 2 tokens ( 37.12 ms per token, 26.94 tokens per second) 0.35.913.196 I slot print_timing: id 1 | task 34 | total time = 919.65 ms / 130 tokens 0.35.913.196 I slot print_timing: id 1 | task 34 | graphs reused = 2 0.35.913.197 I slot print_timing: id 1 | task 34 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.913.207 I slot release: id 1 | task 34 | stop processing: n_tokens = 129, truncated = 0 0.35.913.300 I slot print_timing: id 2 | task 35 | prompt eval time = 882.60 ms / 110 tokens ( 8.02 ms per token, 124.63 tokens per second) 0.35.913.304 I slot print_timing: id 2 | task 35 | eval time = 37.14 ms / 2 tokens ( 37.14 ms per token, 26.93 tokens per second) 0.35.913.304 I slot print_timing: id 2 | task 35 | total time = 919.74 ms / 112 tokens 0.35.913.304 I slot print_timing: id 2 | task 35 | graphs reused = 2 0.35.913.305 I slot print_timing: id 2 | task 35 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.913.314 I slot release: id 2 | task 35 | stop processing: n_tokens = 111, truncated = 0 0.35.913.319 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.158 (> 0.100 thold), f_keep = 0.217 0.35.915.200 I slot launch_slot_: id 0 | task 39 | processing task, is_child = 0 0.35.920.092 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.250 (> 0.100 thold), f_keep = 0.202 0.35.920.166 I slot launch_slot_: id 1 | task 40 | processing task, is_child = 0 0.35.920.212 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.226 (> 0.100 thold), f_keep = 0.234 0.35.920.271 I slot launch_slot_: id 2 | task 41 | processing task, is_child = 0 0.35.920.295 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.200 (> 0.100 thold), f_keep = 0.188 0.35.920.355 I slot launch_slot_: id 3 | task 42 | processing task, is_child = 0 0.37.241.919 I slot print_timing: id 0 | task 39 | prompt eval time = 1280.78 ms / 165 tokens ( 7.76 ms per token, 128.83 tokens per second) 0.37.241.921 I slot print_timing: id 0 | task 39 | eval time = 40.78 ms / 2 tokens ( 40.78 ms per token, 24.52 tokens per second) 0.37.241.922 I slot print_timing: id 0 | task 39 | total time = 1321.56 ms / 167 tokens 0.37.241.922 I slot print_timing: id 0 | task 39 | graphs reused = 2 0.37.241.923 I slot print_timing: id 0 | task 39 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.241.942 I slot release: id 0 | task 39 | stop processing: n_tokens = 166, truncated = 0 0.37.242.194 I slot print_timing: id 3 | task 42 | prompt eval time = 1281.01 ms / 130 tokens ( 9.85 ms per token, 101.48 tokens per second) 0.37.242.196 I slot print_timing: id 3 | task 42 | eval time = 40.77 ms / 2 tokens ( 40.77 ms per token, 24.53 tokens per second) 0.37.242.197 I slot print_timing: id 3 | task 42 | total time = 1321.77 ms / 132 tokens 0.37.242.197 I slot print_timing: id 3 | task 42 | graphs reused = 2 0.37.242.197 I slot print_timing: id 3 | task 42 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.242.213 I slot release: id 3 | task 42 | stop processing: n_tokens = 131, truncated = 0 0.37.274.338 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.200 (> 0.100 thold), f_keep = 0.163 0.37.276.714 I slot launch_slot_: id 0 | task 47 | processing task, is_child = 0 0.37.278.094 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.194 (> 0.100 thold), f_keep = 0.198 0.37.278.165 I slot launch_slot_: id 3 | task 48 | processing task, is_child = 0 0.38.274.714 I slot print_timing: id 2 | task 41 | prompt eval time = 1280.93 ms / 115 tokens ( 11.14 ms per token, 89.78 tokens per second) 0.38.274.719 I slot print_timing: id 2 | task 41 | eval time = 1073.38 ms / 6 tokens ( 214.68 ms per token, 4.66 tokens per second) 0.38.274.720 I slot print_timing: id 2 | task 41 | total time = 2354.31 ms / 121 tokens 0.38.274.720 I slot print_timing: id 2 | task 41 | graphs reused = 2 0.38.274.721 I slot print_timing: id 2 | task 41 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.274.738 I slot release: id 2 | task 41 | stop processing: n_tokens = 120, truncated = 0 0.38.274.827 I slot print_timing: id 3 | task 48 | prompt eval time = 955.87 ms / 134 tokens ( 7.13 ms per token, 140.19 tokens per second) 0.38.274.829 I slot print_timing: id 3 | task 48 | eval time = 40.76 ms / 2 tokens ( 40.76 ms per token, 24.53 tokens per second) 0.38.274.829 I slot print_timing: id 3 | task 48 | total time = 996.63 ms / 136 tokens 0.38.274.829 I slot print_timing: id 3 | task 48 | graphs reused = 2 0.38.274.830 I slot print_timing: id 3 | task 48 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.274.844 I slot release: id 3 | task 48 | stop processing: n_tokens = 135, truncated = 0 0.38.307.834 I slot print_timing: id 1 | task 40 | prompt eval time = 1280.85 ms / 104 tokens ( 12.32 ms per token, 81.20 tokens per second) 0.38.307.836 I slot print_timing: id 1 | task 40 | eval time = 1106.60 ms / 7 tokens ( 184.43 ms per token, 5.42 tokens per second) 0.38.307.837 I slot print_timing: id 1 | task 40 | total time = 2387.45 ms / 111 tokens 0.38.307.837 I slot print_timing: id 1 | task 40 | graphs reused = 2 0.38.307.838 I slot print_timing: id 1 | task 40 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.307.854 I slot release: id 1 | task 40 | stop processing: n_tokens = 110, truncated = 0 0.38.307.859 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.260 (> 0.100 thold), f_keep = 0.225 0.38.309.688 I slot launch_slot_: id 2 | task 53 | processing task, is_child = 0 0.38.312.439 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.241 (> 0.100 thold), f_keep = 0.236 0.38.312.511 I slot launch_slot_: id 1 | task 54 | processing task, is_child = 0 0.38.312.537 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.193 0.38.312.597 I slot launch_slot_: id 3 | task 55 | processing task, is_child = 0 0.39.165.743 I slot print_timing: id 0 | task 47 | prompt eval time = 955.62 ms / 135 tokens ( 7.08 ms per token, 141.27 tokens per second) 0.39.165.749 I slot print_timing: id 0 | task 47 | eval time = 931.94 ms / 6 tokens ( 186.39 ms per token, 5.37 tokens per second) 0.39.165.749 I slot print_timing: id 0 | task 47 | total time = 1887.57 ms / 141 tokens 0.39.165.749 I slot print_timing: id 0 | task 47 | graphs reused = 2 0.39.165.750 I slot print_timing: id 0 | task 47 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.165.778 I slot release: id 0 | task 47 | stop processing: n_tokens = 140, truncated = 0 0.39.165.867 I slot print_timing: id 1 | task 54 | prompt eval time = 812.77 ms / 108 tokens ( 7.53 ms per token, 132.88 tokens per second) 0.39.165.869 I slot print_timing: id 1 | task 54 | eval time = 40.49 ms / 2 tokens ( 40.49 ms per token, 24.70 tokens per second) 0.39.165.870 I slot print_timing: id 1 | task 54 | total time = 853.27 ms / 110 tokens 0.39.165.870 I slot print_timing: id 1 | task 54 | graphs reused = 2 0.39.165.870 I slot print_timing: id 1 | task 54 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.165.881 I slot release: id 1 | task 54 | stop processing: n_tokens = 109, truncated = 0 0.39.165.977 I slot print_timing: id 2 | task 53 | prompt eval time = 812.86 ms / 104 tokens ( 7.82 ms per token, 127.94 tokens per second) 0.39.165.979 I slot print_timing: id 2 | task 53 | eval time = 40.50 ms / 2 tokens ( 40.50 ms per token, 24.69 tokens per second) 0.39.165.979 I slot print_timing: id 2 | task 53 | total time = 853.35 ms / 106 tokens 0.39.165.980 I slot print_timing: id 2 | task 53 | graphs reused = 2 0.39.165.980 I slot print_timing: id 2 | task 53 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.165.989 I slot release: id 2 | task 53 | stop processing: n_tokens = 105, truncated = 0 0.39.166.078 I slot print_timing: id 3 | task 55 | prompt eval time = 812.93 ms / 113 tokens ( 7.19 ms per token, 139.00 tokens per second) 0.39.166.080 I slot print_timing: id 3 | task 55 | eval time = 40.50 ms / 2 tokens ( 40.50 ms per token, 24.69 tokens per second) 0.39.166.080 I slot print_timing: id 3 | task 55 | total time = 853.44 ms / 115 tokens 0.39.166.081 I slot print_timing: id 3 | task 55 | graphs reused = 2 0.39.166.081 I slot print_timing: id 3 | task 55 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.166.089 I slot release: id 3 | task 55 | stop processing: n_tokens = 114, truncated = 0 0.39.171.206 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.268 (> 0.100 thold), f_keep = 0.186 0.39.173.265 I slot launch_slot_: id 0 | task 59 | processing task, is_child = 0 0.39.177.442 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.250 (> 0.100 thold), f_keep = 0.286 0.39.177.517 I slot launch_slot_: id 2 | task 61 | processing task, is_child = 0 0.39.177.562 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.193 (> 0.100 thold), f_keep = 0.239 0.39.177.621 I slot launch_slot_: id 1 | task 60 | processing task, is_child = 0 0.39.177.645 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.202 (> 0.100 thold), f_keep = 0.228 0.39.177.702 I slot launch_slot_: id 3 | task 62 | processing task, is_child = 0 0.40.378.650 I slot print_timing: id 2 | task 61 | prompt eval time = 1160.51 ms / 120 tokens ( 9.67 ms per token, 103.40 tokens per second) 0.40.378.652 I slot print_timing: id 2 | task 61 | eval time = 40.38 ms / 2 tokens ( 40.38 ms per token, 24.76 tokens per second) 0.40.378.653 I slot print_timing: id 2 | task 61 | total time = 1200.89 ms / 122 tokens 0.40.378.653 I slot print_timing: id 2 | task 61 | graphs reused = 2 0.40.378.653 I slot print_timing: id 2 | task 61 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.378.671 I slot release: id 2 | task 61 | stop processing: n_tokens = 121, truncated = 0 0.40.429.625 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.274 (> 0.100 thold), f_keep = 0.215 0.40.431.553 I slot launch_slot_: id 2 | task 67 | processing task, is_child = 0 0.40.932.073 I slot print_timing: id 2 | task 67 | prompt eval time = 459.44 ms / 95 tokens ( 4.84 ms per token, 206.77 tokens per second) 0.40.932.079 I slot print_timing: id 2 | task 67 | eval time = 41.07 ms / 2 tokens ( 41.07 ms per token, 24.35 tokens per second) 0.40.932.079 I slot print_timing: id 2 | task 67 | total time = 500.50 ms / 97 tokens 0.40.932.080 I slot print_timing: id 2 | task 67 | graphs reused = 2 0.40.932.081 I slot print_timing: id 2 | task 67 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.932.100 I slot release: id 2 | task 67 | stop processing: n_tokens = 96, truncated = 0 0.40.932.210 I slot print_timing: id 3 | task 62 | prompt eval time = 1160.60 ms / 129 tokens ( 9.00 ms per token, 111.15 tokens per second) 0.40.932.212 I slot print_timing: id 3 | task 62 | eval time = 593.85 ms / 6 tokens ( 118.77 ms per token, 8.42 tokens per second) 0.40.932.213 I slot print_timing: id 3 | task 62 | total time = 1754.45 ms / 135 tokens 0.40.932.213 I slot print_timing: id 3 | task 62 | graphs reused = 2 0.40.932.214 I slot print_timing: id 3 | task 62 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.932.227 I slot release: id 3 | task 62 | stop processing: n_tokens = 134, truncated = 0 0.40.965.837 I slot print_timing: id 0 | task 59 | prompt eval time = 1160.34 ms / 97 tokens ( 11.96 ms per token, 83.60 tokens per second) 0.40.965.844 I slot print_timing: id 0 | task 59 | eval time = 627.78 ms / 7 tokens ( 104.63 ms per token, 9.56 tokens per second) 0.40.965.845 I slot print_timing: id 0 | task 59 | total time = 1788.12 ms / 104 tokens 0.40.965.846 I slot print_timing: id 0 | task 59 | graphs reused = 2 0.40.965.846 I slot print_timing: id 0 | task 59 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.965.872 I slot release: id 0 | task 59 | stop processing: n_tokens = 103, truncated = 0 0.40.966.037 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.265 (> 0.100 thold), f_keep = 0.252 0.40.968.282 I slot launch_slot_: id 0 | task 72 | processing task, is_child = 0 0.40.971.752 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.149 (> 0.100 thold), f_keep = 0.271 0.40.971.874 I slot launch_slot_: id 2 | task 73 | processing task, is_child = 0 0.40.971.921 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.158 (> 0.100 thold), f_keep = 0.194 0.40.972.035 I slot launch_slot_: id 3 | task 74 | processing task, is_child = 0 0.42.167.865 I slot print_timing: id 3 | task 74 | prompt eval time = 1155.40 ms / 165 tokens ( 7.00 ms per token, 142.81 tokens per second) 0.42.167.870 I slot print_timing: id 3 | task 74 | eval time = 40.36 ms / 2 tokens ( 40.36 ms per token, 24.78 tokens per second) 0.42.167.870 I slot print_timing: id 3 | task 74 | total time = 1195.76 ms / 167 tokens 0.42.167.871 I slot print_timing: id 3 | task 74 | graphs reused = 2 0.42.167.871 I slot print_timing: id 3 | task 74 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.167.896 I slot release: id 3 | task 74 | stop processing: n_tokens = 166, truncated = 0 0.42.204.705 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.208 (> 0.100 thold), f_keep = 0.157 0.42.207.035 I slot launch_slot_: id 3 | task 79 | processing task, is_child = 0 0.42.621.608 I slot print_timing: id 1 | task 60 | prompt eval time = 1160.43 ms / 135 tokens ( 8.60 ms per token, 116.34 tokens per second) 0.42.621.614 I slot print_timing: id 1 | task 60 | eval time = 2283.44 ms / 12 tokens ( 207.59 ms per token, 4.82 tokens per second) 0.42.621.614 I slot print_timing: id 1 | task 60 | total time = 3443.88 ms / 147 tokens 0.42.621.614 I slot print_timing: id 1 | task 60 | graphs reused = 2 0.42.621.615 I slot print_timing: id 1 | task 60 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.621.635 I slot release: id 1 | task 60 | stop processing: n_tokens = 146, truncated = 0 0.42.705.124 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.165 (> 0.100 thold), f_keep = 0.178 0.42.707.779 I slot launch_slot_: id 1 | task 82 | processing task, is_child = 0 0.43.185.600 I slot print_timing: id 0 | task 72 | prompt eval time = 1155.19 ms / 98 tokens ( 11.79 ms per token, 84.83 tokens per second) 0.43.185.603 I slot print_timing: id 0 | task 72 | eval time = 1058.36 ms / 6 tokens ( 211.67 ms per token, 4.72 tokens per second) 0.43.185.604 I slot print_timing: id 0 | task 72 | total time = 2213.55 ms / 104 tokens 0.43.185.604 I slot print_timing: id 0 | task 72 | graphs reused = 2 0.43.185.605 I slot print_timing: id 0 | task 72 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.185.622 I slot release: id 0 | task 72 | stop processing: n_tokens = 103, truncated = 0 0.43.185.765 I slot print_timing: id 2 | task 73 | prompt eval time = 1155.33 ms / 174 tokens ( 6.64 ms per token, 150.61 tokens per second) 0.43.185.767 I slot print_timing: id 2 | task 73 | eval time = 1058.36 ms / 6 tokens ( 211.67 ms per token, 4.72 tokens per second) 0.43.185.767 I slot print_timing: id 2 | task 73 | total time = 2213.69 ms / 180 tokens 0.43.185.768 I slot print_timing: id 2 | task 73 | graphs reused = 2 0.43.185.768 I slot print_timing: id 2 | task 73 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.185.780 I slot release: id 2 | task 73 | stop processing: n_tokens = 179, truncated = 0 0.43.245.120 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.165 (> 0.100 thold), f_keep = 0.252 0.43.246.355 I slot launch_slot_: id 0 | task 86 | processing task, is_child = 0 0.43.249.093 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.186 (> 0.100 thold), f_keep = 0.145 0.43.249.170 I slot launch_slot_: id 2 | task 85 | processing task, is_child = 0 0.44.114.446 I slot print_timing: id 3 | task 79 | prompt eval time = 498.08 ms / 125 tokens ( 3.98 ms per token, 250.96 tokens per second) 0.44.114.449 I slot print_timing: id 3 | task 79 | eval time = 1409.32 ms / 4 tokens ( 469.77 ms per token, 2.13 tokens per second) 0.44.114.449 I slot print_timing: id 3 | task 79 | total time = 1907.40 ms / 129 tokens 0.44.114.449 I slot print_timing: id 3 | task 79 | graphs reused = 2 0.44.114.450 I slot print_timing: id 3 | task 79 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.114.473 I slot release: id 3 | task 79 | stop processing: n_tokens = 128, truncated = 0 0.44.216.936 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.195 (> 0.100 thold), f_keep = 0.203 0.44.218.865 I slot launch_slot_: id 3 | task 89 | processing task, is_child = 0 0.44.644.664 I slot print_timing: id 0 | task 86 | prompt eval time = 967.54 ms / 158 tokens ( 6.12 ms per token, 163.30 tokens per second) 0.44.644.666 I slot print_timing: id 0 | task 86 | eval time = 427.94 ms / 2 tokens ( 427.94 ms per token, 2.34 tokens per second) 0.44.644.667 I slot print_timing: id 0 | task 86 | total time = 1395.48 ms / 160 tokens 0.44.644.667 I slot print_timing: id 0 | task 86 | graphs reused = 2 0.44.644.667 I slot print_timing: id 0 | task 86 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.644.686 I slot release: id 0 | task 86 | stop processing: n_tokens = 159, truncated = 0 0.44.644.783 I slot print_timing: id 1 | task 82 | prompt eval time = 537.22 ms / 158 tokens ( 3.40 ms per token, 294.11 tokens per second) 0.44.644.787 I slot print_timing: id 1 | task 82 | eval time = 1399.78 ms / 4 tokens ( 466.59 ms per token, 2.14 tokens per second) 0.44.644.788 I slot print_timing: id 1 | task 82 | total time = 1937.00 ms / 162 tokens 0.44.644.788 I slot print_timing: id 1 | task 82 | graphs reused = 2 0.44.644.788 I slot print_timing: id 1 | task 82 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.644.799 I slot release: id 1 | task 82 | stop processing: n_tokens = 161, truncated = 0 0.44.709.732 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.218 (> 0.100 thold), f_keep = 0.164 0.44.711.527 I slot launch_slot_: id 0 | task 92 | processing task, is_child = 0 0.44.714.040 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.161 0.44.714.120 I slot launch_slot_: id 1 | task 93 | processing task, is_child = 0 0.45.270.105 I slot print_timing: id 2 | task 85 | prompt eval time = 967.73 ms / 140 tokens ( 6.91 ms per token, 144.67 tokens per second) 0.45.270.108 I slot print_timing: id 2 | task 85 | eval time = 1053.17 ms / 4 tokens ( 351.06 ms per token, 2.85 tokens per second) 0.45.270.109 I slot print_timing: id 2 | task 85 | total time = 2020.90 ms / 144 tokens 0.45.270.109 I slot print_timing: id 2 | task 85 | graphs reused = 2 0.45.270.109 I slot print_timing: id 2 | task 85 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.270.130 I slot release: id 2 | task 85 | stop processing: n_tokens = 143, truncated = 0 0.45.344.743 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.167 (> 0.100 thold), f_keep = 0.182 0.45.346.792 I slot launch_slot_: id 2 | task 96 | processing task, is_child = 0 0.45.810.317 I slot print_timing: id 0 | task 92 | prompt eval time = 630.42 ms / 119 tokens ( 5.30 ms per token, 188.76 tokens per second) 0.45.810.324 I slot print_timing: id 0 | task 92 | eval time = 465.76 ms / 2 tokens ( 465.76 ms per token, 2.15 tokens per second) 0.45.810.326 I slot print_timing: id 0 | task 92 | total time = 1096.18 ms / 121 tokens 0.45.810.326 I slot print_timing: id 0 | task 92 | graphs reused = 2 0.45.810.327 I slot print_timing: id 0 | task 92 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.810.347 I slot release: id 0 | task 92 | stop processing: n_tokens = 120, truncated = 0 0.45.810.459 I slot print_timing: id 1 | task 93 | prompt eval time = 630.49 ms / 114 tokens ( 5.53 ms per token, 180.81 tokens per second) 0.45.810.461 I slot print_timing: id 1 | task 93 | eval time = 465.81 ms / 2 tokens ( 465.81 ms per token, 2.15 tokens per second) 0.45.810.462 I slot print_timing: id 1 | task 93 | total time = 1096.30 ms / 116 tokens 0.45.810.462 I slot print_timing: id 1 | task 93 | graphs reused = 2 0.45.810.462 I slot print_timing: id 1 | task 93 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.810.474 I slot release: id 1 | task 93 | stop processing: n_tokens = 115, truncated = 0 0.45.810.629 I slot print_timing: id 3 | task 89 | prompt eval time = 490.86 ms / 133 tokens ( 3.69 ms per token, 270.95 tokens per second) 0.45.810.630 I slot print_timing: id 3 | task 89 | eval time = 1100.90 ms / 4 tokens ( 366.97 ms per token, 2.73 tokens per second) 0.45.810.631 I slot print_timing: id 3 | task 89 | total time = 1591.76 ms / 137 tokens 0.45.810.631 I slot print_timing: id 3 | task 89 | graphs reused = 2 0.45.810.632 I slot print_timing: id 3 | task 89 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.810.641 I slot release: id 3 | task 89 | stop processing: n_tokens = 136, truncated = 0 0.45.850.526 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.273 (> 0.100 thold), f_keep = 0.199 0.45.852.240 I slot launch_slot_: id 3 | task 99 | processing task, is_child = 0 0.45.855.625 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.182 (> 0.100 thold), f_keep = 0.235 0.45.855.702 I slot launch_slot_: id 1 | task 100 | processing task, is_child = 0 0.45.855.729 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.165 (> 0.100 thold), f_keep = 0.217 0.45.855.809 I slot launch_slot_: id 0 | task 101 | processing task, is_child = 0 0.46.846.599 I slot print_timing: id 2 | task 96 | prompt eval time = 503.72 ms / 156 tokens ( 3.23 ms per token, 309.70 tokens per second) 0.46.846.605 I slot print_timing: id 2 | task 96 | eval time = 996.07 ms / 2 tokens ( 996.07 ms per token, 1.00 tokens per second) 0.46.846.605 I slot print_timing: id 2 | task 96 | total time = 1499.79 ms / 158 tokens 0.46.846.606 I slot print_timing: id 2 | task 96 | graphs reused = 2 0.46.846.606 I slot print_timing: id 2 | task 96 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.846.632 I slot release: id 2 | task 96 | stop processing: n_tokens = 157, truncated = 0 0.46.941.080 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.173 (> 0.100 thold), f_keep = 0.172 0.46.943.405 I slot launch_slot_: id 2 | task 104 | processing task, is_child = 0 0.47.417.125 I slot print_timing: id 0 | task 101 | prompt eval time = 1085.07 ms / 158 tokens ( 6.87 ms per token, 145.61 tokens per second) 0.47.417.130 I slot print_timing: id 0 | task 101 | eval time = 476.24 ms / 2 tokens ( 476.24 ms per token, 2.10 tokens per second) 0.47.417.131 I slot print_timing: id 0 | task 101 | total time = 1561.31 ms / 160 tokens 0.47.417.131 I slot print_timing: id 0 | task 101 | graphs reused = 2 0.47.417.131 I slot print_timing: id 0 | task 101 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.417.151 I slot release: id 0 | task 101 | stop processing: n_tokens = 159, truncated = 0 0.47.417.250 I slot print_timing: id 1 | task 100 | prompt eval time = 1085.14 ms / 148 tokens ( 7.33 ms per token, 136.39 tokens per second) 0.47.417.252 I slot print_timing: id 1 | task 100 | eval time = 476.27 ms / 2 tokens ( 476.27 ms per token, 2.10 tokens per second) 0.47.417.253 I slot print_timing: id 1 | task 100 | total time = 1561.41 ms / 150 tokens 0.47.417.253 I slot print_timing: id 1 | task 100 | graphs reused = 2 0.47.417.253 I slot print_timing: id 1 | task 100 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.417.265 I slot release: id 1 | task 100 | stop processing: n_tokens = 149, truncated = 0 0.47.417.408 I slot print_timing: id 3 | task 99 | prompt eval time = 1085.22 ms / 99 tokens ( 10.96 ms per token, 91.23 tokens per second) 0.47.417.409 I slot print_timing: id 3 | task 99 | eval time = 476.33 ms / 2 tokens ( 476.33 ms per token, 2.10 tokens per second) 0.47.417.409 I slot print_timing: id 3 | task 99 | total time = 1561.55 ms / 101 tokens 0.47.417.410 I slot print_timing: id 3 | task 99 | graphs reused = 2 0.47.417.410 I slot print_timing: id 3 | task 99 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.417.418 I slot release: id 3 | task 99 | stop processing: n_tokens = 100, truncated = 0 0.47.458.061 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.267 (> 0.100 thold), f_keep = 0.170 0.47.460.474 I slot launch_slot_: id 0 | task 107 | processing task, is_child = 0 0.47.463.991 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.267 (> 0.100 thold), f_keep = 0.181 0.47.464.063 I slot launch_slot_: id 1 | task 108 | processing task, is_child = 0 0.47.464.088 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.210 (> 0.100 thold), f_keep = 0.260 0.47.464.150 I slot launch_slot_: id 3 | task 109 | processing task, is_child = 0 0.48.339.500 I slot print_timing: id 2 | task 104 | prompt eval time = 514.65 ms / 156 tokens ( 3.30 ms per token, 303.12 tokens per second) 0.48.339.505 I slot print_timing: id 2 | task 104 | eval time = 881.44 ms / 2 tokens ( 881.44 ms per token, 1.13 tokens per second) 0.48.339.506 I slot print_timing: id 2 | task 104 | total time = 1396.08 ms / 158 tokens 0.48.339.506 I slot print_timing: id 2 | task 104 | graphs reused = 2 0.48.339.507 I slot print_timing: id 2 | task 104 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.339.526 I slot release: id 2 | task 104 | stop processing: n_tokens = 157, truncated = 0 0.48.431.922 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.166 0.48.434.346 I slot launch_slot_: id 2 | task 112 | processing task, is_child = 0 0.48.854.407 I slot print_timing: id 3 | task 109 | prompt eval time = 967.72 ms / 124 tokens ( 7.80 ms per token, 128.14 tokens per second) 0.48.854.413 I slot print_timing: id 3 | task 109 | eval time = 422.49 ms / 2 tokens ( 422.49 ms per token, 2.37 tokens per second) 0.48.854.413 I slot print_timing: id 3 | task 109 | total time = 1390.20 ms / 126 tokens 0.48.854.413 I slot print_timing: id 3 | task 109 | graphs reused = 2 0.48.854.414 I slot print_timing: id 3 | task 109 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.854.430 I slot release: id 3 | task 109 | stop processing: n_tokens = 125, truncated = 0 0.48.924.000 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.194 (> 0.100 thold), f_keep = 0.208 0.48.925.511 I slot launch_slot_: id 3 | task 115 | processing task, is_child = 0 0.49.364.672 I slot print_timing: id 2 | task 112 | prompt eval time = 489.64 ms / 114 tokens ( 4.30 ms per token, 232.82 tokens per second) 0.49.364.677 I slot print_timing: id 2 | task 112 | eval time = 440.67 ms / 2 tokens ( 440.67 ms per token, 2.27 tokens per second) 0.49.364.678 I slot print_timing: id 2 | task 112 | total time = 930.32 ms / 116 tokens 0.49.364.678 I slot print_timing: id 2 | task 112 | graphs reused = 2 0.49.364.678 I slot print_timing: id 2 | task 112 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.364.697 I slot release: id 2 | task 112 | stop processing: n_tokens = 115, truncated = 0 0.49.433.127 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.226 0.49.434.922 I slot launch_slot_: id 2 | task 118 | processing task, is_child = 0 0.49.855.736 I slot print_timing: id 0 | task 107 | prompt eval time = 967.53 ms / 101 tokens ( 9.58 ms per token, 104.39 tokens per second) 0.49.855.738 I slot print_timing: id 0 | task 107 | eval time = 1424.05 ms / 6 tokens ( 284.81 ms per token, 3.51 tokens per second) 0.49.855.738 I slot print_timing: id 0 | task 107 | total time = 2391.58 ms / 107 tokens 0.49.855.739 I slot print_timing: id 0 | task 107 | graphs reused = 2 0.49.855.739 I slot print_timing: id 0 | task 107 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.855.758 I slot release: id 0 | task 107 | stop processing: n_tokens = 106, truncated = 0 0.49.937.727 I slot print_timing: id 1 | task 108 | prompt eval time = 967.64 ms / 101 tokens ( 9.58 ms per token, 104.38 tokens per second) 0.49.937.732 I slot print_timing: id 1 | task 108 | eval time = 1505.90 ms / 7 tokens ( 250.98 ms per token, 3.98 tokens per second) 0.49.937.732 I slot print_timing: id 1 | task 108 | total time = 2473.54 ms / 108 tokens 0.49.937.733 I slot print_timing: id 1 | task 108 | graphs reused = 2 0.49.937.733 I slot print_timing: id 1 | task 108 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.937.750 I slot release: id 1 | task 108 | stop processing: n_tokens = 107, truncated = 0 0.49.937.985 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.195 (> 0.100 thold), f_keep = 0.245 0.49.940.631 I slot launch_slot_: id 0 | task 121 | processing task, is_child = 0 0.49.941.894 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 0.49.941.991 I slot launch_slot_: id 1 | task 122 | processing task, is_child = 0 0.50.579.674 I slot print_timing: id 2 | task 118 | prompt eval time = 502.94 ms / 113 tokens ( 4.45 ms per token, 224.68 tokens per second) 0.50.579.677 I slot print_timing: id 2 | task 118 | eval time = 641.80 ms / 2 tokens ( 641.80 ms per token, 1.56 tokens per second) 0.50.579.677 I slot print_timing: id 2 | task 118 | total time = 1144.74 ms / 115 tokens 0.50.579.677 I slot print_timing: id 2 | task 118 | graphs reused = 2 0.50.579.678 I slot print_timing: id 2 | task 118 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.579.701 I slot release: id 2 | task 118 | stop processing: n_tokens = 114, truncated = 0 0.50.654.955 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.195 (> 0.100 thold), f_keep = 0.228 0.50.657.336 I slot launch_slot_: id 2 | task 125 | processing task, is_child = 0 0.51.100.009 I slot print_timing: id 3 | task 115 | prompt eval time = 507.60 ms / 134 tokens ( 3.79 ms per token, 263.99 tokens per second) 0.51.100.012 I slot print_timing: id 3 | task 115 | eval time = 1666.88 ms / 6 tokens ( 333.38 ms per token, 3.00 tokens per second) 0.51.100.012 I slot print_timing: id 3 | task 115 | total time = 2174.49 ms / 140 tokens 0.51.100.012 I slot print_timing: id 3 | task 115 | graphs reused = 2 0.51.100.013 I slot print_timing: id 3 | task 115 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.100.032 I slot release: id 3 | task 115 | stop processing: n_tokens = 139, truncated = 0 0.51.170.051 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.217 (> 0.100 thold), f_keep = 0.187 0.51.171.713 I slot launch_slot_: id 3 | task 128 | processing task, is_child = 0 0.51.576.988 I slot print_timing: id 2 | task 125 | prompt eval time = 512.70 ms / 133 tokens ( 3.85 ms per token, 259.41 tokens per second) 0.51.576.990 I slot print_timing: id 2 | task 125 | eval time = 406.94 ms / 2 tokens ( 406.94 ms per token, 2.46 tokens per second) 0.51.576.990 I slot print_timing: id 2 | task 125 | total time = 919.64 ms / 135 tokens 0.51.576.991 I slot print_timing: id 2 | task 125 | graphs reused = 2 0.51.576.991 I slot print_timing: id 2 | task 125 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.577.014 I slot release: id 2 | task 125 | stop processing: n_tokens = 134, truncated = 0 0.51.646.466 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.236 (> 0.100 thold), f_keep = 0.194 0.51.648.593 I slot launch_slot_: id 2 | task 131 | processing task, is_child = 0 0.52.063.708 I slot print_timing: id 0 | task 121 | prompt eval time = 712.63 ms / 133 tokens ( 5.36 ms per token, 186.63 tokens per second) 0.52.063.710 I slot print_timing: id 0 | task 121 | eval time = 1409.08 ms / 6 tokens ( 281.82 ms per token, 3.55 tokens per second) 0.52.063.711 I slot print_timing: id 0 | task 121 | total time = 2121.71 ms / 139 tokens 0.52.063.711 I slot print_timing: id 0 | task 121 | graphs reused = 2 0.52.063.712 I slot print_timing: id 0 | task 121 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.063.731 I slot release: id 0 | task 121 | stop processing: n_tokens = 138, truncated = 0 0.52.146.858 I slot print_timing: id 1 | task 122 | prompt eval time = 712.85 ms / 113 tokens ( 6.31 ms per token, 158.52 tokens per second) 0.52.146.863 I slot print_timing: id 1 | task 122 | eval time = 1491.98 ms / 7 tokens ( 248.66 ms per token, 4.02 tokens per second) 0.52.146.864 I slot print_timing: id 1 | task 122 | total time = 2204.84 ms / 120 tokens 0.52.146.864 I slot print_timing: id 1 | task 122 | graphs reused = 2 0.52.146.865 I slot print_timing: id 1 | task 122 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.146.884 I slot release: id 1 | task 122 | stop processing: n_tokens = 119, truncated = 0 0.52.147.118 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.273 (> 0.100 thold), f_keep = 0.196 0.52.149.391 I slot launch_slot_: id 0 | task 134 | processing task, is_child = 0 0.52.151.161 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.218 0.52.151.238 I slot launch_slot_: id 1 | task 135 | processing task, is_child = 0 0.52.839.018 I slot print_timing: id 0 | task 134 | prompt eval time = 647.17 ms / 99 tokens ( 6.54 ms per token, 152.97 tokens per second) 0.52.839.021 I slot print_timing: id 0 | task 134 | eval time = 40.60 ms / 2 tokens ( 40.60 ms per token, 24.63 tokens per second) 0.52.839.021 I slot print_timing: id 0 | task 134 | total time = 687.77 ms / 101 tokens 0.52.839.022 I slot print_timing: id 0 | task 134 | graphs reused = 2 0.52.839.022 I slot print_timing: id 0 | task 134 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.839.039 I slot release: id 0 | task 134 | stop processing: n_tokens = 100, truncated = 0 0.52.839.129 I slot print_timing: id 1 | task 135 | prompt eval time = 647.35 ms / 113 tokens ( 5.73 ms per token, 174.56 tokens per second) 0.52.839.132 I slot print_timing: id 1 | task 135 | eval time = 40.51 ms / 2 tokens ( 40.51 ms per token, 24.68 tokens per second) 0.52.839.132 I slot print_timing: id 1 | task 135 | total time = 687.86 ms / 115 tokens 0.52.839.132 I slot print_timing: id 1 | task 135 | graphs reused = 2 0.52.839.133 I slot print_timing: id 1 | task 135 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.839.143 I slot release: id 1 | task 135 | stop processing: n_tokens = 114, truncated = 0 0.52.839.315 I slot print_timing: id 3 | task 128 | prompt eval time = 474.74 ms / 120 tokens ( 3.96 ms per token, 252.77 tokens per second) 0.52.839.317 I slot print_timing: id 3 | task 128 | eval time = 1192.85 ms / 6 tokens ( 238.57 ms per token, 4.19 tokens per second) 0.52.839.317 I slot print_timing: id 3 | task 128 | total time = 1667.60 ms / 126 tokens 0.52.839.317 I slot print_timing: id 3 | task 128 | graphs reused = 2 0.52.839.318 I slot print_timing: id 3 | task 128 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.839.326 I slot release: id 3 | task 128 | stop processing: n_tokens = 125, truncated = 0 0.52.860.693 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.262 (> 0.100 thold), f_keep = 0.224 0.52.862.145 I slot launch_slot_: id 3 | task 140 | processing task, is_child = 0 0.52.865.321 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.160 (> 0.100 thold), f_keep = 0.260 0.52.865.399 I slot launch_slot_: id 0 | task 141 | processing task, is_child = 0 0.52.865.429 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.121 (> 0.100 thold), f_keep = 0.228 0.52.865.491 I slot launch_slot_: id 1 | task 142 | processing task, is_child = 0 0.54.241.255 I slot print_timing: id 2 | task 131 | prompt eval time = 498.43 ms / 110 tokens ( 4.53 ms per token, 220.69 tokens per second) 0.54.241.260 I slot print_timing: id 2 | task 131 | eval time = 2094.23 ms / 7 tokens ( 349.04 ms per token, 2.87 tokens per second) 0.54.241.260 I slot print_timing: id 2 | task 131 | total time = 2592.65 ms / 117 tokens 0.54.241.261 I slot print_timing: id 2 | task 131 | graphs reused = 2 0.54.241.261 I slot print_timing: id 2 | task 131 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.241.279 I slot release: id 2 | task 131 | stop processing: n_tokens = 116, truncated = 0 0.54.291.737 I slot print_timing: id 0 | task 141 | prompt eval time = 1375.59 ms / 162 tokens ( 8.49 ms per token, 117.77 tokens per second) 0.54.291.743 I slot print_timing: id 0 | task 141 | eval time = 50.65 ms / 2 tokens ( 50.65 ms per token, 19.74 tokens per second) 0.54.291.743 I slot print_timing: id 0 | task 141 | total time = 1426.24 ms / 164 tokens 0.54.291.743 I slot print_timing: id 0 | task 141 | graphs reused = 2 0.54.291.744 I slot print_timing: id 0 | task 141 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.291.763 I slot release: id 0 | task 141 | stop processing: n_tokens = 163, truncated = 0 0.54.291.869 I slot print_timing: id 1 | task 142 | prompt eval time = 1375.66 ms / 214 tokens ( 6.43 ms per token, 155.56 tokens per second) 0.54.291.874 I slot print_timing: id 1 | task 142 | eval time = 50.69 ms / 2 tokens ( 50.69 ms per token, 19.73 tokens per second) 0.54.291.874 I slot print_timing: id 1 | task 142 | total time = 1426.35 ms / 216 tokens 0.54.291.874 I slot print_timing: id 1 | task 142 | graphs reused = 2 0.54.291.875 I slot print_timing: id 1 | task 142 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.291.887 I slot release: id 1 | task 142 | stop processing: n_tokens = 215, truncated = 0 0.54.291.985 I slot print_timing: id 3 | task 140 | prompt eval time = 1375.86 ms / 107 tokens ( 12.86 ms per token, 77.77 tokens per second) 0.54.291.986 I slot print_timing: id 3 | task 140 | eval time = 50.59 ms / 2 tokens ( 50.59 ms per token, 19.77 tokens per second) 0.54.291.987 I slot print_timing: id 3 | task 140 | total time = 1426.45 ms / 109 tokens 0.54.291.987 I slot print_timing: id 3 | task 140 | graphs reused = 2 0.54.291.987 I slot print_timing: id 3 | task 140 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.291.993 I slot release: id 3 | task 140 | stop processing: n_tokens = 108, truncated = 0 0.54.291.997 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.213 (> 0.100 thold), f_keep = 0.233 0.54.293.742 I slot launch_slot_: id 2 | task 146 | processing task, is_child = 0 0.54.300.016 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.218 (> 0.100 thold), f_keep = 0.269 0.54.300.092 I slot launch_slot_: id 3 | task 147 | processing task, is_child = 0 0.54.300.150 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.176 (> 0.100 thold), f_keep = 0.160 0.54.300.567 I slot launch_slot_: id 0 | task 148 | processing task, is_child = 0 0.54.300.603 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.158 (> 0.100 thold), f_keep = 0.121 0.54.300.670 I slot launch_slot_: id 1 | task 149 | processing task, is_child = 0 0.55.626.779 I slot print_timing: id 2 | task 146 | prompt eval time = 1285.20 ms / 127 tokens ( 10.12 ms per token, 98.82 tokens per second) 0.55.626.784 I slot print_timing: id 2 | task 146 | eval time = 40.85 ms / 2 tokens ( 40.85 ms per token, 24.48 tokens per second) 0.55.626.785 I slot print_timing: id 2 | task 146 | total time = 1326.06 ms / 129 tokens 0.55.626.785 I slot print_timing: id 2 | task 146 | graphs reused = 2 0.55.626.786 I slot print_timing: id 2 | task 146 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.626.804 I slot release: id 2 | task 146 | stop processing: n_tokens = 128, truncated = 0 0.55.626.892 I slot print_timing: id 3 | task 147 | prompt eval time = 1285.30 ms / 133 tokens ( 9.66 ms per token, 103.48 tokens per second) 0.55.626.895 I slot print_timing: id 3 | task 147 | eval time = 40.85 ms / 2 tokens ( 40.85 ms per token, 24.48 tokens per second) 0.55.626.895 I slot print_timing: id 3 | task 147 | total time = 1326.16 ms / 135 tokens 0.55.626.895 I slot print_timing: id 3 | task 147 | graphs reused = 2 0.55.626.896 I slot print_timing: id 3 | task 147 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.626.905 I slot release: id 3 | task 147 | stop processing: n_tokens = 134, truncated = 0 0.55.659.780 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.176 (> 0.100 thold), f_keep = 0.203 0.55.661.786 I slot launch_slot_: id 2 | task 154 | processing task, is_child = 0 0.55.664.226 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.122 (> 0.100 thold), f_keep = 0.194 0.55.664.305 I slot launch_slot_: id 3 | task 155 | processing task, is_child = 0 0.56.579.449 I slot print_timing: id 0 | task 148 | prompt eval time = 1285.03 ms / 148 tokens ( 8.68 ms per token, 115.17 tokens per second) 0.56.579.454 I slot print_timing: id 0 | task 148 | eval time = 993.74 ms / 4 tokens ( 331.25 ms per token, 3.02 tokens per second) 0.56.579.455 I slot print_timing: id 0 | task 148 | total time = 2278.77 ms / 152 tokens 0.56.579.455 I slot print_timing: id 0 | task 148 | graphs reused = 2 0.56.579.456 I slot print_timing: id 0 | task 148 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.579.481 I slot release: id 0 | task 148 | stop processing: n_tokens = 151, truncated = 0 0.56.663.701 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.289 (> 0.100 thold), f_keep = 0.185 0.56.666.779 I slot launch_slot_: id 0 | task 158 | processing task, is_child = 0 0.57.027.963 I slot print_timing: id 1 | task 149 | prompt eval time = 1285.11 ms / 165 tokens ( 7.79 ms per token, 128.39 tokens per second) 0.57.027.968 I slot print_timing: id 1 | task 149 | eval time = 1442.16 ms / 6 tokens ( 288.43 ms per token, 3.47 tokens per second) 0.57.027.968 I slot print_timing: id 1 | task 149 | total time = 2727.27 ms / 171 tokens 0.57.027.969 I slot print_timing: id 1 | task 149 | graphs reused = 2 0.57.027.969 I slot print_timing: id 1 | task 149 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.027.991 I slot release: id 1 | task 149 | stop processing: n_tokens = 170, truncated = 0 0.57.028.086 I slot print_timing: id 2 | task 154 | prompt eval time = 999.29 ms / 148 tokens ( 6.75 ms per token, 148.11 tokens per second) 0.57.028.090 I slot print_timing: id 2 | task 154 | eval time = 364.49 ms / 2 tokens ( 364.49 ms per token, 2.74 tokens per second) 0.57.028.091 I slot print_timing: id 2 | task 154 | total time = 1363.78 ms / 150 tokens 0.57.028.091 I slot print_timing: id 2 | task 154 | graphs reused = 2 0.57.028.092 I slot print_timing: id 2 | task 154 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.028.101 I slot release: id 2 | task 154 | stop processing: n_tokens = 149, truncated = 0 0.57.028.200 I slot print_timing: id 3 | task 155 | prompt eval time = 999.36 ms / 213 tokens ( 4.69 ms per token, 213.14 tokens per second) 0.57.028.202 I slot print_timing: id 3 | task 155 | eval time = 364.50 ms / 2 tokens ( 364.50 ms per token, 2.74 tokens per second) 0.57.028.202 I slot print_timing: id 3 | task 155 | total time = 1363.86 ms / 215 tokens 0.57.028.203 I slot print_timing: id 3 | task 155 | graphs reused = 2 0.57.028.203 I slot print_timing: id 3 | task 155 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.028.215 I slot release: id 3 | task 155 | stop processing: n_tokens = 214, truncated = 0 0.57.068.202 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.250 (> 0.100 thold), f_keep = 0.153 0.57.070.787 I slot launch_slot_: id 1 | task 161 | processing task, is_child = 0 0.57.076.206 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.197 (> 0.100 thold), f_keep = 0.174 0.57.076.283 I slot launch_slot_: id 2 | task 162 | processing task, is_child = 0 0.57.076.316 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.148 (> 0.100 thold), f_keep = 0.121 0.57.077.057 I slot launch_slot_: id 3 | task 163 | processing task, is_child = 0 0.58.221.926 I slot print_timing: id 0 | task 158 | prompt eval time = 401.41 ms / 97 tokens ( 4.14 ms per token, 241.65 tokens per second) 0.58.221.931 I slot print_timing: id 0 | task 158 | eval time = 1153.73 ms / 2 tokens ( 1153.73 ms per token, 0.87 tokens per second) 0.58.221.932 I slot print_timing: id 0 | task 158 | total time = 1555.14 ms / 99 tokens 0.58.221.933 I slot print_timing: id 0 | task 158 | graphs reused = 2 0.58.221.933 I slot print_timing: id 0 | task 158 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.221.960 I slot release: id 0 | task 158 | stop processing: n_tokens = 98, truncated = 0 0.58.300.312 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.159 (> 0.100 thold), f_keep = 0.265 0.58.300.987 I slot launch_slot_: id 0 | task 166 | processing task, is_child = 0 0.58.766.411 I slot print_timing: id 2 | task 162 | prompt eval time = 1223.12 ms / 132 tokens ( 9.27 ms per token, 107.92 tokens per second) 0.58.766.415 I slot print_timing: id 2 | task 162 | eval time = 466.20 ms / 2 tokens ( 466.20 ms per token, 2.14 tokens per second) 0.58.766.415 I slot print_timing: id 2 | task 162 | total time = 1689.32 ms / 134 tokens 0.58.766.415 I slot print_timing: id 2 | task 162 | graphs reused = 2 0.58.766.416 I slot print_timing: id 2 | task 162 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.766.435 I slot release: id 2 | task 162 | stop processing: n_tokens = 133, truncated = 0 0.58.843.147 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.205 (> 0.100 thold), f_keep = 0.195 0.58.844.679 I slot launch_slot_: id 2 | task 169 | processing task, is_child = 0 0.59.278.767 I slot print_timing: id 0 | task 166 | prompt eval time = 541.94 ms / 164 tokens ( 3.30 ms per token, 302.62 tokens per second) 0.59.278.773 I slot print_timing: id 0 | task 166 | eval time = 435.83 ms / 2 tokens ( 435.83 ms per token, 2.29 tokens per second) 0.59.278.773 I slot print_timing: id 0 | task 166 | total time = 977.77 ms / 166 tokens 0.59.278.774 I slot print_timing: id 0 | task 166 | graphs reused = 2 0.59.278.774 I slot print_timing: id 0 | task 166 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.278.794 I slot release: id 0 | task 166 | stop processing: n_tokens = 165, truncated = 0 0.59.361.770 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.236 (> 0.100 thold), f_keep = 0.158 0.59.364.805 I slot launch_slot_: id 0 | task 172 | processing task, is_child = 0 0.59.834.929 I slot print_timing: id 3 | task 163 | prompt eval time = 1223.20 ms / 176 tokens ( 6.95 ms per token, 143.88 tokens per second) 0.59.834.934 I slot print_timing: id 3 | task 163 | eval time = 1534.62 ms / 7 tokens ( 255.77 ms per token, 3.91 tokens per second) 0.59.834.935 I slot print_timing: id 3 | task 163 | total time = 2757.82 ms / 183 tokens 0.59.834.935 I slot print_timing: id 3 | task 163 | graphs reused = 2 0.59.834.935 I slot print_timing: id 3 | task 163 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.834.958 I slot release: id 3 | task 163 | stop processing: n_tokens = 182, truncated = 0 0.59.871.652 I slot print_timing: id 0 | task 172 | prompt eval time = 469.88 ms / 110 tokens ( 4.27 ms per token, 234.10 tokens per second) 0.59.871.659 I slot print_timing: id 0 | task 172 | eval time = 36.95 ms / 2 tokens ( 36.95 ms per token, 27.06 tokens per second) 0.59.871.659 I slot print_timing: id 0 | task 172 | total time = 506.84 ms / 112 tokens 0.59.871.659 I slot print_timing: id 0 | task 172 | graphs reused = 2 0.59.871.660 I slot print_timing: id 0 | task 172 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.871.677 I slot release: id 0 | task 172 | stop processing: n_tokens = 111, truncated = 0 0.59.871.859 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.270 (> 0.100 thold), f_keep = 0.243 0.59.872.584 I slot launch_slot_: id 0 | task 176 | processing task, is_child = 0 1.00.234.118 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.172 (> 0.100 thold), f_keep = 0.143 1.00.234.231 I slot launch_slot_: id 3 | task 178 | processing task, is_child = 0 1.00.800.174 I slot print_timing: id 2 | task 169 | prompt eval time = 516.98 ms / 127 tokens ( 4.07 ms per token, 245.66 tokens per second) 1.00.800.180 I slot print_timing: id 2 | task 169 | eval time = 1438.49 ms / 7 tokens ( 239.75 ms per token, 4.17 tokens per second) 1.00.800.181 I slot print_timing: id 2 | task 169 | total time = 1955.48 ms / 134 tokens 1.00.800.181 I slot print_timing: id 2 | task 169 | graphs reused = 2 1.00.800.184 I slot print_timing: id 2 | task 169 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.800.205 I slot release: id 2 | task 169 | stop processing: n_tokens = 133, truncated = 0 1.00.850.923 I slot print_timing: id 1 | task 161 | prompt eval time = 1223.05 ms / 104 tokens ( 11.76 ms per token, 85.03 tokens per second) 1.00.850.928 I slot print_timing: id 1 | task 161 | eval time = 2550.81 ms / 12 tokens ( 231.89 ms per token, 4.31 tokens per second) 1.00.850.929 I slot print_timing: id 1 | task 161 | total time = 3773.86 ms / 116 tokens 1.00.850.929 I slot print_timing: id 1 | task 161 | graphs reused = 2 1.00.850.930 I slot print_timing: id 1 | task 161 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.850.947 I slot release: id 1 | task 161 | stop processing: n_tokens = 115, truncated = 0 1.00.851.047 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.210 (> 0.100 thold), f_keep = 0.226 1.00.851.796 I slot launch_slot_: id 1 | task 182 | processing task, is_child = 0 1.01.282.900 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.210 (> 0.100 thold), f_keep = 0.195 1.01.283.004 I slot launch_slot_: id 2 | task 184 | processing task, is_child = 0 1.01.836.515 I slot print_timing: id 1 | task 182 | prompt eval time = 894.97 ms / 124 tokens ( 7.22 ms per token, 138.55 tokens per second) 1.01.836.523 I slot print_timing: id 1 | task 182 | eval time = 88.16 ms / 2 tokens ( 88.16 ms per token, 11.34 tokens per second) 1.01.836.524 I slot print_timing: id 1 | task 182 | total time = 983.12 ms / 126 tokens 1.01.836.524 I slot print_timing: id 1 | task 182 | graphs reused = 2 1.01.836.525 I slot print_timing: id 1 | task 182 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.836.543 I slot release: id 1 | task 182 | stop processing: n_tokens = 125, truncated = 0 1.01.888.507 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.234 (> 0.100 thold), f_keep = 0.208 1.01.891.802 I slot launch_slot_: id 1 | task 188 | processing task, is_child = 0 1.02.316.709 I slot print_timing: id 3 | task 178 | prompt eval time = 565.80 ms / 151 tokens ( 3.75 ms per token, 266.88 tokens per second) 1.02.316.715 I slot print_timing: id 3 | task 178 | eval time = 1516.39 ms / 7 tokens ( 252.73 ms per token, 3.96 tokens per second) 1.02.316.716 I slot print_timing: id 3 | task 178 | total time = 2082.19 ms / 158 tokens 1.02.316.716 I slot print_timing: id 3 | task 178 | graphs reused = 2 1.02.316.716 I slot print_timing: id 3 | task 178 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.316.736 I slot release: id 3 | task 178 | stop processing: n_tokens = 157, truncated = 0 1.02.399.253 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.222 (> 0.100 thold), f_keep = 0.166 1.02.401.851 I slot launch_slot_: id 3 | task 191 | processing task, is_child = 0 1.02.814.655 I slot print_timing: id 1 | task 188 | prompt eval time = 507.34 ms / 111 tokens ( 4.57 ms per token, 218.79 tokens per second) 1.02.814.670 I slot print_timing: id 1 | task 188 | eval time = 415.50 ms / 2 tokens ( 415.50 ms per token, 2.41 tokens per second) 1.02.814.672 I slot print_timing: id 1 | task 188 | total time = 922.84 ms / 113 tokens 1.02.814.672 I slot print_timing: id 1 | task 188 | graphs reused = 2 1.02.814.672 I slot print_timing: id 1 | task 188 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.814.700 I slot release: id 1 | task 188 | stop processing: n_tokens = 112, truncated = 0 1.02.898.012 I slot print_timing: id 2 | task 184 | prompt eval time = 552.74 ms / 124 tokens ( 4.46 ms per token, 224.34 tokens per second) 1.02.898.019 I slot print_timing: id 2 | task 184 | eval time = 1061.34 ms / 6 tokens ( 212.27 ms per token, 4.71 tokens per second) 1.02.898.019 I slot print_timing: id 2 | task 184 | total time = 1614.08 ms / 130 tokens 1.02.898.020 I slot print_timing: id 2 | task 184 | graphs reused = 2 1.02.898.020 I slot print_timing: id 2 | task 184 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.898.037 I slot release: id 2 | task 184 | stop processing: n_tokens = 129, truncated = 0 1.02.898.146 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.156 (> 0.100 thold), f_keep = 0.232 1.02.899.541 I slot launch_slot_: id 1 | task 194 | processing task, is_child = 0 1.02.901.599 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.152 (> 0.100 thold), f_keep = 0.202 1.02.901.672 I slot launch_slot_: id 2 | task 195 | processing task, is_child = 0 1.03.619.224 I slot print_timing: id 3 | task 191 | prompt eval time = 496.28 ms / 117 tokens ( 4.24 ms per token, 235.75 tokens per second) 1.03.619.230 I slot print_timing: id 3 | task 191 | eval time = 721.08 ms / 2 tokens ( 721.08 ms per token, 1.39 tokens per second) 1.03.619.230 I slot print_timing: id 3 | task 191 | total time = 1217.36 ms / 119 tokens 1.03.619.231 I slot print_timing: id 3 | task 191 | graphs reused = 2 1.03.619.231 I slot print_timing: id 3 | task 191 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.619.252 I slot release: id 3 | task 191 | stop processing: n_tokens = 118, truncated = 0 1.03.702.087 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.161 (> 0.100 thold), f_keep = 0.220 1.03.703.470 I slot launch_slot_: id 3 | task 198 | processing task, is_child = 0 1.04.167.969 I slot print_timing: id 1 | task 194 | prompt eval time = 800.28 ms / 167 tokens ( 4.79 ms per token, 208.68 tokens per second) 1.04.167.973 I slot print_timing: id 1 | task 194 | eval time = 466.01 ms / 2 tokens ( 466.01 ms per token, 2.15 tokens per second) 1.04.167.974 I slot print_timing: id 1 | task 194 | total time = 1266.29 ms / 169 tokens 1.04.167.974 I slot print_timing: id 1 | task 194 | graphs reused = 2 1.04.167.975 I slot print_timing: id 1 | task 194 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.167.996 I slot release: id 1 | task 194 | stop processing: n_tokens = 168, truncated = 0 1.04.168.093 I slot print_timing: id 2 | task 195 | prompt eval time = 800.38 ms / 171 tokens ( 4.68 ms per token, 213.65 tokens per second) 1.04.168.097 I slot print_timing: id 2 | task 195 | eval time = 466.01 ms / 2 tokens ( 466.01 ms per token, 2.15 tokens per second) 1.04.168.097 I slot print_timing: id 2 | task 195 | total time = 1266.39 ms / 173 tokens 1.04.168.098 I slot print_timing: id 2 | task 195 | graphs reused = 2 1.04.168.098 I slot print_timing: id 2 | task 195 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.168.110 I slot release: id 2 | task 195 | stop processing: n_tokens = 172, truncated = 0 1.04.228.365 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.236 (> 0.100 thold), f_keep = 0.155 1.04.230.966 I slot launch_slot_: id 1 | task 202 | processing task, is_child = 0 1.04.233.926 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.241 (> 0.100 thold), f_keep = 0.151 1.04.234.004 I slot launch_slot_: id 2 | task 201 | processing task, is_child = 0 1.04.794.201 I slot print_timing: id 3 | task 198 | prompt eval time = 524.88 ms / 161 tokens ( 3.26 ms per token, 306.74 tokens per second) 1.04.794.206 I slot print_timing: id 3 | task 198 | eval time = 565.84 ms / 2 tokens ( 565.84 ms per token, 1.77 tokens per second) 1.04.794.207 I slot print_timing: id 3 | task 198 | total time = 1090.72 ms / 163 tokens 1.04.794.207 I slot print_timing: id 3 | task 198 | graphs reused = 2 1.04.794.208 I slot print_timing: id 3 | task 198 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.794.231 I slot release: id 3 | task 198 | stop processing: n_tokens = 162, truncated = 0 1.04.874.880 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.226 (> 0.100 thold), f_keep = 0.160 1.04.877.002 I slot launch_slot_: id 3 | task 205 | processing task, is_child = 0 1.05.282.692 I slot print_timing: id 2 | task 201 | prompt eval time = 640.83 ms / 108 tokens ( 5.93 ms per token, 168.53 tokens per second) 1.05.282.697 I slot print_timing: id 2 | task 201 | eval time = 407.81 ms / 2 tokens ( 407.81 ms per token, 2.45 tokens per second) 1.05.282.697 I slot print_timing: id 2 | task 201 | total time = 1048.65 ms / 110 tokens 1.05.282.698 I slot print_timing: id 2 | task 201 | graphs reused = 2 1.05.282.698 I slot print_timing: id 2 | task 201 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.282.717 I slot release: id 2 | task 201 | stop processing: n_tokens = 109, truncated = 0 1.05.352.081 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.245 (> 0.100 thold), f_keep = 0.239 1.05.353.681 I slot launch_slot_: id 2 | task 208 | processing task, is_child = 0 1.05.761.582 I slot print_timing: id 3 | task 205 | prompt eval time = 475.07 ms / 115 tokens ( 4.13 ms per token, 242.07 tokens per second) 1.05.761.587 I slot print_timing: id 3 | task 205 | eval time = 409.50 ms / 2 tokens ( 409.50 ms per token, 2.44 tokens per second) 1.05.761.587 I slot print_timing: id 3 | task 205 | total time = 884.57 ms / 117 tokens 1.05.761.588 I slot print_timing: id 3 | task 205 | graphs reused = 2 1.05.761.588 I slot print_timing: id 3 | task 205 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.761.608 I slot release: id 3 | task 205 | stop processing: n_tokens = 116, truncated = 0 1.05.831.247 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.217 (> 0.100 thold), f_keep = 0.224 1.05.832.927 I slot launch_slot_: id 3 | task 211 | processing task, is_child = 0 1.06.245.346 I slot print_timing: id 1 | task 202 | prompt eval time = 640.77 ms / 110 tokens ( 5.83 ms per token, 171.67 tokens per second) 1.06.245.351 I slot print_timing: id 1 | task 202 | eval time = 1370.56 ms / 6 tokens ( 274.11 ms per token, 3.65 tokens per second) 1.06.245.351 I slot print_timing: id 1 | task 202 | total time = 2011.33 ms / 116 tokens 1.06.245.352 I slot print_timing: id 1 | task 202 | graphs reused = 2 1.06.245.352 I slot print_timing: id 1 | task 202 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.245.371 I slot release: id 1 | task 202 | stop processing: n_tokens = 115, truncated = 0 1.06.328.552 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.195 (> 0.100 thold), f_keep = 0.226 1.06.329.264 I slot launch_slot_: id 1 | task 214 | processing task, is_child = 0 1.06.909.883 I slot print_timing: id 1 | task 214 | prompt eval time = 539.28 ms / 133 tokens ( 4.05 ms per token, 246.63 tokens per second) 1.06.909.890 I slot print_timing: id 1 | task 214 | eval time = 41.33 ms / 2 tokens ( 41.33 ms per token, 24.20 tokens per second) 1.06.909.891 I slot print_timing: id 1 | task 214 | total time = 580.61 ms / 135 tokens 1.06.909.892 I slot print_timing: id 1 | task 214 | graphs reused = 2 1.06.909.892 I slot print_timing: id 1 | task 214 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.909.914 I slot release: id 1 | task 214 | stop processing: n_tokens = 134, truncated = 0 1.06.910.228 I slot print_timing: id 3 | task 211 | prompt eval time = 495.61 ms / 120 tokens ( 4.13 ms per token, 242.13 tokens per second) 1.06.910.234 I slot print_timing: id 3 | task 211 | eval time = 581.68 ms / 4 tokens ( 193.89 ms per token, 5.16 tokens per second) 1.06.910.235 I slot print_timing: id 3 | task 211 | total time = 1077.29 ms / 124 tokens 1.06.910.235 I slot print_timing: id 3 | task 211 | graphs reused = 2 1.06.910.236 I slot print_timing: id 3 | task 211 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.910.249 I slot release: id 3 | task 211 | stop processing: n_tokens = 123, truncated = 0 1.06.953.276 I slot print_timing: id 2 | task 208 | prompt eval time = 477.56 ms / 106 tokens ( 4.51 ms per token, 221.96 tokens per second) 1.06.953.285 I slot print_timing: id 2 | task 208 | eval time = 1122.03 ms / 7 tokens ( 187.00 ms per token, 5.35 tokens per second) 1.06.953.286 I slot print_timing: id 2 | task 208 | total time = 1599.58 ms / 113 tokens 1.06.953.286 I slot print_timing: id 2 | task 208 | graphs reused = 2 1.06.953.287 I slot print_timing: id 2 | task 208 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.953.317 I slot release: id 2 | task 208 | stop processing: n_tokens = 112, truncated = 0 1.06.953.327 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.211 (> 0.100 thold), f_keep = 0.194 1.06.957.851 I slot launch_slot_: id 1 | task 219 | processing task, is_child = 0 1.06.963.530 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.218 (> 0.100 thold), f_keep = 0.232 1.06.964.194 I slot launch_slot_: id 2 | task 220 | processing task, is_child = 0 1.06.964.253 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.211 1.06.964.387 I slot launch_slot_: id 3 | task 221 | processing task, is_child = 0 1.07.870.075 I slot print_timing: id 2 | task 220 | prompt eval time = 864.92 ms / 119 tokens ( 7.27 ms per token, 137.59 tokens per second) 1.07.870.081 I slot print_timing: id 2 | task 220 | eval time = 40.70 ms / 2 tokens ( 40.70 ms per token, 24.57 tokens per second) 1.07.870.081 I slot print_timing: id 2 | task 220 | total time = 905.62 ms / 121 tokens 1.07.870.082 I slot print_timing: id 2 | task 220 | graphs reused = 2 1.07.870.082 I slot print_timing: id 2 | task 220 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.870.103 I slot release: id 2 | task 220 | stop processing: n_tokens = 120, truncated = 0 1.07.870.189 I slot print_timing: id 3 | task 221 | prompt eval time = 864.98 ms / 114 tokens ( 7.59 ms per token, 131.79 tokens per second) 1.07.870.191 I slot print_timing: id 3 | task 221 | eval time = 40.72 ms / 2 tokens ( 40.72 ms per token, 24.56 tokens per second) 1.07.870.192 I slot print_timing: id 3 | task 221 | total time = 905.71 ms / 116 tokens 1.07.870.192 I slot print_timing: id 3 | task 221 | graphs reused = 2 1.07.870.193 I slot print_timing: id 3 | task 221 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.870.202 I slot release: id 3 | task 221 | stop processing: n_tokens = 115, truncated = 0 1.07.902.502 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.215 (> 0.100 thold), f_keep = 0.217 1.07.904.075 I slot launch_slot_: id 2 | task 227 | processing task, is_child = 0 1.07.905.964 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.274 (> 0.100 thold), f_keep = 0.226 1.07.906.039 I slot launch_slot_: id 3 | task 226 | processing task, is_child = 0 1.08.644.340 I slot print_timing: id 1 | task 219 | prompt eval time = 864.86 ms / 123 tokens ( 7.03 ms per token, 142.22 tokens per second) 1.08.644.343 I slot print_timing: id 1 | task 219 | eval time = 815.08 ms / 6 tokens ( 163.02 ms per token, 6.13 tokens per second) 1.08.644.343 I slot print_timing: id 1 | task 219 | total time = 1679.94 ms / 129 tokens 1.08.644.344 I slot print_timing: id 1 | task 219 | graphs reused = 2 1.08.644.344 I slot print_timing: id 1 | task 219 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.644.361 I slot release: id 1 | task 219 | stop processing: n_tokens = 128, truncated = 0 1.08.695.905 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.179 (> 0.100 thold), f_keep = 0.203 1.08.697.823 I slot launch_slot_: id 1 | task 232 | processing task, is_child = 0 1.09.338.708 I slot print_timing: id 2 | task 227 | prompt eval time = 697.66 ms / 121 tokens ( 5.77 ms per token, 173.44 tokens per second) 1.09.338.716 I slot print_timing: id 2 | task 227 | eval time = 734.99 ms / 7 tokens ( 122.50 ms per token, 8.16 tokens per second) 1.09.338.717 I slot print_timing: id 2 | task 227 | total time = 1432.66 ms / 128 tokens 1.09.338.718 I slot print_timing: id 2 | task 227 | graphs reused = 3 1.09.338.719 I slot print_timing: id 2 | task 227 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.338.748 I slot release: id 2 | task 227 | stop processing: n_tokens = 127, truncated = 0 1.09.397.477 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.200 (> 0.100 thold), f_keep = 0.205 1.09.400.922 I slot launch_slot_: id 2 | task 238 | processing task, is_child = 0 1.09.975.473 I slot print_timing: id 1 | task 232 | prompt eval time = 561.64 ms / 145 tokens ( 3.87 ms per token, 258.17 tokens per second) 1.09.975.480 I slot print_timing: id 1 | task 232 | eval time = 716.00 ms / 7 tokens ( 119.33 ms per token, 8.38 tokens per second) 1.09.975.481 I slot print_timing: id 1 | task 232 | total time = 1277.63 ms / 152 tokens 1.09.975.482 I slot print_timing: id 1 | task 232 | graphs reused = 3 1.09.975.483 I slot print_timing: id 1 | task 232 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.975.507 I slot release: id 1 | task 232 | stop processing: n_tokens = 151, truncated = 0 1.09.975.663 I slot print_timing: id 2 | task 238 | prompt eval time = 532.70 ms / 130 tokens ( 4.10 ms per token, 244.04 tokens per second) 1.09.975.667 I slot print_timing: id 2 | task 238 | eval time = 42.03 ms / 2 tokens ( 42.03 ms per token, 23.79 tokens per second) 1.09.975.667 I slot print_timing: id 2 | task 238 | total time = 574.73 ms / 132 tokens 1.09.975.668 I slot print_timing: id 2 | task 238 | graphs reused = 3 1.09.975.668 I slot print_timing: id 2 | task 238 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.975.688 I slot release: id 2 | task 238 | stop processing: n_tokens = 131, truncated = 0 1.10.021.218 I slot print_timing: id 3 | task 226 | prompt eval time = 697.74 ms / 95 tokens ( 7.34 ms per token, 136.15 tokens per second) 1.10.021.222 I slot print_timing: id 3 | task 226 | eval time = 1417.40 ms / 12 tokens ( 128.85 ms per token, 7.76 tokens per second) 1.10.021.223 I slot print_timing: id 3 | task 226 | total time = 2115.14 ms / 107 tokens 1.10.021.224 I slot print_timing: id 3 | task 226 | graphs reused = 3 1.10.021.225 I slot print_timing: id 3 | task 226 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.021.247 I slot release: id 3 | task 226 | stop processing: n_tokens = 106, truncated = 0 1.10.021.256 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.178 (> 0.100 thold), f_keep = 0.172 1.10.025.517 I slot launch_slot_: id 1 | task 243 | processing task, is_child = 0 1.10.030.787 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.169 (> 0.100 thold), f_keep = 0.198 1.10.030.943 I slot launch_slot_: id 2 | task 244 | processing task, is_child = 0 1.10.030.997 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.265 (> 0.100 thold), f_keep = 0.255 1.10.031.131 I slot launch_slot_: id 3 | task 245 | processing task, is_child = 0 1.11.167.480 I slot print_timing: id 2 | task 244 | prompt eval time = 1095.55 ms / 154 tokens ( 7.11 ms per token, 140.57 tokens per second) 1.11.167.483 I slot print_timing: id 2 | task 244 | eval time = 40.73 ms / 2 tokens ( 40.73 ms per token, 24.55 tokens per second) 1.11.167.484 I slot print_timing: id 2 | task 244 | total time = 1136.28 ms / 156 tokens 1.11.167.484 I slot print_timing: id 2 | task 244 | graphs reused = 3 1.11.167.484 I slot print_timing: id 2 | task 244 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.167.503 I slot release: id 2 | task 244 | stop processing: n_tokens = 155, truncated = 0 1.11.167.595 I slot print_timing: id 3 | task 245 | prompt eval time = 1095.60 ms / 102 tokens ( 10.74 ms per token, 93.10 tokens per second) 1.11.167.596 I slot print_timing: id 3 | task 245 | eval time = 40.76 ms / 2 tokens ( 40.76 ms per token, 24.53 tokens per second) 1.11.167.597 I slot print_timing: id 3 | task 245 | total time = 1136.36 ms / 104 tokens 1.11.167.597 I slot print_timing: id 3 | task 245 | graphs reused = 3 1.11.167.597 I slot print_timing: id 3 | task 245 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.167.610 I slot release: id 3 | task 245 | stop processing: n_tokens = 103, truncated = 0 1.11.200.465 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.260 (> 0.100 thold), f_keep = 0.168 1.11.203.250 I slot launch_slot_: id 2 | task 250 | processing task, is_child = 0 1.11.204.297 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.252 1.11.204.365 I slot launch_slot_: id 3 | task 251 | processing task, is_child = 0 1.12.050.810 I slot print_timing: id 1 | task 243 | prompt eval time = 1095.51 ms / 146 tokens ( 7.50 ms per token, 133.27 tokens per second) 1.12.050.815 I slot print_timing: id 1 | task 243 | eval time = 924.16 ms / 6 tokens ( 184.83 ms per token, 5.41 tokens per second) 1.12.050.815 I slot print_timing: id 1 | task 243 | total time = 2019.67 ms / 152 tokens 1.12.050.816 I slot print_timing: id 1 | task 243 | graphs reused = 3 1.12.050.816 I slot print_timing: id 1 | task 243 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.050.835 I slot release: id 1 | task 243 | stop processing: n_tokens = 151, truncated = 0 1.12.102.389 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.202 (> 0.100 thold), f_keep = 0.172 1.12.104.205 I slot launch_slot_: id 1 | task 256 | processing task, is_child = 0 1.12.678.993 I slot print_timing: id 1 | task 256 | prompt eval time = 533.79 ms / 129 tokens ( 4.14 ms per token, 241.67 tokens per second) 1.12.678.999 I slot print_timing: id 1 | task 256 | eval time = 40.99 ms / 2 tokens ( 40.99 ms per token, 24.40 tokens per second) 1.12.678.999 I slot print_timing: id 1 | task 256 | total time = 574.78 ms / 131 tokens 1.12.679.000 I slot print_timing: id 1 | task 256 | graphs reused = 3 1.12.679.000 I slot print_timing: id 1 | task 256 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.679.019 I slot release: id 1 | task 256 | stop processing: n_tokens = 130, truncated = 0 1.12.679.104 I slot print_timing: id 2 | task 250 | prompt eval time = 805.58 ms / 100 tokens ( 8.06 ms per token, 124.13 tokens per second) 1.12.679.106 I slot print_timing: id 2 | task 250 | eval time = 669.16 ms / 6 tokens ( 133.83 ms per token, 7.47 tokens per second) 1.12.679.106 I slot print_timing: id 2 | task 250 | total time = 1474.73 ms / 106 tokens 1.12.679.106 I slot print_timing: id 2 | task 250 | graphs reused = 3 1.12.679.107 I slot print_timing: id 2 | task 250 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.679.118 I slot release: id 2 | task 250 | stop processing: n_tokens = 105, truncated = 0 1.12.679.203 I slot print_timing: id 3 | task 251 | prompt eval time = 805.66 ms / 138 tokens ( 5.84 ms per token, 171.29 tokens per second) 1.12.679.205 I slot print_timing: id 3 | task 251 | eval time = 669.14 ms / 6 tokens ( 133.83 ms per token, 7.47 tokens per second) 1.12.679.205 I slot print_timing: id 3 | task 251 | total time = 1474.81 ms / 144 tokens 1.12.679.205 I slot print_timing: id 3 | task 251 | graphs reused = 3 1.12.679.206 I slot print_timing: id 3 | task 251 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.679.218 I slot release: id 3 | task 251 | stop processing: n_tokens = 143, truncated = 0 1.12.700.958 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.255 (> 0.100 thold), f_keep = 0.200 1.12.704.361 I slot launch_slot_: id 1 | task 261 | processing task, is_child = 0 1.12.706.782 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.252 (> 0.100 thold), f_keep = 0.248 1.12.707.834 I slot launch_slot_: id 2 | task 262 | processing task, is_child = 0 1.12.707.872 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.179 (> 0.100 thold), f_keep = 0.182 1.12.707.972 I slot launch_slot_: id 3 | task 263 | processing task, is_child = 0 1.13.729.987 I slot print_timing: id 1 | task 261 | prompt eval time = 981.04 ms / 102 tokens ( 9.62 ms per token, 103.97 tokens per second) 1.13.729.989 I slot print_timing: id 1 | task 261 | eval time = 40.96 ms / 2 tokens ( 40.96 ms per token, 24.41 tokens per second) 1.13.729.990 I slot print_timing: id 1 | task 261 | total time = 1022.00 ms / 104 tokens 1.13.729.990 I slot print_timing: id 1 | task 261 | graphs reused = 3 1.13.729.991 I slot print_timing: id 1 | task 261 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.730.008 I slot release: id 1 | task 261 | stop processing: n_tokens = 103, truncated = 0 1.13.781.590 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.215 (> 0.100 thold), f_keep = 0.252 1.13.782.243 I slot launch_slot_: id 1 | task 268 | processing task, is_child = 0 1.14.349.878 I slot print_timing: id 1 | task 268 | prompt eval time = 526.46 ms / 121 tokens ( 4.35 ms per token, 229.84 tokens per second) 1.14.349.883 I slot print_timing: id 1 | task 268 | eval time = 41.16 ms / 2 tokens ( 41.16 ms per token, 24.29 tokens per second) 1.14.349.884 I slot print_timing: id 1 | task 268 | total time = 567.62 ms / 123 tokens 1.14.349.884 I slot print_timing: id 1 | task 268 | graphs reused = 3 1.14.349.885 I slot print_timing: id 1 | task 268 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.349.903 I slot release: id 1 | task 268 | stop processing: n_tokens = 122, truncated = 0 1.14.401.307 I slot print_timing: id 2 | task 262 | prompt eval time = 981.11 ms / 103 tokens ( 9.53 ms per token, 104.98 tokens per second) 1.14.401.313 I slot print_timing: id 2 | task 262 | eval time = 712.19 ms / 7 tokens ( 118.70 ms per token, 8.42 tokens per second) 1.14.401.314 I slot print_timing: id 2 | task 262 | total time = 1693.30 ms / 110 tokens 1.14.401.314 I slot print_timing: id 2 | task 262 | graphs reused = 3 1.14.401.315 I slot print_timing: id 2 | task 262 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.401.329 I slot release: id 2 | task 262 | stop processing: n_tokens = 109, truncated = 0 1.14.401.471 I slot print_timing: id 3 | task 263 | prompt eval time = 981.19 ms / 145 tokens ( 6.77 ms per token, 147.78 tokens per second) 1.14.401.473 I slot print_timing: id 3 | task 263 | eval time = 712.26 ms / 7 tokens ( 118.71 ms per token, 8.42 tokens per second) 1.14.401.475 I slot print_timing: id 3 | task 263 | total time = 1693.44 ms / 152 tokens 1.14.401.475 I slot print_timing: id 3 | task 263 | graphs reused = 3 1.14.401.475 I slot print_timing: id 3 | task 263 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.401.490 I slot release: id 3 | task 263 | stop processing: n_tokens = 151, truncated = 0 1.14.401.494 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.226 (> 0.100 thold), f_keep = 0.213 1.14.404.323 I slot launch_slot_: id 1 | task 273 | processing task, is_child = 0 1.14.408.018 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.252 (> 0.100 thold), f_keep = 0.248 1.14.408.095 I slot launch_slot_: id 2 | task 274 | processing task, is_child = 0 1.14.408.123 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.167 (> 0.100 thold), f_keep = 0.172 1.14.408.189 I slot launch_slot_: id 3 | task 275 | processing task, is_child = 0 1.15.492.199 I slot print_timing: id 2 | task 274 | prompt eval time = 1043.10 ms / 107 tokens ( 9.75 ms per token, 102.58 tokens per second) 1.15.492.204 I slot print_timing: id 2 | task 274 | eval time = 40.88 ms / 2 tokens ( 40.88 ms per token, 24.46 tokens per second) 1.15.492.205 I slot print_timing: id 2 | task 274 | total time = 1083.98 ms / 109 tokens 1.15.492.205 I slot print_timing: id 2 | task 274 | graphs reused = 3 1.15.492.205 I slot print_timing: id 2 | task 274 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.492.225 I slot release: id 2 | task 274 | stop processing: n_tokens = 108, truncated = 0 1.15.543.991 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.173 (> 0.100 thold), f_keep = 0.241 1.15.545.639 I slot launch_slot_: id 2 | task 280 | processing task, is_child = 0 1.16.143.738 I slot print_timing: id 0 | task 176 | prompt eval time = 851.62 ms / 100 tokens ( 8.52 ms per token, 117.42 tokens per second) 1.16.143.743 I slot print_timing: id 0 | task 176 | eval time = 15417.47 ms / 71 tokens ( 220.25 ms per token, 4.54 tokens per second) 1.16.143.743 I slot print_timing: id 0 | task 176 | total time = 16269.09 ms / 171 tokens 1.16.143.744 I slot print_timing: id 0 | task 176 | graphs reused = 3 1.16.143.744 I slot print_timing: id 0 | task 176 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.143.763 I slot release: id 0 | task 176 | stop processing: n_tokens = 170, truncated = 0 1.16.143.852 I slot print_timing: id 1 | task 273 | prompt eval time = 1043.02 ms / 115 tokens ( 9.07 ms per token, 110.26 tokens per second) 1.16.143.854 I slot print_timing: id 1 | task 273 | eval time = 692.64 ms / 6 tokens ( 138.53 ms per token, 7.22 tokens per second) 1.16.143.854 I slot print_timing: id 1 | task 273 | total time = 1735.66 ms / 121 tokens 1.16.143.855 I slot print_timing: id 1 | task 273 | graphs reused = 3 1.16.143.855 I slot print_timing: id 1 | task 273 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.143.863 I slot release: id 1 | task 273 | stop processing: n_tokens = 120, truncated = 0 1.16.143.945 I slot print_timing: id 2 | task 280 | prompt eval time = 556.65 ms / 150 tokens ( 3.71 ms per token, 269.47 tokens per second) 1.16.143.950 I slot print_timing: id 2 | task 280 | eval time = 41.65 ms / 2 tokens ( 41.65 ms per token, 24.01 tokens per second) 1.16.143.951 I slot print_timing: id 2 | task 280 | total time = 598.30 ms / 152 tokens 1.16.143.951 I slot print_timing: id 2 | task 280 | graphs reused = 3 1.16.143.951 I slot print_timing: id 2 | task 280 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.143.958 I slot release: id 2 | task 280 | stop processing: n_tokens = 151, truncated = 0 1.16.144.045 I slot print_timing: id 3 | task 275 | prompt eval time = 1043.21 ms / 156 tokens ( 6.69 ms per token, 149.54 tokens per second) 1.16.144.048 I slot print_timing: id 3 | task 275 | eval time = 692.60 ms / 6 tokens ( 138.52 ms per token, 7.22 tokens per second) 1.16.144.048 I slot print_timing: id 3 | task 275 | total time = 1735.81 ms / 162 tokens 1.16.144.049 I slot print_timing: id 3 | task 275 | graphs reused = 3 1.16.144.049 I slot print_timing: id 3 | task 275 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.144.059 I slot release: id 3 | task 275 | stop processing: n_tokens = 161, truncated = 0 1.16.149.263 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.263 (> 0.100 thold), f_keep = 0.153 1.16.151.100 I slot launch_slot_: id 0 | task 284 | processing task, is_child = 0 1.16.157.689 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 1.16.157.774 I slot launch_slot_: id 1 | task 285 | processing task, is_child = 0 1.16.157.828 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.186 (> 0.100 thold), f_keep = 0.179 1.16.157.892 I slot launch_slot_: id 2 | task 286 | processing task, is_child = 0 1.16.157.922 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.158 (> 0.100 thold), f_keep = 0.161 1.16.157.987 I slot launch_slot_: id 3 | task 287 | processing task, is_child = 0 1.17.608.563 I slot print_timing: id 0 | task 284 | prompt eval time = 1409.77 ms / 99 tokens ( 14.24 ms per token, 70.22 tokens per second) 1.17.608.566 I slot print_timing: id 0 | task 284 | eval time = 40.79 ms / 2 tokens ( 40.79 ms per token, 24.51 tokens per second) 1.17.608.566 I slot print_timing: id 0 | task 284 | total time = 1450.57 ms / 101 tokens 1.17.608.567 I slot print_timing: id 0 | task 284 | graphs reused = 3 1.17.608.567 I slot print_timing: id 0 | task 284 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.608.585 I slot release: id 0 | task 284 | stop processing: n_tokens = 100, truncated = 0 1.17.608.675 I slot print_timing: id 1 | task 285 | prompt eval time = 1409.87 ms / 120 tokens ( 11.75 ms per token, 85.11 tokens per second) 1.17.608.677 I slot print_timing: id 1 | task 285 | eval time = 40.78 ms / 2 tokens ( 40.78 ms per token, 24.52 tokens per second) 1.17.608.677 I slot print_timing: id 1 | task 285 | total time = 1450.65 ms / 122 tokens 1.17.608.677 I slot print_timing: id 1 | task 285 | graphs reused = 3 1.17.608.678 I slot print_timing: id 1 | task 285 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.608.691 I slot release: id 1 | task 285 | stop processing: n_tokens = 121, truncated = 0 1.17.608.783 I slot print_timing: id 2 | task 286 | prompt eval time = 1409.96 ms / 145 tokens ( 9.72 ms per token, 102.84 tokens per second) 1.17.608.785 I slot print_timing: id 2 | task 286 | eval time = 40.77 ms / 2 tokens ( 40.77 ms per token, 24.53 tokens per second) 1.17.608.785 I slot print_timing: id 2 | task 286 | total time = 1450.73 ms / 147 tokens 1.17.608.786 I slot print_timing: id 2 | task 286 | graphs reused = 3 1.17.608.786 I slot print_timing: id 2 | task 286 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.608.802 I slot release: id 2 | task 286 | stop processing: n_tokens = 146, truncated = 0 1.17.608.896 I slot print_timing: id 3 | task 287 | prompt eval time = 1410.07 ms / 165 tokens ( 8.55 ms per token, 117.02 tokens per second) 1.17.608.897 I slot print_timing: id 3 | task 287 | eval time = 40.76 ms / 2 tokens ( 40.76 ms per token, 24.53 tokens per second) 1.17.608.897 I slot print_timing: id 3 | task 287 | total time = 1450.83 ms / 167 tokens 1.17.608.898 I slot print_timing: id 3 | task 287 | graphs reused = 3 1.17.608.898 I slot print_timing: id 3 | task 287 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.608.908 I slot release: id 3 | task 287 | stop processing: n_tokens = 166, truncated = 0 1.17.614.022 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.243 (> 0.100 thold), f_keep = 0.260 1.17.614.960 I slot launch_slot_: id 0 | task 291 | processing task, is_child = 0 1.17.621.407 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.208 (> 0.100 thold), f_keep = 0.215 1.17.621.491 I slot launch_slot_: id 1 | task 292 | processing task, is_child = 0 1.17.621.562 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.210 (> 0.100 thold), f_keep = 0.178 1.17.621.628 I slot launch_slot_: id 2 | task 293 | processing task, is_child = 0 1.17.621.655 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.174 (> 0.100 thold), f_keep = 0.157 1.17.621.718 I slot launch_slot_: id 3 | task 294 | processing task, is_child = 0 1.18.878.176 I slot print_timing: id 1 | task 292 | prompt eval time = 1215.21 ms / 125 tokens ( 9.72 ms per token, 102.86 tokens per second) 1.18.878.182 I slot print_timing: id 1 | task 292 | eval time = 41.22 ms / 2 tokens ( 41.22 ms per token, 24.26 tokens per second) 1.18.878.182 I slot print_timing: id 1 | task 292 | total time = 1256.43 ms / 127 tokens 1.18.878.183 I slot print_timing: id 1 | task 292 | graphs reused = 3 1.18.878.183 I slot print_timing: id 1 | task 292 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.878.200 I slot release: id 1 | task 292 | stop processing: n_tokens = 126, truncated = 0 1.18.878.287 I slot print_timing: id 2 | task 293 | prompt eval time = 1215.32 ms / 124 tokens ( 9.80 ms per token, 102.03 tokens per second) 1.18.878.289 I slot print_timing: id 2 | task 293 | eval time = 41.20 ms / 2 tokens ( 41.20 ms per token, 24.27 tokens per second) 1.18.878.289 I slot print_timing: id 2 | task 293 | total time = 1256.53 ms / 126 tokens 1.18.878.290 I slot print_timing: id 2 | task 293 | graphs reused = 3 1.18.878.290 I slot print_timing: id 2 | task 293 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.878.305 I slot release: id 2 | task 293 | stop processing: n_tokens = 125, truncated = 0 1.18.878.395 I slot print_timing: id 3 | task 294 | prompt eval time = 1215.43 ms / 149 tokens ( 8.16 ms per token, 122.59 tokens per second) 1.18.878.396 I slot print_timing: id 3 | task 294 | eval time = 41.19 ms / 2 tokens ( 41.19 ms per token, 24.28 tokens per second) 1.18.878.397 I slot print_timing: id 3 | task 294 | total time = 1256.62 ms / 151 tokens 1.18.878.397 I slot print_timing: id 3 | task 294 | graphs reused = 3 1.18.878.397 I slot print_timing: id 3 | task 294 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.878.408 I slot release: id 3 | task 294 | stop processing: n_tokens = 150, truncated = 0 1.18.900.330 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.190 (> 0.100 thold), f_keep = 0.214 1.18.902.548 I slot launch_slot_: id 1 | task 299 | processing task, is_child = 0 1.18.907.599 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.205 (> 0.100 thold), f_keep = 0.208 1.18.907.687 I slot launch_slot_: id 2 | task 300 | processing task, is_child = 0 1.18.907.726 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.173 1.18.908.906 I slot launch_slot_: id 3 | task 301 | processing task, is_child = 0 1.19.939.020 I slot print_timing: id 0 | task 291 | prompt eval time = 1215.10 ms / 107 tokens ( 11.36 ms per token, 88.06 tokens per second) 1.19.939.022 I slot print_timing: id 0 | task 291 | eval time = 1102.19 ms / 6 tokens ( 220.44 ms per token, 4.54 tokens per second) 1.19.939.023 I slot print_timing: id 0 | task 291 | total time = 2317.29 ms / 113 tokens 1.19.939.023 I slot print_timing: id 0 | task 291 | graphs reused = 3 1.19.939.024 I slot print_timing: id 0 | task 291 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.939.043 I slot release: id 0 | task 291 | stop processing: n_tokens = 112, truncated = 0 1.19.939.133 I slot print_timing: id 1 | task 299 | prompt eval time = 989.76 ms / 142 tokens ( 6.97 ms per token, 143.47 tokens per second) 1.19.939.136 I slot print_timing: id 1 | task 299 | eval time = 40.46 ms / 2 tokens ( 40.46 ms per token, 24.72 tokens per second) 1.19.939.136 I slot print_timing: id 1 | task 299 | total time = 1030.22 ms / 144 tokens 1.19.939.137 I slot print_timing: id 1 | task 299 | graphs reused = 3 1.19.939.137 I slot print_timing: id 1 | task 299 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.939.152 I slot release: id 1 | task 299 | stop processing: n_tokens = 143, truncated = 0 1.19.939.242 I slot print_timing: id 2 | task 300 | prompt eval time = 989.85 ms / 127 tokens ( 7.79 ms per token, 128.30 tokens per second) 1.19.939.245 I slot print_timing: id 2 | task 300 | eval time = 40.45 ms / 2 tokens ( 40.45 ms per token, 24.72 tokens per second) 1.19.939.245 I slot print_timing: id 2 | task 300 | total time = 1030.30 ms / 129 tokens 1.19.939.246 I slot print_timing: id 2 | task 300 | graphs reused = 3 1.19.939.246 I slot print_timing: id 2 | task 300 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.939.255 I slot release: id 2 | task 300 | stop processing: n_tokens = 128, truncated = 0 1.19.939.354 I slot print_timing: id 3 | task 301 | prompt eval time = 989.93 ms / 114 tokens ( 8.68 ms per token, 115.16 tokens per second) 1.19.939.357 I slot print_timing: id 3 | task 301 | eval time = 40.46 ms / 2 tokens ( 40.46 ms per token, 24.71 tokens per second) 1.19.939.357 I slot print_timing: id 3 | task 301 | total time = 1030.40 ms / 116 tokens 1.19.939.357 I slot print_timing: id 3 | task 301 | graphs reused = 3 1.19.939.357 I slot print_timing: id 3 | task 301 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.939.363 I slot release: id 3 | task 301 | stop processing: n_tokens = 115, truncated = 0 1.19.945.146 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.267 (> 0.100 thold), f_keep = 0.243 1.19.946.037 I slot launch_slot_: id 3 | task 305 | processing task, is_child = 0 1.19.951.064 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.187 (> 0.100 thold), f_keep = 0.232 1.19.951.148 I slot launch_slot_: id 0 | task 306 | processing task, is_child = 0 1.19.951.202 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.174 (> 0.100 thold), f_keep = 0.182 1.19.951.266 I slot launch_slot_: id 1 | task 307 | processing task, is_child = 0 1.19.951.291 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.174 (> 0.100 thold), f_keep = 0.203 1.19.951.360 I slot launch_slot_: id 2 | task 308 | processing task, is_child = 0 1.21.247.301 I slot print_timing: id 0 | task 306 | prompt eval time = 1254.46 ms / 139 tokens ( 9.02 ms per token, 110.80 tokens per second) 1.21.247.304 I slot print_timing: id 0 | task 306 | eval time = 41.47 ms / 2 tokens ( 41.47 ms per token, 24.12 tokens per second) 1.21.247.304 I slot print_timing: id 0 | task 306 | total time = 1295.93 ms / 141 tokens 1.21.247.304 I slot print_timing: id 0 | task 306 | graphs reused = 3 1.21.247.305 I slot print_timing: id 0 | task 306 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.247.325 I slot release: id 0 | task 306 | stop processing: n_tokens = 140, truncated = 0 1.21.247.414 I slot print_timing: id 1 | task 307 | prompt eval time = 1254.56 ms / 149 tokens ( 8.42 ms per token, 118.77 tokens per second) 1.21.247.417 I slot print_timing: id 1 | task 307 | eval time = 41.47 ms / 2 tokens ( 41.47 ms per token, 24.12 tokens per second) 1.21.247.417 I slot print_timing: id 1 | task 307 | total time = 1296.03 ms / 151 tokens 1.21.247.417 I slot print_timing: id 1 | task 307 | graphs reused = 3 1.21.247.418 I slot print_timing: id 1 | task 307 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.247.427 I slot release: id 1 | task 307 | stop processing: n_tokens = 150, truncated = 0 1.21.247.515 I slot print_timing: id 2 | task 308 | prompt eval time = 1254.66 ms / 149 tokens ( 8.42 ms per token, 118.76 tokens per second) 1.21.247.518 I slot print_timing: id 2 | task 308 | eval time = 41.45 ms / 2 tokens ( 41.45 ms per token, 24.13 tokens per second) 1.21.247.519 I slot print_timing: id 2 | task 308 | total time = 1296.11 ms / 151 tokens 1.21.247.519 I slot print_timing: id 2 | task 308 | graphs reused = 3 1.21.247.519 I slot print_timing: id 2 | task 308 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.247.528 I slot release: id 2 | task 308 | stop processing: n_tokens = 150, truncated = 0 1.21.269.534 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.265 (> 0.100 thold), f_keep = 0.186 1.21.271.808 I slot launch_slot_: id 0 | task 313 | processing task, is_child = 0 1.21.276.812 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.181 (> 0.100 thold), f_keep = 0.173 1.21.276.892 I slot launch_slot_: id 1 | task 314 | processing task, is_child = 0 1.21.276.922 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.182 (> 0.100 thold), f_keep = 0.173 1.21.276.995 I slot launch_slot_: id 2 | task 315 | processing task, is_child = 0 1.22.316.502 I slot print_timing: id 2 | task 315 | prompt eval time = 998.78 ms / 143 tokens ( 6.98 ms per token, 143.17 tokens per second) 1.22.316.507 I slot print_timing: id 2 | task 315 | eval time = 40.67 ms / 2 tokens ( 40.67 ms per token, 24.59 tokens per second) 1.22.316.508 I slot print_timing: id 2 | task 315 | total time = 1039.45 ms / 145 tokens 1.22.316.508 I slot print_timing: id 2 | task 315 | graphs reused = 4 1.22.316.509 I slot print_timing: id 2 | task 315 | graph reallocs = 0 / 0 (same size) / (changed size) 1.22.316.528 I slot release: id 2 | task 315 | stop processing: n_tokens = 144, truncated = 0 1.22.367.734 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.245 (> 0.100 thold), f_keep = 0.181 1.22.369.478 I slot launch_slot_: id 2 | task 320 | processing task, is_child = 0 1.22.783.270 I slot print_timing: id 1 | task 314 | prompt eval time = 998.70 ms / 144 tokens ( 6.94 ms per token, 144.19 tokens per second) 1.22.783.275 I slot print_timing: id 1 | task 314 | eval time = 507.53 ms / 4 tokens ( 169.18 ms per token, 5.91 tokens per second) 1.22.783.276 I slot print_timing: id 1 | task 314 | total time = 1506.24 ms / 148 tokens 1.22.783.276 I slot print_timing: id 1 | task 314 | graphs reused = 4 1.22.783.277 I slot print_timing: id 1 | task 314 | graph reallocs = 0 / 0 (same size) / (changed size) 1.22.783.298 I slot release: id 1 | task 314 | stop processing: n_tokens = 147, truncated = 0 1.22.859.693 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.146 (> 0.100 thold), f_keep = 0.177 1.22.861.354 I slot launch_slot_: id 1 | task 323 | processing task, is_child = 0 1.23.464.529 I slot print_timing: id 0 | task 313 | prompt eval time = 998.63 ms / 98 tokens ( 10.19 ms per token, 98.13 tokens per second) 1.23.464.532 I slot print_timing: id 0 | task 313 | eval time = 1188.89 ms / 7 tokens ( 198.15 ms per token, 5.05 tokens per second) 1.23.464.533 I slot print_timing: id 0 | task 313 | total time = 2187.52 ms / 105 tokens 1.23.464.533 I slot print_timing: id 0 | task 313 | graphs reused = 4 1.23.464.534 I slot print_timing: id 0 | task 313 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.464.551 I slot release: id 0 | task 313 | stop processing: n_tokens = 104, truncated = 0 1.23.502.021 I slot print_timing: id 1 | task 323 | prompt eval time = 603.33 ms / 178 tokens ( 3.39 ms per token, 295.03 tokens per second) 1.23.502.027 I slot print_timing: id 1 | task 323 | eval time = 37.32 ms / 2 tokens ( 37.32 ms per token, 26.80 tokens per second) 1.23.502.027 I slot print_timing: id 1 | task 323 | total time = 640.65 ms / 180 tokens 1.23.502.028 I slot print_timing: id 1 | task 323 | graphs reused = 4 1.23.502.028 I slot print_timing: id 1 | task 323 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.502.044 I slot release: id 1 | task 323 | stop processing: n_tokens = 179, truncated = 0 1.23.502.300 I slot print_timing: id 3 | task 305 | prompt eval time = 1254.76 ms / 105 tokens ( 11.95 ms per token, 83.68 tokens per second) 1.23.502.302 I slot print_timing: id 3 | task 305 | eval time = 2296.11 ms / 12 tokens ( 208.74 ms per token, 4.79 tokens per second) 1.23.502.302 I slot print_timing: id 3 | task 305 | total time = 3550.88 ms / 117 tokens 1.23.502.303 I slot print_timing: id 3 | task 305 | graphs reused = 4 1.23.502.303 I slot print_timing: id 3 | task 305 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.502.317 I slot release: id 3 | task 305 | stop processing: n_tokens = 116, truncated = 0 1.23.502.322 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.312 (> 0.100 thold), f_keep = 0.250 1.23.503.731 I slot launch_slot_: id 3 | task 327 | processing task, is_child = 0 1.23.507.904 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.255 (> 0.100 thold), f_keep = 0.250 1.23.508.292 I slot launch_slot_: id 0 | task 329 | processing task, is_child = 0 1.23.508.324 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.145 1.23.508.696 I slot launch_slot_: id 1 | task 328 | processing task, is_child = 0 1.24.551.415 I slot print_timing: id 2 | task 320 | prompt eval time = 490.11 ms / 106 tokens ( 4.62 ms per token, 216.28 tokens per second) 1.24.551.418 I slot print_timing: id 2 | task 320 | eval time = 1691.81 ms / 7 tokens ( 281.97 ms per token, 3.55 tokens per second) 1.24.551.419 I slot print_timing: id 2 | task 320 | total time = 2181.93 ms / 113 tokens 1.24.551.420 I slot print_timing: id 2 | task 320 | graphs reused = 4 1.24.551.420 I slot print_timing: id 2 | task 320 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.551.437 I slot release: id 2 | task 320 | stop processing: n_tokens = 112, truncated = 0 1.24.602.673 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.220 (> 0.100 thold), f_keep = 0.232 1.24.603.430 I slot launch_slot_: id 2 | task 334 | processing task, is_child = 0 1.25.028.909 I slot print_timing: id 3 | task 327 | prompt eval time = 1002.06 ms / 93 tokens ( 10.77 ms per token, 92.81 tokens per second) 1.25.028.914 I slot print_timing: id 3 | task 327 | eval time = 518.10 ms / 4 tokens ( 172.70 ms per token, 5.79 tokens per second) 1.25.028.914 I slot print_timing: id 3 | task 327 | total time = 1520.16 ms / 97 tokens 1.25.028.915 I slot print_timing: id 3 | task 327 | graphs reused = 4 1.25.028.915 I slot print_timing: id 3 | task 327 | graph reallocs = 0 / 0 (same size) / (changed size) 1.25.028.939 I slot release: id 3 | task 327 | stop processing: n_tokens = 96, truncated = 0 1.25.099.197 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.176 (> 0.100 thold), f_keep = 0.271 1.25.100.422 I slot launch_slot_: id 3 | task 337 | processing task, is_child = 0 1.25.556.885 I slot print_timing: id 0 | task 329 | prompt eval time = 1001.78 ms / 102 tokens ( 9.82 ms per token, 101.82 tokens per second) 1.25.556.887 I slot print_timing: id 0 | task 329 | eval time = 1046.39 ms / 6 tokens ( 209.28 ms per token, 4.78 tokens per second) 1.25.556.887 I slot print_timing: id 0 | task 329 | total time = 2048.18 ms / 108 tokens 1.25.556.888 I slot print_timing: id 0 | task 329 | graphs reused = 4 1.25.556.888 I slot print_timing: id 0 | task 329 | graph reallocs = 0 / 0 (same size) / (changed size) 1.25.556.905 I slot release: id 0 | task 329 | stop processing: n_tokens = 107, truncated = 0 1.25.557.066 I slot print_timing: id 1 | task 328 | prompt eval time = 1001.90 ms / 114 tokens ( 8.79 ms per token, 113.78 tokens per second) 1.25.557.071 I slot print_timing: id 1 | task 328 | eval time = 1046.44 ms / 6 tokens ( 209.29 ms per token, 4.78 tokens per second) 1.25.557.071 I slot print_timing: id 1 | task 328 | total time = 2048.34 ms / 120 tokens 1.25.557.071 I slot print_timing: id 1 | task 328 | graphs reused = 4 1.25.557.072 I slot print_timing: id 1 | task 328 | graph reallocs = 0 / 0 (same size) / (changed size) 1.25.557.081 I slot release: id 1 | task 328 | stop processing: n_tokens = 119, truncated = 0 1.25.624.008 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.226 (> 0.100 thold), f_keep = 0.243 1.25.625.270 I slot launch_slot_: id 0 | task 340 | processing task, is_child = 0 1.25.626.914 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.206 (> 0.100 thold), f_keep = 0.218 1.25.627.386 I slot launch_slot_: id 1 | task 341 | processing task, is_child = 0 1.26.347.496 I slot print_timing: id 0 | task 340 | prompt eval time = 679.54 ms / 115 tokens ( 5.91 ms per token, 169.23 tokens per second) 1.26.347.502 I slot print_timing: id 0 | task 340 | eval time = 40.56 ms / 2 tokens ( 40.56 ms per token, 24.65 tokens per second) 1.26.347.502 I slot print_timing: id 0 | task 340 | total time = 720.10 ms / 117 tokens 1.26.347.503 I slot print_timing: id 0 | task 340 | graphs reused = 4 1.26.347.503 I slot print_timing: id 0 | task 340 | graph reallocs = 0 / 0 (same size) / (changed size) 1.26.347.522 I slot release: id 0 | task 340 | stop processing: n_tokens = 116, truncated = 0 1.26.347.613 I slot print_timing: id 1 | task 341 | prompt eval time = 679.64 ms / 126 tokens ( 5.39 ms per token, 185.39 tokens per second) 1.26.347.614 I slot print_timing: id 1 | task 341 | eval time = 40.56 ms / 2 tokens ( 40.56 ms per token, 24.65 tokens per second) 1.26.347.615 I slot print_timing: id 1 | task 341 | total time = 720.20 ms / 128 tokens 1.26.347.615 I slot print_timing: id 1 | task 341 | graphs reused = 4 1.26.347.615 I slot print_timing: id 1 | task 341 | graph reallocs = 0 / 0 (same size) / (changed size) 1.26.347.628 I slot release: id 1 | task 341 | stop processing: n_tokens = 127, truncated = 0 1.26.347.715 I slot print_timing: id 2 | task 334 | prompt eval time = 495.76 ms / 118 tokens ( 4.20 ms per token, 238.02 tokens per second) 1.26.347.717 I slot print_timing: id 2 | task 334 | eval time = 1248.52 ms / 6 tokens ( 249.70 ms per token, 4.00 tokens per second) 1.26.347.718 I slot print_timing: id 2 | task 334 | total time = 1744.28 ms / 124 tokens 1.26.347.718 I slot print_timing: id 2 | task 334 | graphs reused = 4 1.26.347.718 I slot print_timing: id 2 | task 334 | graph reallocs = 0 / 0 (same size) / (changed size) 1.26.347.727 I slot release: id 2 | task 334 | stop processing: n_tokens = 123, truncated = 0 1.26.368.869 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.224 1.26.370.622 I slot launch_slot_: id 0 | task 346 | processing task, is_child = 0 1.26.374.265 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.211 (> 0.100 thold), f_keep = 0.213 1.26.374.338 I slot launch_slot_: id 1 | task 347 | processing task, is_child = 0 1.26.374.366 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.172 (> 0.100 thold), f_keep = 0.211 1.26.374.982 I slot launch_slot_: id 2 | task 348 | processing task, is_child = 0 1.27.391.946 I slot print_timing: id 3 | task 337 | prompt eval time = 523.57 ms / 148 tokens ( 3.54 ms per token, 282.67 tokens per second) 1.27.391.952 I slot print_timing: id 3 | task 337 | eval time = 1767.94 ms / 7 tokens ( 294.66 ms per token, 3.39 tokens per second) 1.27.391.953 I slot print_timing: id 3 | task 337 | total time = 2291.51 ms / 155 tokens 1.27.391.953 I slot print_timing: id 3 | task 337 | graphs reused = 5 1.27.391.953 I slot print_timing: id 3 | task 337 | graph reallocs = 0 / 0 (same size) / (changed size) 1.27.391.973 I slot release: id 3 | task 337 | stop processing: n_tokens = 154, truncated = 0 1.27.429.184 I slot print_timing: id 1 | task 347 | prompt eval time = 1016.72 ms / 128 tokens ( 7.94 ms per token, 125.90 tokens per second) 1.27.429.190 I slot print_timing: id 1 | task 347 | eval time = 37.45 ms / 2 tokens ( 37.45 ms per token, 26.70 tokens per second) 1.27.429.190 I slot print_timing: id 1 | task 347 | total time = 1054.17 ms / 130 tokens 1.27.429.190 I slot print_timing: id 1 | task 347 | graphs reused = 5 1.27.429.191 I slot print_timing: id 1 | task 347 | graph reallocs = 0 / 0 (same size) / (changed size) 1.27.429.209 I slot release: id 1 | task 347 | stop processing: n_tokens = 129, truncated = 0 1.27.429.307 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.197 (> 0.100 thold), f_keep = 0.202 1.27.430.998 I slot launch_slot_: id 1 | task 352 | processing task, is_child = 0 1.27.433.786 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.162 (> 0.100 thold), f_keep = 0.169 1.27.433.867 I slot launch_slot_: id 3 | task 353 | processing task, is_child = 0 1.28.468.583 I slot print_timing: id 1 | task 352 | prompt eval time = 990.69 ms / 132 tokens ( 7.51 ms per token, 133.24 tokens per second) 1.28.468.591 I slot print_timing: id 1 | task 352 | eval time = 44.02 ms / 2 tokens ( 44.02 ms per token, 22.72 tokens per second) 1.28.468.593 I slot print_timing: id 1 | task 352 | total time = 1034.70 ms / 134 tokens 1.28.468.594 I slot print_timing: id 1 | task 352 | graphs reused = 5 1.28.468.595 I slot print_timing: id 1 | task 352 | graph reallocs = 0 / 0 (same size) / (changed size) 1.28.468.627 I slot release: id 1 | task 352 | stop processing: n_tokens = 133, truncated = 0 1.28.469.058 I slot print_timing: id 3 | task 353 | prompt eval time = 991.02 ms / 160 tokens ( 6.19 ms per token, 161.45 tokens per second) 1.28.469.065 I slot print_timing: id 3 | task 353 | eval time = 44.14 ms / 2 tokens ( 44.14 ms per token, 22.65 tokens per second) 1.28.469.067 I slot print_timing: id 3 | task 353 | total time = 1035.16 ms / 162 tokens 1.28.469.067 I slot print_timing: id 3 | task 353 | graphs reused = 5 1.28.469.068 I slot print_timing: id 3 | task 353 | graph reallocs = 0 / 0 (same size) / (changed size) 1.28.469.101 I slot release: id 3 | task 353 | stop processing: n_tokens = 161, truncated = 0 1.28.515.211 I slot print_timing: id 2 | task 348 | prompt eval time = 1016.83 ms / 151 tokens ( 6.73 ms per token, 148.50 tokens per second) 1.28.515.219 I slot print_timing: id 2 | task 348 | eval time = 1123.36 ms / 6 tokens ( 224.67 ms per token, 4.45 tokens per second) 1.28.515.220 I slot print_timing: id 2 | task 348 | total time = 2140.18 ms / 157 tokens 1.28.515.220 I slot print_timing: id 2 | task 348 | graphs reused = 5 1.28.515.221 I slot print_timing: id 2 | task 348 | graph reallocs = 0 / 0 (same size) / (changed size) 1.28.515.243 I slot release: id 2 | task 348 | stop processing: n_tokens = 156, truncated = 0 1.28.515.250 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.195 1.28.517.589 I slot launch_slot_: id 1 | task 358 | processing task, is_child = 0 1.28.525.116 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.149 (> 0.100 thold), f_keep = 0.167 1.28.525.243 I slot launch_slot_: id 2 | task 359 | processing task, is_child = 0 1.28.525.288 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.181 (> 0.100 thold), f_keep = 0.161 1.28.525.394 I slot launch_slot_: id 3 | task 360 | processing task, is_child = 0 1.29.615.932 I slot print_timing: id 0 | task 346 | prompt eval time = 1016.63 ms / 113 tokens ( 9.00 ms per token, 111.15 tokens per second) 1.29.615.935 I slot print_timing: id 0 | task 346 | eval time = 2224.30 ms / 7 tokens ( 370.72 ms per token, 2.70 tokens per second) 1.29.615.936 I slot print_timing: id 0 | task 346 | total time = 3240.93 ms / 120 tokens 1.29.615.936 I slot print_timing: id 0 | task 346 | graphs reused = 5 1.29.615.936 I slot print_timing: id 0 | task 346 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.615.956 I slot release: id 0 | task 346 | stop processing: n_tokens = 119, truncated = 0 1.29.695.432 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.271 (> 0.100 thold), f_keep = 0.218 1.29.696.958 I slot launch_slot_: id 0 | task 363 | processing task, is_child = 0 1.30.055.346 I slot print_timing: id 1 | task 358 | prompt eval time = 1169.80 ms / 113 tokens ( 10.35 ms per token, 96.60 tokens per second) 1.30.055.349 I slot print_timing: id 1 | task 358 | eval time = 360.14 ms / 2 tokens ( 360.14 ms per token, 2.78 tokens per second) 1.30.055.350 I slot print_timing: id 1 | task 358 | total time = 1529.94 ms / 115 tokens 1.30.055.350 I slot print_timing: id 1 | task 358 | graphs reused = 5 1.30.055.350 I slot print_timing: id 1 | task 358 | graph reallocs = 0 / 0 (same size) / (changed size) 1.30.055.378 I slot release: id 1 | task 358 | stop processing: n_tokens = 114, truncated = 0 1.30.055.651 I slot print_timing: id 3 | task 360 | prompt eval time = 1169.96 ms / 144 tokens ( 8.12 ms per token, 123.08 tokens per second) 1.30.055.655 I slot print_timing: id 3 | task 360 | eval time = 360.22 ms / 2 tokens ( 360.22 ms per token, 2.78 tokens per second) 1.30.055.655 I slot print_timing: id 3 | task 360 | total time = 1530.18 ms / 146 tokens 1.30.055.656 I slot print_timing: id 3 | task 360 | graphs reused = 5 1.30.055.656 I slot print_timing: id 3 | task 360 | graph reallocs = 0 / 0 (same size) / (changed size) 1.30.055.668 I slot release: id 3 | task 360 | stop processing: n_tokens = 145, truncated = 0 1.30.114.489 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.206 (> 0.100 thold), f_keep = 0.228 1.30.116.624 I slot launch_slot_: id 1 | task 366 | processing task, is_child = 0 1.30.118.051 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.226 (> 0.100 thold), f_keep = 0.179 1.30.118.127 I slot launch_slot_: id 3 | task 367 | processing task, is_child = 0 1.30.928.819 I slot print_timing: id 2 | task 359 | prompt eval time = 1169.88 ms / 175 tokens ( 6.69 ms per token, 149.59 tokens per second) 1.30.928.822 I slot print_timing: id 2 | task 359 | eval time = 1233.50 ms / 4 tokens ( 411.17 ms per token, 2.43 tokens per second) 1.30.928.822 I slot print_timing: id 2 | task 359 | total time = 2403.38 ms / 179 tokens 1.30.928.823 I slot print_timing: id 2 | task 359 | graphs reused = 5 1.30.928.823 I slot print_timing: id 2 | task 359 | graph reallocs = 0 / 0 (same size) / (changed size) 1.30.928.849 I slot release: id 2 | task 359 | stop processing: n_tokens = 178, truncated = 0 1.31.030.229 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.203 (> 0.100 thold), f_keep = 0.146 1.31.033.283 I slot launch_slot_: id 2 | task 370 | processing task, is_child = 0 1.31.466.509 I slot print_timing: id 3 | task 367 | prompt eval time = 912.08 ms / 115 tokens ( 7.93 ms per token, 126.09 tokens per second) 1.31.466.513 I slot print_timing: id 3 | task 367 | eval time = 436.28 ms / 2 tokens ( 436.28 ms per token, 2.29 tokens per second) 1.31.466.513 I slot print_timing: id 3 | task 367 | total time = 1348.35 ms / 117 tokens 1.31.466.513 I slot print_timing: id 3 | task 367 | graphs reused = 5 1.31.466.514 I slot print_timing: id 3 | task 367 | graph reallocs = 0 / 0 (same size) / (changed size) 1.31.466.532 I slot release: id 3 | task 367 | stop processing: n_tokens = 116, truncated = 0 1.31.574.143 I slot print_timing: id 0 | task 363 | prompt eval time = 417.43 ms / 96 tokens ( 4.35 ms per token, 229.98 tokens per second) 1.31.574.145 I slot print_timing: id 0 | task 363 | eval time = 1459.74 ms / 6 tokens ( 291.95 ms per token, 3.43 tokens per second) 1.31.574.146 I slot print_timing: id 0 | task 363 | total time = 1877.17 ms / 102 tokens 1.31.574.146 I slot print_timing: id 0 | task 363 | graphs reused = 5 1.31.574.146 I slot print_timing: id 0 | task 363 | graph reallocs = 0 / 0 (same size) / (changed size) 1.31.574.160 I slot release: id 0 | task 363 | stop processing: n_tokens = 101, truncated = 0 1.31.636.256 I slot print_timing: id 1 | task 366 | prompt eval time = 912.00 ms / 126 tokens ( 7.24 ms per token, 138.16 tokens per second) 1.31.636.262 I slot print_timing: id 1 | task 366 | eval time = 606.12 ms / 6 tokens ( 121.22 ms per token, 8.25 tokens per second) 1.31.636.262 I slot print_timing: id 1 | task 366 | total time = 1518.12 ms / 132 tokens 1.31.636.263 I slot print_timing: id 1 | task 366 | graphs reused = 6 1.31.636.263 I slot print_timing: id 1 | task 366 | graph reallocs = 0 / 0 (same size) / (changed size) 1.31.636.275 I slot release: id 1 | task 366 | stop processing: n_tokens = 131, truncated = 0 1.31.676.820 I slot print_timing: id 2 | task 370 | prompt eval time = 503.86 ms / 128 tokens ( 3.94 ms per token, 254.04 tokens per second) 1.31.676.823 I slot print_timing: id 2 | task 370 | eval time = 139.67 ms / 6 tokens ( 27.93 ms per token, 35.80 tokens per second) 1.31.676.823 I slot print_timing: id 2 | task 370 | total time = 643.53 ms / 134 tokens 1.31.676.824 I slot print_timing: id 2 | task 370 | graphs reused = 7 1.31.676.824 I slot print_timing: id 2 | task 370 | graph reallocs = 0 / 0 (same size) / (changed size) 1.31.676.837 I slot release: id 2 | task 370 | stop processing: n_tokens = 133, truncated = 0 1.31.695.521 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 116, t_last = 352874360712 1.31.697.574 I slot launch_slot_: id 3 | task 378 | processing task, is_child = 0 1.31.703.533 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 101, t_last = 352874468340 1.31.703.582 I slot launch_slot_: id 0 | task 379 | processing task, is_child = 0 1.31.703.654 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 131, t_last = 352874530455 1.31.703.708 I slot launch_slot_: id 1 | task 380 | processing task, is_child = 0 1.31.703.745 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 133, t_last = 352874571018 1.31.703.803 I slot launch_slot_: id 2 | task 381 | processing task, is_child = 0 1.35.204.399 I slot print_timing: id 0 | task 379 | prompt processing, n_tokens = 532, progress = 0.51, t = 3.50 s / 151.98 tokens per second 1.35.289.352 I slot print_timing: id 1 | task 380 | prompt processing, n_tokens = 525, progress = 0.50, t = 3.50 s / 149.98 tokens per second 1.35.294.367 I slot print_timing: id 2 | task 381 | prompt processing, n_tokens = 540, progress = 0.51, t = 3.50 s / 154.26 tokens per second 1.35.297.763 I slot print_timing: id 3 | task 378 | prompt processing, n_tokens = 513, progress = 0.50, t = 3.50 s / 146.55 tokens per second 1.38.323.504 I slot print_timing: id 0 | task 379 | prompt processing, n_tokens = 953, progress = 0.91, t = 6.62 s / 143.96 tokens per second 1.38.464.911 I slot print_timing: id 1 | task 380 | prompt processing, n_tokens = 953, progress = 0.92, t = 6.62 s / 143.97 tokens per second 1.38.468.591 I slot print_timing: id 2 | task 381 | prompt processing, n_tokens = 953, progress = 0.90, t = 6.62 s / 143.97 tokens per second 1.38.471.802 I slot print_timing: id 3 | task 378 | prompt processing, n_tokens = 953, progress = 0.93, t = 6.62 s / 143.97 tokens per second 1.39.362.781 I slot print_timing: id 0 | task 379 | prompt processing, n_tokens = 1044, progress = 1.00, t = 7.66 s / 136.31 tokens per second 1.39.449.379 I slot print_timing: id 1 | task 380 | prompt processing, n_tokens = 1037, progress = 1.00, t = 7.66 s / 135.40 tokens per second 1.39.453.666 I slot print_timing: id 2 | task 381 | prompt processing, n_tokens = 1052, progress = 1.00, t = 7.66 s / 137.36 tokens per second 1.39.457.160 I slot print_timing: id 3 | task 378 | prompt processing, n_tokens = 1025, progress = 1.00, t = 7.66 s / 133.83 tokens per second 1.43.533.228 I slot print_timing: id 0 | task 379 | n_gen = 100, tg = 24.92 t/s, tg_3s = 25.17 t/s 1.43.533.404 I slot print_timing: id 1 | task 380 | n_gen = 100, tg = 24.91 t/s, tg_3s = 25.17 t/s 1.43.533.576 I slot print_timing: id 2 | task 381 | n_gen = 100, tg = 24.91 t/s, tg_3s = 25.17 t/s 1.43.533.746 I slot print_timing: id 3 | task 378 | n_gen = 100, tg = 24.91 t/s, tg_3s = 25.17 t/s 1.43.815.160 I slot print_timing: id 3 | task 378 | prompt eval time = 7856.26 ms / 1029 tokens ( 7.63 ms per token, 130.98 tokens per second) 1.43.815.168 I slot print_timing: id 3 | task 378 | eval time = 4254.99 ms / 107 tokens ( 40.14 ms per token, 24.91 tokens per second) 1.43.815.169 I slot print_timing: id 3 | task 378 | total time = 12111.25 ms / 1136 tokens 1.43.815.170 I slot print_timing: id 3 | task 378 | graphs reused = 114 1.43.815.171 I slot print_timing: id 3 | task 378 | graph reallocs = 0 / 0 (same size) / (changed size) 1.43.815.245 I slot release: id 3 | task 378 | stop processing: n_tokens = 1135, truncated = 0 1.43.856.478 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.909 (> 0.100 thold), f_keep = 0.856 1.43.856.510 I slot launch_slot_: id 3 | task 495 | processing task, is_child = 0 1.45.102.556 I slot print_timing: id 1 | task 380 | prompt eval time = 7856.00 ms / 1041 tokens ( 7.55 ms per token, 132.51 tokens per second) 1.45.102.563 I slot print_timing: id 1 | task 380 | eval time = 5542.71 ms / 129 tokens ( 43.30 ms per token, 23.09 tokens per second) 1.45.102.565 I slot print_timing: id 1 | task 380 | total time = 13398.71 ms / 1170 tokens 1.45.102.565 I slot print_timing: id 1 | task 380 | graphs reused = 132 1.45.102.566 I slot print_timing: id 1 | task 380 | graph reallocs = 0 / 0 (same size) / (changed size) 1.45.102.637 I slot release: id 1 | task 380 | stop processing: n_tokens = 1169, truncated = 0 1.45.159.705 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.831 1.45.159.730 I slot launch_slot_: id 1 | task 518 | processing task, is_child = 0 1.46.548.779 I slot print_timing: id 0 | task 379 | n_gen = 153, tg = 21.75 t/s, tg_3s = 17.58 t/s 1.46.549.119 I slot print_timing: id 2 | task 381 | n_gen = 153, tg = 21.75 t/s, tg_3s = 17.58 t/s 1.48.479.840 I slot print_timing: id 2 | task 381 | prompt eval time = 7856.07 ms / 1056 tokens ( 7.44 ms per token, 134.42 tokens per second) 1.48.479.848 I slot print_timing: id 2 | task 381 | eval time = 8919.89 ms / 201 tokens ( 44.60 ms per token, 22.42 tokens per second) 1.48.479.849 I slot print_timing: id 2 | task 381 | total time = 16775.96 ms / 1257 tokens 1.48.479.850 I slot print_timing: id 2 | task 381 | graphs reused = 200 1.48.479.851 I slot print_timing: id 2 | task 381 | graph reallocs = 0 / 0 (same size) / (changed size) 1.48.479.923 I slot release: id 2 | task 381 | stop processing: n_tokens = 1256, truncated = 0 1.48.537.565 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.902 (> 0.100 thold), f_keep = 0.773 1.48.537.594 I slot launch_slot_: id 2 | task 591 | processing task, is_child = 0 1.49.275.463 I slot print_timing: id 3 | task 495 | n_gen = 100, tg = 20.03 t/s, tg_3s = 20.23 t/s 1.49.557.344 I slot print_timing: id 0 | task 379 | n_gen = 216, tg = 21.51 t/s, tg_3s = 20.94 t/s 1.50.161.097 I slot print_timing: id 1 | task 518 | n_gen = 100, tg = 22.20 t/s, tg_3s = 22.43 t/s 1.52.298.038 I slot print_timing: id 3 | task 495 | n_gen = 175, tg = 21.84 t/s, tg_3s = 24.81 t/s 1.52.578.972 I slot print_timing: id 0 | task 379 | n_gen = 291, tg = 22.27 t/s, tg_3s = 24.82 t/s 1.53.061.727 I slot print_timing: id 2 | task 591 | n_gen = 100, tg = 24.77 t/s, tg_3s = 25.02 t/s 1.53.182.387 I slot print_timing: id 1 | task 518 | n_gen = 175, tg = 23.26 t/s, tg_3s = 24.82 t/s 1.55.316.803 I slot print_timing: id 3 | task 495 | n_gen = 250, tg = 22.67 t/s, tg_3s = 24.84 t/s 1.55.598.735 I slot print_timing: id 0 | task 379 | n_gen = 366, tg = 22.76 t/s, tg_3s = 24.84 t/s 1.56.082.689 I slot print_timing: id 2 | task 591 | n_gen = 175, tg = 24.79 t/s, tg_3s = 24.83 t/s 1.56.203.017 I slot print_timing: id 1 | task 518 | n_gen = 250, tg = 23.71 t/s, tg_3s = 24.83 t/s 1.56.364.426 I slot print_timing: id 3 | task 495 | prompt eval time = 475.26 ms / 97 tokens ( 4.90 ms per token, 204.10 tokens per second) 1.56.364.431 I slot print_timing: id 3 | task 495 | eval time = 12032.65 ms / 276 tokens ( 43.76 ms per token, 22.85 tokens per second) 1.56.364.432 I slot print_timing: id 3 | task 495 | total time = 12507.91 ms / 373 tokens 1.56.364.433 I slot print_timing: id 3 | task 495 | graphs reused = 379 1.56.364.434 I slot print_timing: id 3 | task 495 | graph reallocs = 0 / 0 (same size) / (changed size) 1.56.364.507 I slot release: id 3 | task 495 | stop processing: n_tokens = 1343, truncated = 0 1.56.406.491 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.924 (> 0.100 thold), f_keep = 0.723 1.56.406.515 I slot launch_slot_: id 3 | task 776 | processing task, is_child = 0 1.57.947.655 I slot print_timing: id 1 | task 518 | prompt eval time = 542.09 ms / 104 tokens ( 5.21 ms per token, 191.85 tokens per second) 1.57.947.664 I slot print_timing: id 1 | task 518 | eval time = 12245.83 ms / 284 tokens ( 43.27 ms per token, 23.11 tokens per second) 1.57.947.665 I slot print_timing: id 1 | task 518 | total time = 12787.92 ms / 388 tokens 1.57.947.666 I slot print_timing: id 1 | task 518 | graphs reused = 405 1.57.947.667 I slot print_timing: id 1 | task 518 | graph reallocs = 0 / 0 (same size) / (changed size) 1.57.947.748 I slot release: id 1 | task 518 | stop processing: n_tokens = 1358, truncated = 0 1.58.004.417 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.899 (> 0.100 thold), f_keep = 0.715 1.58.004.443 I slot launch_slot_: id 1 | task 807 | processing task, is_child = 0 1.58.551.112 I slot print_timing: id 0 | task 379 | prompt eval time = 7855.93 ms / 1048 tokens ( 7.50 ms per token, 133.40 tokens per second) 1.58.551.118 I slot print_timing: id 0 | task 379 | eval time = 18991.37 ms / 418 tokens ( 45.54 ms per token, 21.96 tokens per second) 1.58.551.118 I slot print_timing: id 0 | task 379 | total time = 26847.30 ms / 1466 tokens 1.58.551.119 I slot print_timing: id 0 | task 379 | graphs reused = 405 1.58.551.119 I slot print_timing: id 0 | task 379 | graph reallocs = 0 / 0 (same size) / (changed size) 1.58.551.161 I slot release: id 0 | task 379 | stop processing: n_tokens = 1465, truncated = 0 1.58.590.014 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.877 (> 0.100 thold), f_keep = 0.663 1.58.590.032 I slot launch_slot_: id 0 | task 811 | processing task, is_child = 0 1.59.118.499 I slot print_timing: id 2 | task 591 | n_gen = 218, tg = 21.58 t/s, tg_3s = 14.16 t/s 2.01.784.933 I slot print_timing: id 3 | task 776 | n_gen = 100, tg = 20.07 t/s, tg_3s = 20.27 t/s 2.02.147.393 I slot print_timing: id 2 | task 591 | n_gen = 293, tg = 22.32 t/s, tg_3s = 24.76 t/s 2.02.993.848 I slot print_timing: id 1 | task 807 | n_gen = 100, tg = 22.28 t/s, tg_3s = 22.51 t/s 2.03.114.302 I slot print_timing: id 0 | task 811 | n_gen = 100, tg = 24.77 t/s, tg_3s = 25.03 t/s 2.04.808.872 I slot print_timing: id 3 | task 776 | n_gen = 175, tg = 21.87 t/s, tg_3s = 24.80 t/s 2.05.171.155 I slot print_timing: id 2 | task 591 | n_gen = 368, tg = 22.79 t/s, tg_3s = 24.80 t/s 2.06.018.911 I slot print_timing: id 1 | task 807 | n_gen = 175, tg = 23.30 t/s, tg_3s = 24.79 t/s 2.06.139.923 I slot print_timing: id 0 | task 811 | n_gen = 175, tg = 24.78 t/s, tg_3s = 24.79 t/s 2.06.261.105 I slot print_timing: id 1 | task 807 | prompt eval time = 546.86 ms / 109 tokens ( 5.02 ms per token, 199.32 tokens per second) 2.06.261.109 I slot print_timing: id 1 | task 807 | eval time = 7709.79 ms / 181 tokens ( 42.83 ms per token, 23.35 tokens per second) 2.06.261.110 I slot print_timing: id 1 | task 807 | total time = 8256.65 ms / 290 tokens 2.06.261.111 I slot print_timing: id 1 | task 807 | graphs reused = 582 2.06.261.112 I slot print_timing: id 1 | task 807 | graph reallocs = 0 / 0 (same size) / (changed size) 2.06.261.185 I slot release: id 1 | task 807 | stop processing: n_tokens = 1260, truncated = 0 2.06.318.286 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.771 2.06.318.320 I slot launch_slot_: id 1 | task 992 | processing task, is_child = 0 2.07.842.319 I slot print_timing: id 3 | task 776 | n_gen = 239, tg = 21.65 t/s, tg_3s = 21.10 t/s 2.08.205.730 I slot print_timing: id 2 | task 591 | n_gen = 432, tg = 22.52 t/s, tg_3s = 21.09 t/s 2.09.175.050 I slot print_timing: id 0 | task 811 | n_gen = 239, tg = 23.67 t/s, tg_3s = 21.09 t/s 2.10.840.102 I slot print_timing: id 1 | task 992 | n_gen = 100, tg = 24.64 t/s, tg_3s = 24.89 t/s 2.10.880.707 I slot print_timing: id 3 | task 776 | n_gen = 314, tg = 22.31 t/s, tg_3s = 24.68 t/s 2.11.244.247 I slot print_timing: id 2 | task 591 | n_gen = 507, tg = 22.81 t/s, tg_3s = 24.68 t/s 2.11.568.661 I slot print_timing: id 3 | task 776 | prompt eval time = 445.19 ms / 80 tokens ( 5.56 ms per token, 179.70 tokens per second) 2.11.568.667 I slot print_timing: id 3 | task 776 | eval time = 14716.93 ms / 331 tokens ( 44.60 ms per token, 22.42 tokens per second) 2.11.568.668 I slot print_timing: id 3 | task 776 | total time = 15162.13 ms / 411 tokens 2.11.568.669 I slot print_timing: id 3 | task 776 | graphs reused = 697 2.11.568.669 I slot print_timing: id 3 | task 776 | graph reallocs = 0 / 0 (same size) / (changed size) 2.11.568.753 I slot release: id 3 | task 776 | stop processing: n_tokens = 1381, truncated = 0 2.11.611.104 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.703 2.11.611.139 I slot launch_slot_: id 3 | task 1113 | processing task, is_child = 0 2.12.192.622 I slot print_timing: id 0 | task 811 | n_gen = 305, tg = 23.25 t/s, tg_3s = 21.87 t/s 2.13.857.483 I slot print_timing: id 1 | task 992 | n_gen = 166, tg = 23.45 t/s, tg_3s = 21.87 t/s 2.14.261.496 I slot print_timing: id 2 | task 591 | n_gen = 573, tg = 22.70 t/s, tg_3s = 21.87 t/s 2.14.706.037 I slot print_timing: id 1 | task 992 | prompt eval time = 503.45 ms / 92 tokens ( 5.47 ms per token, 182.74 tokens per second) 2.14.706.042 I slot print_timing: id 1 | task 992 | eval time = 7884.26 ms / 187 tokens ( 42.39 ms per token, 23.59 tokens per second) 2.14.706.043 I slot print_timing: id 1 | task 992 | total time = 8387.71 ms / 279 tokens 2.14.706.044 I slot print_timing: id 1 | task 992 | graphs reused = 762 2.14.706.045 I slot print_timing: id 1 | task 992 | graph reallocs = 0 / 0 (same size) / (changed size) 2.14.706.114 I slot release: id 1 | task 992 | stop processing: n_tokens = 1249, truncated = 0 2.14.763.447 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.777 2.14.763.474 I slot launch_slot_: id 1 | task 1183 | processing task, is_child = 0 2.15.205.271 I slot print_timing: id 0 | task 811 | n_gen = 370, tg = 22.94 t/s, tg_3s = 21.58 t/s 2.16.345.364 I slot print_timing: id 2 | task 591 | prompt eval time = 527.07 ms / 105 tokens ( 5.02 ms per token, 199.21 tokens per second) 2.16.345.371 I slot print_timing: id 2 | task 591 | eval time = 27280.69 ms / 615 tokens ( 44.43 ms per token, 22.51 tokens per second) 2.16.345.372 I slot print_timing: id 2 | task 591 | total time = 27807.76 ms / 720 tokens 2.16.345.373 I slot print_timing: id 2 | task 591 | graphs reused = 789 2.16.345.373 I slot print_timing: id 2 | task 591 | graph reallocs = 0 / 0 (same size) / (changed size) 2.16.345.437 I slot release: id 2 | task 591 | stop processing: n_tokens = 1690, truncated = 0 2.16.402.314 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.575 2.16.402.348 I slot launch_slot_: id 2 | task 1215 | processing task, is_child = 0 2.16.729.870 I slot print_timing: id 3 | task 1113 | n_gen = 100, tg = 21.06 t/s, tg_3s = 21.27 t/s 2.18.206.548 I slot print_timing: id 0 | task 811 | n_gen = 435, tg = 22.74 t/s, tg_3s = 21.66 t/s 2.19.575.276 I slot print_timing: id 1 | task 1183 | n_gen = 100, tg = 22.66 t/s, tg_3s = 22.88 t/s 2.19.696.036 I slot print_timing: id 0 | task 811 | prompt eval time = 528.30 ms / 136 tokens ( 3.88 ms per token, 257.43 tokens per second) 2.19.696.044 I slot print_timing: id 0 | task 811 | eval time = 20577.70 ms / 472 tokens ( 43.69 ms per token, 22.89 tokens per second) 2.19.696.045 I slot print_timing: id 0 | task 811 | total time = 21106.00 ms / 608 tokens 2.19.696.045 I slot print_timing: id 0 | task 811 | graphs reused = 858 2.19.696.046 I slot print_timing: id 0 | task 811 | graph reallocs = 0 / 0 (same size) / (changed size) 2.19.696.124 I slot release: id 0 | task 811 | stop processing: n_tokens = 1578, truncated = 0 2.19.738.545 I slot print_timing: id 3 | task 1113 | n_gen = 173, tg = 22.31 t/s, tg_3s = 24.26 t/s 2.19.738.553 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.615 2.19.738.575 I slot launch_slot_: id 0 | task 1290 | processing task, is_child = 0 2.21.194.115 I slot print_timing: id 2 | task 1215 | n_gen = 100, tg = 22.65 t/s, tg_3s = 22.88 t/s 2.21.314.553 I slot print_timing: id 3 | task 1113 | prompt eval time = 418.27 ms / 70 tokens ( 5.98 ms per token, 167.36 tokens per second) 2.21.314.558 I slot print_timing: id 3 | task 1113 | eval time = 9285.14 ms / 203 tokens ( 45.97 ms per token, 21.76 tokens per second) 2.21.314.559 I slot print_timing: id 3 | task 1113 | total time = 9703.41 ms / 273 tokens 2.21.314.559 I slot print_timing: id 3 | task 1113 | graphs reused = 886 2.21.314.560 I slot print_timing: id 3 | task 1113 | graph reallocs = 0 / 0 (same size) / (changed size) 2.21.314.632 I slot release: id 3 | task 1113 | stop processing: n_tokens = 1243, truncated = 0 2.21.356.291 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.895 (> 0.100 thold), f_keep = 0.781 2.21.356.315 I slot launch_slot_: id 3 | task 1322 | processing task, is_child = 0 2.22.590.916 I slot print_timing: id 1 | task 1183 | n_gen = 155, tg = 20.85 t/s, tg_3s = 18.24 t/s 2.24.234.080 I slot print_timing: id 2 | task 1215 | n_gen = 165, tg = 22.13 t/s, tg_3s = 21.38 t/s 2.24.594.744 I slot print_timing: id 0 | task 1290 | n_gen = 100, tg = 22.48 t/s, tg_3s = 22.71 t/s 2.25.597.341 I slot print_timing: id 1 | task 1183 | n_gen = 230, tg = 22.04 t/s, tg_3s = 24.95 t/s 2.25.838.912 I slot print_timing: id 3 | task 1322 | n_gen = 100, tg = 24.90 t/s, tg_3s = 25.15 t/s 2.26.847.428 I slot print_timing: id 0 | task 1290 | prompt eval time = 453.02 ms / 89 tokens ( 5.09 ms per token, 196.46 tokens per second) 2.26.847.436 I slot print_timing: id 0 | task 1290 | eval time = 6655.82 ms / 156 tokens ( 42.94 ms per token, 23.29 tokens per second) 2.26.847.437 I slot print_timing: id 0 | task 1290 | total time = 7108.84 ms / 245 tokens 2.26.847.438 I slot print_timing: id 0 | task 1290 | graphs reused = 1008 2.26.847.438 I slot print_timing: id 0 | task 1290 | graph reallocs = 0 / 0 (same size) / (changed size) 2.26.847.514 I slot release: id 0 | task 1290 | stop processing: n_tokens = 1214, truncated = 0 2.26.889.573 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.947 (> 0.100 thold), f_keep = 0.800 2.26.889.597 I slot launch_slot_: id 0 | task 1450 | processing task, is_child = 0 2.27.260.651 I slot print_timing: id 2 | task 1215 | n_gen = 233, tg = 22.23 t/s, tg_3s = 22.47 t/s 2.28.633.534 I slot print_timing: id 1 | task 1183 | n_gen = 298, tg = 22.12 t/s, tg_3s = 22.40 t/s 2.28.875.872 I slot print_timing: id 3 | task 1322 | n_gen = 168, tg = 23.81 t/s, tg_3s = 22.39 t/s 2.30.283.670 I slot print_timing: id 2 | task 1215 | n_gen = 308, tg = 22.81 t/s, tg_3s = 24.81 t/s 2.31.247.673 I slot print_timing: id 0 | task 1450 | n_gen = 100, tg = 24.83 t/s, tg_3s = 25.08 t/s 2.31.651.106 I slot print_timing: id 1 | task 1183 | n_gen = 373, tg = 22.62 t/s, tg_3s = 24.85 t/s 2.31.893.186 I slot print_timing: id 3 | task 1322 | n_gen = 243, tg = 24.13 t/s, tg_3s = 24.86 t/s 2.33.299.271 I slot print_timing: id 2 | task 1215 | n_gen = 383, tg = 23.19 t/s, tg_3s = 24.87 t/s 2.34.264.570 I slot print_timing: id 0 | task 1450 | n_gen = 175, tg = 24.84 t/s, tg_3s = 24.86 t/s 2.34.584.947 I slot print_timing: id 2 | task 1215 | prompt eval time = 420.74 ms / 63 tokens ( 6.68 ms per token, 149.73 tokens per second) 2.34.584.954 I slot print_timing: id 2 | task 1215 | eval time = 17761.85 ms / 415 tokens ( 42.90 ms per token, 23.31 tokens per second) 2.34.584.955 I slot print_timing: id 2 | task 1215 | total time = 18182.59 ms / 478 tokens 2.34.584.956 I slot print_timing: id 2 | task 1215 | graphs reused = 1190 2.34.584.957 I slot print_timing: id 2 | task 1215 | graph reallocs = 0 / 0 (same size) / (changed size) 2.34.585.030 I slot release: id 2 | task 1215 | stop processing: n_tokens = 1448, truncated = 0 2.34.642.506 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.671 2.34.642.531 I slot launch_slot_: id 2 | task 1636 | processing task, is_child = 0 2.35.049.363 I slot print_timing: id 1 | task 1183 | n_gen = 448, tg = 22.53 t/s, tg_3s = 22.07 t/s 2.35.049.505 I slot print_timing: id 3 | task 1322 | n_gen = 312, tg = 23.58 t/s, tg_3s = 21.86 t/s 2.37.285.366 I slot print_timing: id 0 | task 1450 | n_gen = 239, tg = 23.74 t/s, tg_3s = 21.19 t/s 2.37.608.337 I slot print_timing: id 0 | task 1450 | prompt eval time = 370.90 ms / 54 tokens ( 6.87 ms per token, 145.59 tokens per second) 2.37.608.341 I slot print_timing: id 0 | task 1450 | eval time = 10347.83 ms / 247 tokens ( 42.06 ms per token, 23.77 tokens per second) 2.37.608.342 I slot print_timing: id 0 | task 1450 | total time = 10718.73 ms / 301 tokens 2.37.608.343 I slot print_timing: id 0 | task 1450 | graphs reused = 1249 2.37.608.344 I slot print_timing: id 0 | task 1450 | graph reallocs = 0 / 0 (same size) / (changed size) 2.37.608.411 I slot release: id 0 | task 1450 | stop processing: n_tokens = 1271, truncated = 0 2.37.651.115 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.764 2.37.651.138 I slot launch_slot_: id 0 | task 1701 | processing task, is_child = 0 2.38.087.642 I slot print_timing: id 1 | task 1183 | n_gen = 514, tg = 22.42 t/s, tg_3s = 21.72 t/s 2.38.087.812 I slot print_timing: id 3 | task 1322 | n_gen = 378, tg = 23.24 t/s, tg_3s = 21.72 t/s 2.39.458.909 I slot print_timing: id 2 | task 1636 | n_gen = 100, tg = 22.95 t/s, tg_3s = 23.18 t/s 2.41.106.399 I slot print_timing: id 1 | task 1183 | n_gen = 589, tg = 22.70 t/s, tg_3s = 24.84 t/s 2.41.106.748 I slot print_timing: id 3 | task 1322 | n_gen = 453, tg = 23.49 t/s, tg_3s = 24.84 t/s 2.42.031.396 I slot print_timing: id 0 | task 1701 | n_gen = 100, tg = 24.83 t/s, tg_3s = 25.09 t/s 2.42.469.430 I slot print_timing: id 2 | task 1636 | n_gen = 175, tg = 23.75 t/s, tg_3s = 24.91 t/s 2.44.116.857 I slot print_timing: id 1 | task 1183 | n_gen = 664, tg = 22.93 t/s, tg_3s = 24.91 t/s 2.44.117.211 I slot print_timing: id 3 | task 1322 | n_gen = 528, tg = 23.68 t/s, tg_3s = 24.91 t/s 2.44.680.892 I slot print_timing: id 2 | task 1636 | prompt eval time = 502.08 ms / 97 tokens ( 5.18 ms per token, 193.20 tokens per second) 2.44.680.897 I slot print_timing: id 2 | task 1636 | eval time = 9536.27 ms / 230 tokens ( 41.64 ms per token, 24.01 tokens per second) 2.44.680.897 I slot print_timing: id 2 | task 1636 | total time = 10038.35 ms / 327 tokens 2.44.680.898 I slot print_timing: id 2 | task 1636 | graphs reused = 1414 2.44.680.899 I slot print_timing: id 2 | task 1636 | graph reallocs = 0 / 0 (same size) / (changed size) 2.44.680.970 I slot release: id 2 | task 1636 | stop processing: n_tokens = 1296, truncated = 0 2.44.738.460 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.950 (> 0.100 thold), f_keep = 0.749 2.44.738.484 I slot launch_slot_: id 2 | task 1870 | processing task, is_child = 0 2.45.042.072 I slot print_timing: id 0 | task 1701 | n_gen = 168, tg = 23.87 t/s, tg_3s = 22.59 t/s 2.47.033.677 I slot print_timing: id 0 | task 1701 | prompt eval time = 393.89 ms / 66 tokens ( 5.97 ms per token, 167.56 tokens per second) 2.47.033.685 I slot print_timing: id 0 | task 1701 | eval time = 8988.64 ms / 216 tokens ( 41.81 ms per token, 23.92 tokens per second) 2.47.033.686 I slot print_timing: id 0 | task 1701 | total time = 9382.53 ms / 282 tokens 2.47.033.687 I slot print_timing: id 0 | task 1701 | graphs reused = 1460 2.47.033.687 I slot print_timing: id 0 | task 1701 | graph reallocs = 0 / 0 (same size) / (changed size) 2.47.033.759 I slot release: id 0 | task 1701 | stop processing: n_tokens = 1252, truncated = 0 2.47.076.187 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.776 2.47.076.214 I slot launch_slot_: id 0 | task 1921 | processing task, is_child = 0 2.47.422.951 I slot print_timing: id 1 | task 1183 | n_gen = 730, tg = 22.63 t/s, tg_3s = 19.96 t/s 2.47.423.191 I slot print_timing: id 3 | task 1322 | n_gen = 594, tg = 23.20 t/s, tg_3s = 19.96 t/s 2.49.488.188 I slot print_timing: id 2 | task 1870 | n_gen = 100, tg = 22.74 t/s, tg_3s = 22.97 t/s 2.50.456.956 I slot print_timing: id 1 | task 1183 | n_gen = 804, tg = 22.78 t/s, tg_3s = 24.39 t/s 2.50.457.318 I slot print_timing: id 3 | task 1322 | n_gen = 668, tg = 23.33 t/s, tg_3s = 24.39 t/s 2.51.506.187 I slot print_timing: id 0 | task 1921 | n_gen = 100, tg = 24.72 t/s, tg_3s = 24.97 t/s 2.51.869.402 I slot print_timing: id 2 | task 1870 | prompt eval time = 396.57 ms / 51 tokens ( 7.78 ms per token, 128.60 tokens per second) 2.51.869.406 I slot print_timing: id 2 | task 1870 | eval time = 6734.34 ms / 159 tokens ( 42.62 ms per token, 23.46 tokens per second) 2.51.869.407 I slot print_timing: id 2 | task 1870 | total time = 7130.91 ms / 210 tokens 2.51.869.408 I slot print_timing: id 2 | task 1870 | graphs reused = 1567 2.51.869.409 I slot print_timing: id 2 | task 1870 | graph reallocs = 0 / 0 (same size) / (changed size) 2.51.869.477 I slot release: id 2 | task 1870 | stop processing: n_tokens = 1180, truncated = 0 2.51.927.069 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.823 2.51.927.097 I slot launch_slot_: id 2 | task 2033 | processing task, is_child = 0 2.53.460.727 I slot print_timing: id 1 | task 1183 | n_gen = 869, tg = 22.69 t/s, tg_3s = 21.64 t/s 2.53.461.079 I slot print_timing: id 3 | task 1322 | n_gen = 733, tg = 23.17 t/s, tg_3s = 21.64 t/s 2.54.509.883 I slot print_timing: id 0 | task 1921 | n_gen = 165, tg = 23.40 t/s, tg_3s = 21.64 t/s 2.54.873.349 I slot print_timing: id 0 | task 1921 | prompt eval time = 425.65 ms / 70 tokens ( 6.08 ms per token, 164.45 tokens per second) 2.54.873.357 I slot print_timing: id 0 | task 1921 | eval time = 7371.47 ms / 174 tokens ( 42.61 ms per token, 23.47 tokens per second) 2.54.873.358 I slot print_timing: id 0 | task 1921 | total time = 7797.13 ms / 244 tokens 2.54.873.359 I slot print_timing: id 0 | task 1921 | graphs reused = 1628 2.54.873.359 I slot print_timing: id 0 | task 1921 | graph reallocs = 0 / 0 (same size) / (changed size) 2.54.873.434 I slot release: id 0 | task 1921 | stop processing: n_tokens = 1214, truncated = 0 2.54.915.815 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.800 2.54.915.842 I slot launch_slot_: id 0 | task 2099 | processing task, is_child = 0 2.56.466.637 I slot print_timing: id 1 | task 1183 | n_gen = 934, tg = 22.61 t/s, tg_3s = 21.62 t/s 2.56.466.947 I slot print_timing: id 3 | task 1322 | n_gen = 798, tg = 23.03 t/s, tg_3s = 21.62 t/s 2.56.749.821 I slot print_timing: id 2 | task 2033 | n_gen = 100, tg = 22.56 t/s, tg_3s = 22.78 t/s 2.59.387.628 I slot print_timing: id 0 | task 2099 | n_gen = 100, tg = 24.61 t/s, tg_3s = 24.86 t/s 2.59.468.755 I slot print_timing: id 1 | task 1183 | n_gen = 1008, tg = 22.75 t/s, tg_3s = 24.65 t/s 2.59.469.112 I slot print_timing: id 3 | task 1322 | n_gen = 872, tg = 23.16 t/s, tg_3s = 24.65 t/s 2.59.760.939 I slot print_timing: id 2 | task 2033 | n_gen = 174, tg = 23.38 t/s, tg_3s = 24.58 t/s 3.00.128.871 I slot print_timing: id 1 | task 1183 | prompt eval time = 441.96 ms / 69 tokens ( 6.41 ms per token, 156.12 tokens per second) 3.00.128.876 I slot print_timing: id 1 | task 1183 | eval time = 44923.42 ms / 1024 tokens ( 43.91 ms per token, 22.77 tokens per second) 3.00.128.878 I slot print_timing: id 1 | task 1183 | total time = 45365.38 ms / 1093 tokens 3.00.128.878 I slot print_timing: id 1 | task 1183 | graphs reused = 1743 3.00.128.879 I slot print_timing: id 1 | task 1183 | graph reallocs = 0 / 0 (same size) / (changed size) 3.00.128.961 I slot release: id 1 | task 1183 | stop processing: n_tokens = 2063, truncated = 0 3.00.186.055 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.945 (> 0.100 thold), f_keep = 0.471 3.00.214.778 I slot launch_slot_: id 1 | task 2220 | processing task, is_child = 0 3.01.083.517 I slot print_timing: id 2 | task 2033 | prompt eval time = 433.74 ms / 63 tokens ( 6.88 ms per token, 145.25 tokens per second) 3.01.083.522 I slot print_timing: id 2 | task 2033 | eval time = 8722.67 ms / 197 tokens ( 44.50 ms per token, 22.47 tokens per second) 3.01.083.523 I slot print_timing: id 2 | task 2033 | total time = 9156.41 ms / 260 tokens 3.01.083.524 I slot print_timing: id 2 | task 2033 | graphs reused = 1753 3.01.083.525 I slot print_timing: id 2 | task 2033 | graph reallocs = 0 / 0 (same size) / (changed size) 3.01.083.602 I slot release: id 2 | task 2033 | stop processing: n_tokens = 1230, truncated = 0 3.01.141.043 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.789 3.01.141.071 I slot launch_slot_: id 2 | task 2235 | processing task, is_child = 0 3.02.418.564 I slot print_timing: id 0 | task 2099 | n_gen = 156, tg = 21.98 t/s, tg_3s = 18.48 t/s 3.02.499.261 I slot print_timing: id 3 | task 1322 | n_gen = 928, tg = 22.81 t/s, tg_3s = 18.48 t/s 3.02.619.894 I slot print_timing: id 3 | task 1322 | prompt eval time = 505.99 ms / 114 tokens ( 4.44 ms per token, 225.30 tokens per second) 3.02.619.902 I slot print_timing: id 3 | task 1322 | eval time = 40757.59 ms / 931 tokens ( 43.83 ms per token, 22.82 tokens per second) 3.02.619.903 I slot print_timing: id 3 | task 1322 | total time = 41263.57 ms / 1045 tokens 3.02.619.903 I slot print_timing: id 3 | task 1322 | graphs reused = 1777 3.02.619.904 I slot print_timing: id 3 | task 1322 | graph reallocs = 0 / 0 (same size) / (changed size) 3.02.619.978 I slot release: id 3 | task 1322 | stop processing: n_tokens = 2015, truncated = 0 3.02.661.507 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.482 3.02.689.936 I slot launch_slot_: id 3 | task 2265 | processing task, is_child = 0 3.05.333.025 I slot print_timing: id 1 | task 2220 | n_gen = 100, tg = 21.07 t/s, tg_3s = 21.28 t/s 3.05.453.274 I slot print_timing: id 0 | task 2099 | n_gen = 223, tg = 22.01 t/s, tg_3s = 22.08 t/s 3.05.894.623 I slot print_timing: id 2 | task 2235 | n_gen = 100, tg = 22.85 t/s, tg_3s = 23.09 t/s 3.07.056.653 I slot print_timing: id 3 | task 2265 | n_gen = 100, tg = 24.87 t/s, tg_3s = 25.12 t/s 3.08.342.079 I slot print_timing: id 1 | task 2220 | n_gen = 175, tg = 22.57 t/s, tg_3s = 24.92 t/s 3.08.422.227 I slot print_timing: id 1 | task 2220 | prompt eval time = 418.86 ms / 57 tokens ( 7.35 ms per token, 136.08 tokens per second) 3.08.422.232 I slot print_timing: id 1 | task 2220 | eval time = 7788.57 ms / 177 tokens ( 44.25 ms per token, 22.60 tokens per second) 3.08.422.233 I slot print_timing: id 1 | task 2220 | total time = 8207.44 ms / 234 tokens 3.08.422.234 I slot print_timing: id 1 | task 2220 | graphs reused = 1908 3.08.422.235 I slot print_timing: id 1 | task 2220 | graph reallocs = 0 / 0 (same size) / (changed size) 3.08.422.303 I slot release: id 1 | task 2220 | stop processing: n_tokens = 1203, truncated = 0 3.08.478.852 I slot print_timing: id 0 | task 2099 | n_gen = 298, tg = 22.65 t/s, tg_3s = 24.79 t/s 3.08.479.199 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.909 (> 0.100 thold), f_keep = 0.808 3.08.479.225 I slot launch_slot_: id 1 | task 2402 | processing task, is_child = 0 3.08.989.891 I slot print_timing: id 2 | task 2235 | n_gen = 166, tg = 22.22 t/s, tg_3s = 21.32 t/s 3.09.794.538 I slot print_timing: id 2 | task 2235 | prompt eval time = 421.80 ms / 63 tokens ( 6.70 ms per token, 149.36 tokens per second) 3.09.794.545 I slot print_timing: id 2 | task 2235 | eval time = 8231.65 ms / 186 tokens ( 44.50 ms per token, 22.47 tokens per second) 3.09.794.546 I slot print_timing: id 2 | task 2235 | total time = 8653.45 ms / 249 tokens 3.09.794.547 I slot print_timing: id 2 | task 2235 | graphs reused = 1927 3.09.794.548 I slot print_timing: id 2 | task 2235 | graph reallocs = 0 / 0 (same size) / (changed size) 3.09.794.621 I slot release: id 2 | task 2235 | stop processing: n_tokens = 1219, truncated = 0 3.09.851.918 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.797 3.09.851.947 I slot launch_slot_: id 2 | task 2426 | processing task, is_child = 0 3.10.256.849 I slot print_timing: id 3 | task 2265 | n_gen = 159, tg = 22.00 t/s, tg_3s = 18.44 t/s 3.10.681.359 I slot print_timing: id 3 | task 2265 | prompt eval time = 386.24 ms / 56 tokens ( 6.90 ms per token, 144.99 tokens per second) 3.10.681.367 I slot print_timing: id 3 | task 2265 | eval time = 7605.17 ms / 168 tokens ( 45.54 ms per token, 21.96 tokens per second) 3.10.681.368 I slot print_timing: id 3 | task 2265 | total time = 7991.41 ms / 224 tokens 3.10.681.369 I slot print_timing: id 3 | task 2265 | graphs reused = 1934 3.10.681.370 I slot print_timing: id 3 | task 2265 | graph reallocs = 0 / 0 (same size) / (changed size) 3.10.681.438 I slot release: id 3 | task 2265 | stop processing: n_tokens = 1193, truncated = 0 3.10.723.248 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.895 (> 0.100 thold), f_keep = 0.814 3.10.723.275 I slot launch_slot_: id 3 | task 2438 | processing task, is_child = 0 3.11.514.850 I slot print_timing: id 0 | task 2099 | n_gen = 341, tg = 21.05 t/s, tg_3s = 14.16 t/s 3.13.847.307 I slot print_timing: id 1 | task 2402 | n_gen = 100, tg = 20.38 t/s, tg_3s = 20.59 t/s 3.14.536.414 I slot print_timing: id 0 | task 2099 | n_gen = 416, tg = 21.65 t/s, tg_3s = 24.82 t/s 3.14.776.765 I slot print_timing: id 2 | task 2426 | n_gen = 100, tg = 22.36 t/s, tg_3s = 22.59 t/s 3.15.217.945 I slot print_timing: id 3 | task 2438 | n_gen = 100, tg = 24.85 t/s, tg_3s = 25.10 t/s 3.16.870.758 I slot print_timing: id 1 | task 2402 | n_gen = 175, tg = 22.08 t/s, tg_3s = 24.81 t/s 3.17.554.465 I slot print_timing: id 0 | task 2099 | n_gen = 491, tg = 22.08 t/s, tg_3s = 24.85 t/s 3.17.796.126 I slot print_timing: id 2 | task 2426 | n_gen = 175, tg = 23.37 t/s, tg_3s = 24.84 t/s 3.18.238.669 I slot print_timing: id 3 | task 2438 | n_gen = 175, tg = 24.84 t/s, tg_3s = 24.83 t/s 3.19.890.682 I slot print_timing: id 1 | task 2402 | n_gen = 250, tg = 22.84 t/s, tg_3s = 24.84 t/s 3.20.576.149 I slot print_timing: id 0 | task 2099 | n_gen = 566, tg = 22.41 t/s, tg_3s = 24.82 t/s 3.20.818.745 I slot print_timing: id 2 | task 2426 | n_gen = 250, tg = 23.78 t/s, tg_3s = 24.81 t/s 3.21.263.250 I slot print_timing: id 3 | task 2438 | n_gen = 250, tg = 24.83 t/s, tg_3s = 24.80 t/s 3.22.923.033 I slot print_timing: id 1 | task 2402 | n_gen = 325, tg = 23.25 t/s, tg_3s = 24.73 t/s 3.23.610.226 I slot print_timing: id 0 | task 2099 | n_gen = 641, tg = 22.66 t/s, tg_3s = 24.72 t/s 3.23.853.393 I slot print_timing: id 2 | task 2426 | n_gen = 325, tg = 23.99 t/s, tg_3s = 24.71 t/s 3.24.298.679 I slot print_timing: id 3 | task 2438 | n_gen = 325, tg = 24.80 t/s, tg_3s = 24.71 t/s 3.24.946.250 I slot print_timing: id 3 | task 2438 | prompt eval time = 511.06 ms / 114 tokens ( 4.48 ms per token, 223.06 tokens per second) 3.24.946.257 I slot print_timing: id 3 | task 2438 | eval time = 13711.90 ms / 341 tokens ( 40.33 ms per token, 24.80 tokens per second) 3.24.946.258 I slot print_timing: id 3 | task 2438 | total time = 14222.97 ms / 455 tokens 3.24.946.259 I slot print_timing: id 3 | task 2438 | graphs reused = 2271 3.24.946.260 I slot print_timing: id 3 | task 2438 | graph reallocs = 0 / 0 (same size) / (changed size) 3.24.946.338 I slot release: id 3 | task 2438 | stop processing: n_tokens = 1425, truncated = 0 3.24.988.098 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.681 3.24.988.121 I slot launch_slot_: id 3 | task 2782 | processing task, is_child = 0 3.25.620.799 I slot print_timing: id 0 | task 2099 | prompt eval time = 449.41 ms / 98 tokens ( 4.59 ms per token, 218.06 tokens per second) 3.25.620.804 I slot print_timing: id 0 | task 2099 | eval time = 30255.54 ms / 683 tokens ( 44.36 ms per token, 22.54 tokens per second) 3.25.620.805 I slot print_timing: id 0 | task 2099 | total time = 30704.95 ms / 781 tokens 3.25.620.805 I slot print_timing: id 0 | task 2099 | graphs reused = 2276 3.25.620.806 I slot print_timing: id 0 | task 2099 | graph reallocs = 0 / 0 (same size) / (changed size) 3.25.620.851 I slot release: id 0 | task 2099 | stop processing: n_tokens = 1751, truncated = 0 3.25.659.468 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.945 (> 0.100 thold), f_keep = 0.555 3.25.659.488 I slot launch_slot_: id 0 | task 2792 | processing task, is_child = 0 3.25.953.733 I slot print_timing: id 1 | task 2402 | n_gen = 386, tg = 22.70 t/s, tg_3s = 20.13 t/s 3.26.884.246 I slot print_timing: id 2 | task 2426 | n_gen = 385, tg = 23.22 t/s, tg_3s = 19.80 t/s 3.28.979.512 I slot print_timing: id 1 | task 2402 | n_gen = 460, tg = 22.96 t/s, tg_3s = 24.46 t/s 3.29.669.086 I slot print_timing: id 3 | task 2782 | n_gen = 100, tg = 23.07 t/s, tg_3s = 23.30 t/s 3.29.910.402 I slot print_timing: id 2 | task 2426 | n_gen = 460, tg = 23.47 t/s, tg_3s = 24.78 t/s 3.30.030.653 I slot print_timing: id 0 | task 2792 | n_gen = 100, tg = 24.76 t/s, tg_3s = 25.01 t/s 3.30.917.571 I slot print_timing: id 0 | task 2792 | prompt eval time = 372.56 ms / 58 tokens ( 6.42 ms per token, 155.68 tokens per second) 3.30.917.582 I slot print_timing: id 0 | task 2792 | eval time = 4885.51 ms / 122 tokens ( 40.38 ms per token, 24.77 tokens per second) 3.30.917.583 I slot print_timing: id 0 | task 2792 | total time = 5258.07 ms / 180 tokens 3.30.917.584 I slot print_timing: id 0 | task 2792 | graphs reused = 2395 3.30.917.585 I slot print_timing: id 0 | task 2792 | graph reallocs = 0 / 0 (same size) / (changed size) 3.30.917.653 I slot release: id 0 | task 2792 | stop processing: n_tokens = 1149, truncated = 0 3.30.960.050 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.941 (> 0.100 thold), f_keep = 0.845 3.30.960.077 I slot launch_slot_: id 0 | task 2917 | processing task, is_child = 0 3.32.000.834 I slot print_timing: id 1 | task 2402 | n_gen = 527, tg = 22.86 t/s, tg_3s = 22.18 t/s 3.32.686.675 I slot print_timing: id 3 | task 2782 | n_gen = 167, tg = 22.71 t/s, tg_3s = 22.20 t/s 3.32.928.554 I slot print_timing: id 2 | task 2426 | n_gen = 527, tg = 23.30 t/s, tg_3s = 22.20 t/s 3.33.535.061 I slot print_timing: id 3 | task 2782 | prompt eval time = 389.38 ms / 63 tokens ( 6.18 ms per token, 161.80 tokens per second) 3.33.535.069 I slot print_timing: id 3 | task 2782 | eval time = 8157.55 ms / 188 tokens ( 43.62 ms per token, 22.92 tokens per second) 3.33.535.070 I slot print_timing: id 3 | task 2782 | total time = 8546.93 ms / 251 tokens 3.33.535.071 I slot print_timing: id 3 | task 2782 | graphs reused = 2449 3.33.535.071 I slot print_timing: id 3 | task 2782 | graph reallocs = 0 / 0 (same size) / (changed size) 3.33.535.141 I slot release: id 3 | task 2782 | stop processing: n_tokens = 1221, truncated = 0 3.33.577.173 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.795 3.33.577.195 I slot launch_slot_: id 3 | task 2975 | processing task, is_child = 0 3.35.024.469 I slot print_timing: id 1 | task 2402 | n_gen = 593, tg = 22.74 t/s, tg_3s = 21.83 t/s 3.35.709.409 I slot print_timing: id 0 | task 2917 | n_gen = 100, tg = 22.68 t/s, tg_3s = 22.91 t/s 3.35.951.784 I slot print_timing: id 2 | task 2426 | n_gen = 593, tg = 23.12 t/s, tg_3s = 21.83 t/s 3.38.007.310 I slot print_timing: id 3 | task 2975 | n_gen = 100, tg = 24.79 t/s, tg_3s = 25.04 t/s 3.38.047.311 I slot print_timing: id 1 | task 2402 | n_gen = 668, tg = 22.95 t/s, tg_3s = 24.81 t/s 3.38.732.136 I slot print_timing: id 0 | task 2917 | n_gen = 175, tg = 23.55 t/s, tg_3s = 24.81 t/s 3.38.974.472 I slot print_timing: id 2 | task 2426 | n_gen = 668, tg = 23.30 t/s, tg_3s = 24.81 t/s 3.39.095.004 I slot print_timing: id 0 | task 2917 | prompt eval time = 384.61 ms / 61 tokens ( 6.31 ms per token, 158.60 tokens per second) 3.39.095.009 I slot print_timing: id 0 | task 2917 | eval time = 7750.31 ms / 184 tokens ( 42.35 ms per token, 23.61 tokens per second) 3.39.095.010 I slot print_timing: id 0 | task 2917 | total time = 8134.92 ms / 245 tokens 3.39.095.011 I slot print_timing: id 0 | task 2917 | graphs reused = 2574 3.39.095.012 I slot print_timing: id 0 | task 2917 | graph reallocs = 0 / 0 (same size) / (changed size) 3.39.095.084 I slot release: id 0 | task 2917 | stop processing: n_tokens = 1215, truncated = 0 3.39.137.239 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.799 3.39.137.264 I slot launch_slot_: id 0 | task 3105 | processing task, is_child = 0 3.41.042.117 I slot print_timing: id 3 | task 2975 | n_gen = 166, tg = 23.47 t/s, tg_3s = 21.75 t/s 3.41.082.208 I slot print_timing: id 1 | task 2402 | n_gen = 734, tg = 22.84 t/s, tg_3s = 21.75 t/s 3.42.012.596 I slot print_timing: id 2 | task 2426 | n_gen = 734, tg = 23.15 t/s, tg_3s = 21.72 t/s 3.42.940.953 I slot print_timing: id 3 | task 2975 | prompt eval time = 435.91 ms / 73 tokens ( 5.97 ms per token, 167.46 tokens per second) 3.42.940.961 I slot print_timing: id 3 | task 2975 | eval time = 8927.83 ms / 213 tokens ( 42.11 ms per token, 23.75 tokens per second) 3.42.940.962 I slot print_timing: id 3 | task 2975 | total time = 9363.75 ms / 286 tokens 3.42.940.963 I slot print_timing: id 3 | task 2975 | graphs reused = 2656 3.42.940.964 I slot print_timing: id 3 | task 2975 | graph reallocs = 0 / 0 (same size) / (changed size) 3.42.941.036 I slot release: id 3 | task 2975 | stop processing: n_tokens = 1256, truncated = 0 3.42.983.366 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.773 3.42.983.390 I slot launch_slot_: id 3 | task 3192 | processing task, is_child = 0 3.43.956.470 I slot print_timing: id 0 | task 3105 | n_gen = 100, tg = 22.57 t/s, tg_3s = 22.80 t/s 3.44.118.220 I slot print_timing: id 1 | task 2402 | n_gen = 800, tg = 22.75 t/s, tg_3s = 21.74 t/s 3.45.046.738 I slot print_timing: id 2 | task 2426 | n_gen = 800, tg = 23.03 t/s, tg_3s = 21.75 t/s 3.46.541.277 I slot print_timing: id 0 | task 3105 | prompt eval time = 433.70 ms / 79 tokens ( 5.49 ms per token, 182.15 tokens per second) 3.46.541.281 I slot print_timing: id 0 | task 3105 | eval time = 6970.30 ms / 164 tokens ( 42.76 ms per token, 23.38 tokens per second) 3.46.541.282 I slot print_timing: id 0 | task 3105 | total time = 7404.00 ms / 243 tokens 3.46.541.283 I slot print_timing: id 0 | task 3105 | graphs reused = 2732 3.46.541.284 I slot print_timing: id 0 | task 3105 | graph reallocs = 0 / 0 (same size) / (changed size) 3.46.541.358 I slot release: id 0 | task 3105 | stop processing: n_tokens = 1213, truncated = 0 3.46.583.817 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.940 (> 0.100 thold), f_keep = 0.800 3.46.583.840 I slot launch_slot_: id 0 | task 3273 | processing task, is_child = 0 3.47.134.594 I slot print_timing: id 1 | task 2402 | n_gen = 867, tg = 22.70 t/s, tg_3s = 22.21 t/s 3.47.749.551 I slot print_timing: id 3 | task 3192 | n_gen = 100, tg = 22.90 t/s, tg_3s = 23.14 t/s 3.48.072.826 I slot print_timing: id 2 | task 2426 | n_gen = 867, tg = 22.96 t/s, tg_3s = 22.14 t/s 3.50.138.377 I slot print_timing: id 1 | task 2402 | n_gen = 941, tg = 22.84 t/s, tg_3s = 24.64 t/s 3.50.787.141 I slot print_timing: id 3 | task 3192 | n_gen = 175, tg = 23.64 t/s, tg_3s = 24.69 t/s 3.50.989.157 I slot print_timing: id 0 | task 3273 | n_gen = 100, tg = 24.64 t/s, tg_3s = 24.89 t/s 3.51.110.747 I slot print_timing: id 2 | task 2426 | n_gen = 942, tg = 23.09 t/s, tg_3s = 24.69 t/s 3.53.157.359 I slot print_timing: id 1 | task 2402 | n_gen = 1015, tg = 22.96 t/s, tg_3s = 24.51 t/s 3.53.526.202 I slot print_timing: id 1 | task 2402 | prompt eval time = 510.58 ms / 97 tokens ( 5.26 ms per token, 189.98 tokens per second) 3.53.526.209 I slot print_timing: id 1 | task 2402 | eval time = 44536.39 ms / 1024 tokens ( 43.54 ms per token, 22.97 tokens per second) 3.53.526.210 I slot print_timing: id 1 | task 2402 | total time = 45046.97 ms / 1121 tokens 3.53.526.211 I slot print_timing: id 1 | task 2402 | graphs reused = 2892 3.53.526.211 I slot print_timing: id 1 | task 2402 | graph reallocs = 0 / 0 (same size) / (changed size) 3.53.526.286 I slot release: id 1 | task 2402 | stop processing: n_tokens = 2092, truncated = 0 3.53.584.060 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.924 (> 0.100 thold), f_keep = 0.464 3.53.622.964 I slot launch_slot_: id 1 | task 3438 | processing task, is_child = 0 3.54.011.899 I slot print_timing: id 0 | task 3273 | n_gen = 164, tg = 23.15 t/s, tg_3s = 21.17 t/s 3.54.012.158 I slot print_timing: id 3 | task 3192 | n_gen = 244, tg = 22.96 t/s, tg_3s = 21.40 t/s 3.54.110.868 I slot print_timing: id 2 | task 2426 | n_gen = 1004, tg = 22.92 t/s, tg_3s = 20.67 t/s 3.54.936.077 I slot print_timing: id 2 | task 2426 | prompt eval time = 497.49 ms / 100 tokens ( 4.97 ms per token, 201.01 tokens per second) 3.54.936.082 I slot print_timing: id 2 | task 2426 | eval time = 44586.64 ms / 1024 tokens ( 43.58 ms per token, 22.94 tokens per second) 3.54.936.083 I slot print_timing: id 2 | task 2426 | total time = 45084.12 ms / 1124 tokens 3.54.936.084 I slot print_timing: id 2 | task 2426 | graphs reused = 2911 3.54.936.084 I slot print_timing: id 2 | task 2426 | graph reallocs = 0 / 0 (same size) / (changed size) 3.54.936.157 I slot release: id 2 | task 2426 | stop processing: n_tokens = 2094, truncated = 0 3.54.993.573 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.896 (> 0.100 thold), f_keep = 0.464 3.55.022.657 I slot launch_slot_: id 2 | task 3462 | processing task, is_child = 0 3.56.078.661 I slot print_timing: id 3 | task 3192 | prompt eval time = 443.71 ms / 90 tokens ( 4.93 ms per token, 202.83 tokens per second) 3.56.078.666 I slot print_timing: id 3 | task 3192 | eval time = 12651.55 ms / 281 tokens ( 45.18 ms per token, 22.13 tokens per second) 3.56.078.667 I slot print_timing: id 3 | task 3192 | total time = 13095.26 ms / 371 tokens 3.56.078.668 I slot print_timing: id 3 | task 3192 | graphs reused = 2923 3.56.078.669 I slot print_timing: id 3 | task 3192 | graph reallocs = 0 / 0 (same size) / (changed size) 3.56.078.741 I slot release: id 3 | task 3192 | stop processing: n_tokens = 1341, truncated = 0 3.56.120.407 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.724 3.56.120.437 I slot launch_slot_: id 3 | task 3479 | processing task, is_child = 0 3.57.033.358 I slot print_timing: id 0 | task 3273 | n_gen = 215, tg = 21.27 t/s, tg_3s = 16.88 t/s 3.59.002.051 I slot print_timing: id 1 | task 3438 | n_gen = 100, tg = 20.24 t/s, tg_3s = 20.44 t/s 3.59.923.978 I slot print_timing: id 2 | task 3462 | n_gen = 100, tg = 22.62 t/s, tg_3s = 22.85 t/s 4.00.044.884 I slot print_timing: id 0 | task 3273 | n_gen = 290, tg = 22.11 t/s, tg_3s = 24.90 t/s 4.00.165.397 I slot print_timing: id 0 | task 3273 | prompt eval time = 387.80 ms / 62 tokens ( 6.25 ms per token, 159.88 tokens per second) 4.00.165.402 I slot print_timing: id 0 | task 3273 | eval time = 13193.75 ms / 293 tokens ( 45.18 ms per token, 22.13 tokens per second) 4.00.165.403 I slot print_timing: id 0 | task 3273 | total time = 13581.55 ms / 355 tokens 4.00.165.403 I slot print_timing: id 0 | task 3273 | graphs reused = 3010 4.00.165.404 I slot print_timing: id 0 | task 3273 | graph reallocs = 0 / 0 (same size) / (changed size) 4.00.165.479 I slot release: id 0 | task 3273 | stop processing: n_tokens = 1325, truncated = 0 4.00.207.331 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.733 4.00.207.358 I slot launch_slot_: id 0 | task 3572 | processing task, is_child = 0 4.00.935.058 I slot print_timing: id 3 | task 3479 | n_gen = 100, tg = 22.76 t/s, tg_3s = 22.99 t/s 4.02.014.117 I slot print_timing: id 1 | task 3438 | n_gen = 166, tg = 20.88 t/s, tg_3s = 21.91 t/s 4.02.940.321 I slot print_timing: id 2 | task 3462 | n_gen = 166, tg = 22.32 t/s, tg_3s = 21.88 t/s 4.03.541.349 I slot print_timing: id 1 | task 3438 | prompt eval time = 487.80 ms / 80 tokens ( 6.10 ms per token, 164.00 tokens per second) 4.03.541.360 I slot print_timing: id 1 | task 3438 | eval time = 9430.57 ms / 204 tokens ( 46.46 ms per token, 21.53 tokens per second) 4.03.541.361 I slot print_timing: id 1 | task 3438 | total time = 9918.37 ms / 284 tokens 4.03.541.361 I slot print_timing: id 1 | task 3438 | graphs reused = 3081 4.03.541.362 I slot print_timing: id 1 | task 3438 | graph reallocs = 0 / 0 (same size) / (changed size) 4.03.541.435 I slot release: id 1 | task 3438 | stop processing: n_tokens = 1254, truncated = 0 4.03.597.961 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.774 4.03.597.986 I slot launch_slot_: id 1 | task 3648 | processing task, is_child = 0 4.04.005.904 I slot print_timing: id 3 | task 3479 | n_gen = 167, tg = 22.37 t/s, tg_3s = 21.82 t/s 4.05.073.142 I slot print_timing: id 0 | task 3572 | n_gen = 100, tg = 22.36 t/s, tg_3s = 22.58 t/s 4.05.953.703 I slot print_timing: id 2 | task 3462 | n_gen = 230, tg = 22.01 t/s, tg_3s = 21.24 t/s 4.07.033.049 I slot print_timing: id 3 | task 3479 | n_gen = 241, tg = 22.97 t/s, tg_3s = 24.45 t/s 4.08.074.178 I slot print_timing: id 0 | task 3572 | n_gen = 175, tg = 23.42 t/s, tg_3s = 24.99 t/s 4.08.074.355 I slot print_timing: id 1 | task 3648 | n_gen = 100, tg = 24.94 t/s, tg_3s = 25.19 t/s 4.08.957.099 I slot print_timing: id 2 | task 3462 | n_gen = 305, tg = 22.67 t/s, tg_3s = 24.97 t/s 4.10.042.262 I slot print_timing: id 3 | task 3479 | n_gen = 316, tg = 23.41 t/s, tg_3s = 24.92 t/s 4.10.766.254 I slot print_timing: id 0 | task 3572 | prompt eval time = 437.76 ms / 83 tokens ( 5.27 ms per token, 189.60 tokens per second) 4.10.766.259 I slot print_timing: id 0 | task 3572 | eval time = 10121.12 ms / 242 tokens ( 42.00 ms per token, 23.81 tokens per second) 4.10.766.260 I slot print_timing: id 0 | task 3572 | total time = 10558.89 ms / 325 tokens 4.10.766.261 I slot print_timing: id 0 | task 3572 | graphs reused = 3245 4.10.766.262 I slot print_timing: id 0 | task 3572 | graph reallocs = 0 / 0 (same size) / (changed size) 4.10.766.333 I slot release: id 0 | task 3572 | stop processing: n_tokens = 1295, truncated = 0 4.10.808.588 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.902 (> 0.100 thold), f_keep = 0.750 4.10.808.618 I slot launch_slot_: id 0 | task 3818 | processing task, is_child = 0 4.11.227.435 I slot print_timing: id 1 | task 3648 | n_gen = 169, tg = 23.59 t/s, tg_3s = 21.88 t/s 4.11.993.227 I slot print_timing: id 2 | task 3462 | n_gen = 370, tg = 22.44 t/s, tg_3s = 21.41 t/s 4.13.079.578 I slot print_timing: id 3 | task 3479 | n_gen = 381, tg = 23.04 t/s, tg_3s = 21.40 t/s 4.14.254.833 I slot print_timing: id 1 | task 3648 | n_gen = 243, tg = 23.84 t/s, tg_3s = 24.44 t/s 4.15.020.938 I slot print_timing: id 2 | task 3462 | n_gen = 445, tg = 22.80 t/s, tg_3s = 24.77 t/s 4.15.301.969 I slot print_timing: id 0 | task 3818 | n_gen = 100, tg = 24.78 t/s, tg_3s = 25.03 t/s 4.16.114.672 I slot print_timing: id 3 | task 3479 | n_gen = 456, tg = 23.30 t/s, tg_3s = 24.71 t/s 4.17.282.695 I slot print_timing: id 1 | task 3648 | n_gen = 318, tg = 24.06 t/s, tg_3s = 24.77 t/s 4.18.051.834 I slot print_timing: id 2 | task 3462 | n_gen = 520, tg = 23.06 t/s, tg_3s = 24.75 t/s 4.18.333.420 I slot print_timing: id 0 | task 3818 | n_gen = 175, tg = 24.76 t/s, tg_3s = 24.74 t/s 4.19.142.410 I slot print_timing: id 3 | task 3479 | n_gen = 531, tg = 23.50 t/s, tg_3s = 24.77 t/s 4.20.313.811 I slot print_timing: id 1 | task 3648 | n_gen = 393, tg = 24.18 t/s, tg_3s = 24.74 t/s 4.21.085.188 I slot print_timing: id 2 | task 3462 | n_gen = 595, tg = 23.26 t/s, tg_3s = 24.73 t/s 4.21.368.200 I slot print_timing: id 0 | task 3818 | n_gen = 250, tg = 24.75 t/s, tg_3s = 24.71 t/s 4.22.179.469 I slot print_timing: id 3 | task 3479 | n_gen = 606, tg = 23.64 t/s, tg_3s = 24.69 t/s 4.23.314.916 I slot print_timing: id 1 | task 3648 | n_gen = 467, tg = 24.26 t/s, tg_3s = 24.66 t/s 4.24.125.164 I slot print_timing: id 2 | task 3462 | n_gen = 670, tg = 23.41 t/s, tg_3s = 24.67 t/s 4.24.408.153 I slot print_timing: id 0 | task 3818 | n_gen = 325, tg = 24.73 t/s, tg_3s = 24.67 t/s 4.25.177.871 I slot print_timing: id 0 | task 3818 | prompt eval time = 497.65 ms / 106 tokens ( 4.69 ms per token, 213.00 tokens per second) 4.25.177.880 I slot print_timing: id 0 | task 3818 | eval time = 13871.59 ms / 344 tokens ( 40.44 ms per token, 24.73 tokens per second) 4.25.177.881 I slot print_timing: id 0 | task 3818 | total time = 14369.24 ms / 450 tokens 4.25.177.882 I slot print_timing: id 0 | task 3818 | graphs reused = 3586 4.25.177.882 I slot print_timing: id 0 | task 3818 | graph reallocs = 0 / 0 (same size) / (changed size) 4.25.177.963 I slot release: id 0 | task 3818 | stop processing: n_tokens = 1420, truncated = 0 4.25.220.940 I slot print_timing: id 3 | task 3479 | n_gen = 681, tg = 23.75 t/s, tg_3s = 24.66 t/s 4.25.220.947 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.684 4.25.220.973 I slot launch_slot_: id 0 | task 4165 | processing task, is_child = 0 4.26.336.665 I slot print_timing: id 1 | task 3648 | n_gen = 534, tg = 23.97 t/s, tg_3s = 22.17 t/s 4.27.146.938 I slot print_timing: id 2 | task 3462 | n_gen = 737, tg = 23.29 t/s, tg_3s = 22.17 t/s 4.28.243.187 I slot print_timing: id 3 | task 3479 | n_gen = 748, tg = 23.60 t/s, tg_3s = 22.17 t/s 4.29.337.677 I slot print_timing: id 1 | task 3648 | n_gen = 608, tg = 24.06 t/s, tg_3s = 24.66 t/s 4.29.621.183 I slot print_timing: id 0 | task 4165 | n_gen = 100, tg = 24.62 t/s, tg_3s = 24.87 t/s 4.30.148.107 I slot print_timing: id 2 | task 3462 | n_gen = 811, tg = 23.41 t/s, tg_3s = 24.66 t/s 4.31.244.517 I slot print_timing: id 3 | task 3479 | n_gen = 822, tg = 23.69 t/s, tg_3s = 24.66 t/s 4.32.340.004 I slot print_timing: id 1 | task 3648 | n_gen = 682, tg = 24.12 t/s, tg_3s = 24.65 t/s 4.32.624.162 I slot print_timing: id 0 | task 4165 | n_gen = 174, tg = 24.63 t/s, tg_3s = 24.64 t/s 4.33.152.518 I slot print_timing: id 2 | task 3462 | n_gen = 885, tg = 23.51 t/s, tg_3s = 24.63 t/s 4.34.248.932 I slot print_timing: id 3 | task 3479 | n_gen = 896, tg = 23.76 t/s, tg_3s = 24.63 t/s 4.34.940.526 I slot print_timing: id 0 | task 4165 | prompt eval time = 379.44 ms / 64 tokens ( 5.93 ms per token, 168.67 tokens per second) 4.34.940.534 I slot print_timing: id 0 | task 4165 | eval time = 9340.10 ms / 231 tokens ( 40.61 ms per token, 24.63 tokens per second) 4.34.940.535 I slot print_timing: id 0 | task 4165 | total time = 9719.54 ms / 295 tokens 4.34.940.536 I slot print_timing: id 0 | task 4165 | graphs reused = 3815 4.34.940.537 I slot print_timing: id 0 | task 4165 | graph reallocs = 0 / 0 (same size) / (changed size) 4.34.940.613 I slot release: id 0 | task 4165 | stop processing: n_tokens = 1265, truncated = 0 4.34.983.277 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.768 4.34.983.303 I slot launch_slot_: id 0 | task 4399 | processing task, is_child = 0 4.35.401.830 I slot print_timing: id 1 | task 3648 | n_gen = 749, tg = 23.90 t/s, tg_3s = 21.88 t/s 4.36.177.483 I slot print_timing: id 2 | task 3462 | n_gen = 951, tg = 23.38 t/s, tg_3s = 21.82 t/s 4.37.286.068 I slot print_timing: id 3 | task 3479 | n_gen = 962, tg = 23.61 t/s, tg_3s = 21.73 t/s 4.38.435.463 I slot print_timing: id 1 | task 3648 | n_gen = 823, tg = 23.94 t/s, tg_3s = 24.39 t/s 4.39.175.815 I slot print_timing: id 2 | task 3462 | prompt eval time = 525.57 ms / 114 tokens ( 4.61 ms per token, 216.91 tokens per second) 4.39.175.824 I slot print_timing: id 2 | task 3462 | eval time = 43627.57 ms / 1024 tokens ( 42.65 ms per token, 23.45 tokens per second) 4.39.175.825 I slot print_timing: id 2 | task 3462 | total time = 44153.14 ms / 1138 tokens 4.39.175.825 I slot print_timing: id 2 | task 3462 | graphs reused = 3906 4.39.175.826 I slot print_timing: id 2 | task 3462 | graph reallocs = 0 / 0 (same size) / (changed size) 4.39.175.905 I slot release: id 2 | task 3462 | stop processing: n_tokens = 2107, truncated = 0 4.39.234.001 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.461 4.39.267.907 I slot launch_slot_: id 2 | task 4495 | processing task, is_child = 0 4.39.869.175 I slot print_timing: id 0 | task 4399 | n_gen = 100, tg = 22.16 t/s, tg_3s = 22.38 t/s 4.40.239.245 I slot print_timing: id 3 | task 3479 | prompt eval time = 465.81 ms / 99 tokens ( 4.71 ms per token, 212.53 tokens per second) 4.40.239.252 I slot print_timing: id 3 | task 3479 | eval time = 43652.99 ms / 1024 tokens ( 42.67 ms per token, 23.43 tokens per second) 4.40.239.254 I slot print_timing: id 3 | task 3479 | total time = 44118.80 ms / 1123 tokens 4.40.239.254 I slot print_timing: id 3 | task 3479 | graphs reused = 3918 4.40.239.255 I slot print_timing: id 3 | task 3479 | graph reallocs = 0 / 0 (same size) / (changed size) 4.40.239.327 I slot release: id 3 | task 3479 | stop processing: n_tokens = 2093, truncated = 0 4.40.280.877 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.464 4.40.311.425 I slot launch_slot_: id 3 | task 4512 | processing task, is_child = 0 4.41.394.392 I slot print_timing: id 0 | task 4399 | prompt eval time = 418.44 ms / 70 tokens ( 5.98 ms per token, 167.29 tokens per second) 4.41.394.399 I slot print_timing: id 0 | task 4399 | eval time = 5992.64 ms / 128 tokens ( 47.19 ms per token, 21.19 tokens per second) 4.41.394.400 I slot print_timing: id 0 | task 4399 | total time = 6411.08 ms / 198 tokens 4.41.394.401 I slot print_timing: id 0 | task 4399 | graphs reused = 3933 4.41.394.402 I slot print_timing: id 0 | task 4399 | graph reallocs = 0 / 0 (same size) / (changed size) 4.41.394.470 I slot release: id 0 | task 4399 | stop processing: n_tokens = 1168, truncated = 0 4.41.436.724 I slot print_timing: id 1 | task 3648 | n_gen = 877, tg = 23.47 t/s, tg_3s = 17.99 t/s 4.41.437.036 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.831 4.41.437.062 I slot launch_slot_: id 0 | task 4532 | processing task, is_child = 0 4.44.439.622 I slot print_timing: id 1 | task 3648 | n_gen = 943, tg = 23.35 t/s, tg_3s = 21.98 t/s 4.44.439.802 I slot print_timing: id 2 | task 4495 | n_gen = 100, tg = 20.90 t/s, tg_3s = 21.11 t/s 4.45.083.859 I slot print_timing: id 3 | task 4512 | n_gen = 100, tg = 22.80 t/s, tg_3s = 23.03 t/s 4.45.849.438 I slot print_timing: id 0 | task 4532 | n_gen = 100, tg = 24.81 t/s, tg_3s = 25.06 t/s 4.46.011.278 I slot print_timing: id 3 | task 4512 | prompt eval time = 431.04 ms / 70 tokens ( 6.16 ms per token, 162.40 tokens per second) 4.46.011.284 I slot print_timing: id 3 | task 4512 | eval time = 5268.80 ms / 123 tokens ( 43.19 ms per token, 23.16 tokens per second) 4.46.011.286 I slot print_timing: id 3 | task 4512 | total time = 5699.84 ms / 193 tokens 4.46.011.286 I slot print_timing: id 3 | task 4512 | graphs reused = 4036 4.46.011.287 I slot print_timing: id 3 | task 4512 | graph reallocs = 0 / 0 (same size) / (changed size) 4.46.011.364 I slot release: id 3 | task 4512 | stop processing: n_tokens = 1162, truncated = 0 4.46.053.127 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.836 4.46.053.150 I slot launch_slot_: id 3 | task 4639 | processing task, is_child = 0 4.47.446.669 I slot print_timing: id 1 | task 3648 | n_gen = 1008, tg = 23.23 t/s, tg_3s = 21.62 t/s 4.47.446.841 I slot print_timing: id 2 | task 4495 | n_gen = 165, tg = 21.18 t/s, tg_3s = 21.62 t/s 4.48.098.748 I slot print_timing: id 1 | task 3648 | prompt eval time = 506.71 ms / 94 tokens ( 5.39 ms per token, 185.51 tokens per second) 4.48.098.752 I slot print_timing: id 1 | task 3648 | eval time = 43994.04 ms / 1024 tokens ( 43.00 ms per token, 23.25 tokens per second) 4.48.098.753 I slot print_timing: id 1 | task 3648 | total time = 44500.75 ms / 1118 tokens 4.48.098.754 I slot print_timing: id 1 | task 3648 | graphs reused = 4074 4.48.098.755 I slot print_timing: id 1 | task 3648 | graph reallocs = 0 / 0 (same size) / (changed size) 4.48.098.828 I slot release: id 1 | task 3648 | stop processing: n_tokens = 2088, truncated = 0 4.48.155.993 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.465 4.48.187.307 I slot launch_slot_: id 1 | task 4682 | processing task, is_child = 0 4.48.857.555 I slot print_timing: id 0 | task 4532 | n_gen = 153, tg = 21.72 t/s, tg_3s = 17.62 t/s 4.50.463.584 I slot print_timing: id 2 | task 4495 | n_gen = 228, tg = 21.10 t/s, tg_3s = 20.88 t/s 4.50.984.580 I slot print_timing: id 3 | task 4639 | n_gen = 100, tg = 22.11 t/s, tg_3s = 22.33 t/s 4.51.189.737 I slot print_timing: id 2 | task 4495 | prompt eval time = 435.42 ms / 69 tokens ( 6.31 ms per token, 158.47 tokens per second) 4.51.189.741 I slot print_timing: id 2 | task 4495 | eval time = 11486.39 ms / 246 tokens ( 46.88 ms per token, 21.33 tokens per second) 4.51.189.742 I slot print_timing: id 2 | task 4495 | total time = 11921.81 ms / 315 tokens 4.51.189.743 I slot print_timing: id 2 | task 4495 | graphs reused = 4133 4.51.189.744 I slot print_timing: id 2 | task 4495 | graph reallocs = 0 / 0 (same size) / (changed size) 4.51.189.810 I slot release: id 2 | task 4495 | stop processing: n_tokens = 1283, truncated = 0 4.51.246.510 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.757 4.51.246.539 I slot launch_slot_: id 2 | task 4748 | processing task, is_child = 0 4.51.875.587 I slot print_timing: id 0 | task 4532 | n_gen = 218, tg = 21.66 t/s, tg_3s = 21.54 t/s 4.53.092.232 I slot print_timing: id 1 | task 4682 | n_gen = 100, tg = 22.46 t/s, tg_3s = 22.69 t/s 4.54.014.380 I slot print_timing: id 3 | task 4639 | n_gen = 165, tg = 21.84 t/s, tg_3s = 21.45 t/s 4.54.896.957 I slot print_timing: id 0 | task 4532 | n_gen = 293, tg = 22.40 t/s, tg_3s = 24.82 t/s 4.55.217.804 I slot print_timing: id 0 | task 4532 | prompt eval time = 422.11 ms / 74 tokens ( 5.70 ms per token, 175.31 tokens per second) 4.55.217.812 I slot print_timing: id 0 | task 4532 | eval time = 13358.62 ms / 301 tokens ( 44.53 ms per token, 22.46 tokens per second) 4.55.217.813 I slot print_timing: id 0 | task 4532 | total time = 13780.73 ms / 375 tokens 4.55.217.813 I slot print_timing: id 0 | task 4532 | graphs reused = 4218 4.55.217.814 I slot print_timing: id 0 | task 4532 | graph reallocs = 0 / 0 (same size) / (changed size) 4.55.217.883 I slot release: id 0 | task 4532 | stop processing: n_tokens = 1345, truncated = 0 4.55.259.824 I slot print_timing: id 3 | task 4639 | prompt eval time = 453.55 ms / 91 tokens ( 4.98 ms per token, 200.64 tokens per second) 4.55.259.828 I slot print_timing: id 3 | task 4639 | eval time = 8753.11 ms / 196 tokens ( 44.89 ms per token, 22.28 tokens per second) 4.55.259.829 I slot print_timing: id 3 | task 4639 | total time = 9206.66 ms / 287 tokens 4.55.259.830 I slot print_timing: id 3 | task 4639 | graphs reused = 4218 4.55.259.830 I slot print_timing: id 3 | task 4639 | graph reallocs = 0 / 0 (same size) / (changed size) 4.55.259.896 I slot release: id 3 | task 4639 | stop processing: n_tokens = 1257, truncated = 0 4.55.259.907 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.945 (> 0.100 thold), f_keep = 0.722 4.55.259.928 I slot launch_slot_: id 0 | task 4839 | processing task, is_child = 0 4.55.287.504 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.772 4.55.287.529 I slot launch_slot_: id 3 | task 4840 | processing task, is_child = 0 4.56.127.200 I slot print_timing: id 1 | task 4682 | n_gen = 159, tg = 21.23 t/s, tg_3s = 19.44 t/s 4.56.372.081 I slot print_timing: id 2 | task 4748 | n_gen = 100, tg = 21.25 t/s, tg_3s = 21.46 t/s 4.59.144.147 I slot print_timing: id 1 | task 4682 | n_gen = 234, tg = 22.28 t/s, tg_3s = 24.86 t/s 4.59.384.051 I slot print_timing: id 2 | task 4748 | n_gen = 175, tg = 22.68 t/s, tg_3s = 24.90 t/s 4.59.985.445 I slot print_timing: id 0 | task 4839 | n_gen = 100, tg = 24.87 t/s, tg_3s = 25.12 t/s 4.59.985.951 I slot print_timing: id 3 | task 4840 | n_gen = 100, tg = 24.87 t/s, tg_3s = 25.12 t/s 5.02.150.543 I slot print_timing: id 1 | task 4682 | n_gen = 309, tg = 22.87 t/s, tg_3s = 24.95 t/s 5.02.391.269 I slot print_timing: id 2 | task 4748 | n_gen = 250, tg = 23.32 t/s, tg_3s = 24.94 t/s 5.02.993.581 I slot print_timing: id 0 | task 4839 | n_gen = 175, tg = 24.90 t/s, tg_3s = 24.93 t/s 5.02.994.103 I slot print_timing: id 3 | task 4840 | n_gen = 175, tg = 24.90 t/s, tg_3s = 24.93 t/s 5.05.163.420 I slot print_timing: id 1 | task 4682 | n_gen = 384, tg = 23.24 t/s, tg_3s = 24.89 t/s 5.05.404.090 I slot print_timing: id 2 | task 4748 | n_gen = 325, tg = 23.66 t/s, tg_3s = 24.89 t/s 5.06.009.349 I slot print_timing: id 0 | task 4839 | n_gen = 250, tg = 24.89 t/s, tg_3s = 24.87 t/s 5.06.009.866 I slot print_timing: id 3 | task 4840 | n_gen = 250, tg = 24.89 t/s, tg_3s = 24.87 t/s 5.06.171.055 I slot print_timing: id 2 | task 4748 | prompt eval time = 466.38 ms / 75 tokens ( 6.22 ms per token, 160.81 tokens per second) 5.06.171.060 I slot print_timing: id 2 | task 4748 | eval time = 14458.13 ms / 344 tokens ( 42.15 ms per token, 23.72 tokens per second) 5.06.171.061 I slot print_timing: id 2 | task 4748 | total time = 14924.51 ms / 419 tokens 5.06.171.062 I slot print_timing: id 2 | task 4748 | graphs reused = 4468 5.06.171.062 I slot print_timing: id 2 | task 4748 | graph reallocs = 0 / 0 (same size) / (changed size) 5.06.171.140 I slot release: id 2 | task 4748 | stop processing: n_tokens = 1389, truncated = 0 5.06.228.718 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.699 5.06.228.742 I slot launch_slot_: id 2 | task 5097 | processing task, is_child = 0 5.07.350.147 I slot print_timing: id 0 | task 4839 | prompt eval time = 717.80 ms / 56 tokens ( 12.82 ms per token, 78.02 tokens per second) 5.07.350.151 I slot print_timing: id 0 | task 4839 | eval time = 11344.80 ms / 274 tokens ( 41.56 ms per token, 24.06 tokens per second) 5.07.350.152 I slot print_timing: id 0 | task 4839 | total time = 12062.60 ms / 330 tokens 5.07.350.152 I slot print_timing: id 0 | task 4839 | graphs reused = 4483 5.07.350.153 I slot print_timing: id 0 | task 4839 | graph reallocs = 0 / 0 (same size) / (changed size) 5.07.350.217 I slot release: id 0 | task 4839 | stop processing: n_tokens = 1300, truncated = 0 5.07.391.608 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.943 (> 0.100 thold), f_keep = 0.747 5.07.391.629 I slot launch_slot_: id 0 | task 5118 | processing task, is_child = 0 5.08.167.985 I slot print_timing: id 1 | task 4682 | n_gen = 442, tg = 22.64 t/s, tg_3s = 19.30 t/s 5.09.021.161 I slot print_timing: id 3 | task 4840 | n_gen = 308, tg = 23.59 t/s, tg_3s = 19.26 t/s 5.10.878.426 I slot print_timing: id 1 | task 4682 | prompt eval time = 497.97 ms / 91 tokens ( 5.47 ms per token, 182.74 tokens per second) 5.10.878.434 I slot print_timing: id 1 | task 4682 | eval time = 22193.13 ms / 509 tokens ( 43.69 ms per token, 22.89 tokens per second) 5.10.878.435 I slot print_timing: id 1 | task 4682 | total time = 22691.10 ms / 600 tokens 5.10.878.436 I slot print_timing: id 1 | task 4682 | graphs reused = 4559 5.10.878.437 I slot print_timing: id 1 | task 4682 | graph reallocs = 0 / 0 (same size) / (changed size) 5.10.878.514 I slot release: id 1 | task 4682 | stop processing: n_tokens = 1569, truncated = 0 5.10.935.693 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.619 5.10.935.720 I slot launch_slot_: id 1 | task 5199 | processing task, is_child = 0 5.11.332.942 I slot print_timing: id 2 | task 5097 | n_gen = 100, tg = 21.15 t/s, tg_3s = 21.37 t/s 5.12.046.091 I slot print_timing: id 3 | task 4840 | n_gen = 372, tg = 23.13 t/s, tg_3s = 21.16 t/s 5.12.206.615 I slot print_timing: id 0 | task 5118 | n_gen = 100, tg = 22.29 t/s, tg_3s = 22.52 t/s 5.14.371.593 I slot print_timing: id 2 | task 5097 | n_gen = 174, tg = 22.41 t/s, tg_3s = 24.35 t/s 5.15.060.709 I slot print_timing: id 3 | task 4840 | n_gen = 447, tg = 23.41 t/s, tg_3s = 24.88 t/s 5.15.220.562 I slot print_timing: id 0 | task 5118 | n_gen = 175, tg = 23.34 t/s, tg_3s = 24.88 t/s 5.15.421.274 I slot print_timing: id 1 | task 5199 | n_gen = 100, tg = 24.81 t/s, tg_3s = 25.06 t/s 5.15.743.279 I slot print_timing: id 2 | task 5097 | prompt eval time = 424.08 ms / 65 tokens ( 6.52 ms per token, 153.27 tokens per second) 5.15.743.284 I slot print_timing: id 2 | task 5097 | eval time = 9090.45 ms / 208 tokens ( 43.92 ms per token, 22.77 tokens per second) 5.15.743.285 I slot print_timing: id 2 | task 5097 | total time = 9514.53 ms / 273 tokens 5.15.743.286 I slot print_timing: id 2 | task 5097 | graphs reused = 4664 5.15.743.286 I slot print_timing: id 2 | task 5097 | graph reallocs = 0 / 0 (same size) / (changed size) 5.15.743.361 I slot release: id 2 | task 5097 | stop processing: n_tokens = 1243, truncated = 0 5.15.801.154 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.781 5.15.801.183 I slot launch_slot_: id 2 | task 5310 | processing task, is_child = 0 5.18.080.988 I slot print_timing: id 3 | task 4840 | n_gen = 512, tg = 23.15 t/s, tg_3s = 21.52 t/s 5.18.241.869 I slot print_timing: id 0 | task 5118 | n_gen = 240, tg = 22.81 t/s, tg_3s = 21.51 t/s 5.18.442.336 I slot print_timing: id 1 | task 5199 | n_gen = 165, tg = 23.39 t/s, tg_3s = 21.52 t/s 5.19.007.479 I slot print_timing: id 0 | task 5118 | prompt eval time = 373.95 ms / 59 tokens ( 6.34 ms per token, 157.78 tokens per second) 5.19.007.486 I slot print_timing: id 0 | task 5118 | eval time = 11241.89 ms / 259 tokens ( 43.57 ms per token, 22.95 tokens per second) 5.19.007.487 I slot print_timing: id 0 | task 5118 | total time = 11615.84 ms / 318 tokens 5.19.007.488 I slot print_timing: id 0 | task 5118 | graphs reused = 4730 5.19.007.489 I slot print_timing: id 0 | task 5118 | graph reallocs = 0 / 0 (same size) / (changed size) 5.19.007.567 I slot release: id 0 | task 5118 | stop processing: n_tokens = 1288, truncated = 0 5.19.049.909 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.941 (> 0.100 thold), f_keep = 0.754 5.19.049.939 I slot launch_slot_: id 0 | task 5382 | processing task, is_child = 0 5.20.575.502 I slot print_timing: id 2 | task 5310 | n_gen = 100, tg = 22.94 t/s, tg_3s = 23.18 t/s 5.20.696.082 I slot print_timing: id 1 | task 5199 | prompt eval time = 495.62 ms / 86 tokens ( 5.76 ms per token, 173.52 tokens per second) 5.20.696.086 I slot print_timing: id 1 | task 5199 | eval time = 9264.74 ms / 213 tokens ( 43.70 ms per token, 22.88 tokens per second) 5.20.696.087 I slot print_timing: id 1 | task 5199 | total time = 9760.35 ms / 299 tokens 5.20.696.088 I slot print_timing: id 1 | task 5199 | graphs reused = 4761 5.20.696.089 I slot print_timing: id 1 | task 5199 | graph reallocs = 0 / 0 (same size) / (changed size) 5.20.696.164 I slot release: id 1 | task 5199 | stop processing: n_tokens = 1269, truncated = 0 5.20.753.237 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.899 (> 0.100 thold), f_keep = 0.765 5.20.753.269 I slot launch_slot_: id 1 | task 5417 | processing task, is_child = 0 5.21.193.545 I slot print_timing: id 3 | task 4840 | n_gen = 571, tg = 22.63 t/s, tg_3s = 18.96 t/s 5.23.071.638 I slot print_timing: id 2 | task 5310 | prompt eval time = 459.33 ms / 70 tokens ( 6.56 ms per token, 152.40 tokens per second) 5.23.071.643 I slot print_timing: id 2 | task 5310 | eval time = 6811.11 ms / 150 tokens ( 45.71 ms per token, 21.88 tokens per second) 5.23.071.645 I slot print_timing: id 2 | task 5310 | total time = 7270.44 ms / 220 tokens 5.23.071.646 I slot print_timing: id 2 | task 5310 | graphs reused = 4804 5.23.071.647 I slot print_timing: id 2 | task 5310 | graph reallocs = 0 / 0 (same size) / (changed size) 5.23.071.718 I slot release: id 2 | task 5310 | stop processing: n_tokens = 1190, truncated = 0 5.23.129.036 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.816 5.23.129.062 I slot launch_slot_: id 2 | task 5465 | processing task, is_child = 0 5.24.204.795 I slot print_timing: id 3 | task 4840 | n_gen = 634, tg = 22.45 t/s, tg_3s = 20.92 t/s 5.24.324.468 I slot print_timing: id 0 | task 5382 | n_gen = 100, tg = 20.26 t/s, tg_3s = 20.46 t/s 5.25.692.508 I slot print_timing: id 1 | task 5417 | n_gen = 100, tg = 22.50 t/s, tg_3s = 22.72 t/s 5.27.223.111 I slot print_timing: id 3 | task 4840 | n_gen = 709, tg = 22.68 t/s, tg_3s = 24.85 t/s 5.27.342.288 I slot print_timing: id 0 | task 5382 | n_gen = 175, tg = 22.01 t/s, tg_3s = 24.85 t/s 5.27.583.662 I slot print_timing: id 2 | task 5465 | n_gen = 100, tg = 24.84 t/s, tg_3s = 25.09 t/s 5.28.147.463 I slot print_timing: id 0 | task 5382 | prompt eval time = 387.61 ms / 61 tokens ( 6.35 ms per token, 157.37 tokens per second) 5.28.147.471 I slot print_timing: id 0 | task 5382 | eval time = 8709.90 ms / 195 tokens ( 44.90 ms per token, 22.27 tokens per second) 5.28.147.472 I slot print_timing: id 0 | task 5382 | total time = 9097.51 ms / 256 tokens 5.28.147.472 I slot print_timing: id 0 | task 5382 | graphs reused = 4916 5.28.147.473 I slot print_timing: id 0 | task 5382 | graph reallocs = 0 / 0 (same size) / (changed size) 5.28.147.547 I slot release: id 0 | task 5382 | stop processing: n_tokens = 1226, truncated = 0 5.28.189.951 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.792 5.28.189.975 I slot launch_slot_: id 0 | task 5582 | processing task, is_child = 0 5.28.701.604 I slot print_timing: id 1 | task 5417 | n_gen = 164, tg = 22.00 t/s, tg_3s = 21.27 t/s 5.30.245.386 I slot print_timing: id 3 | task 4840 | n_gen = 773, tg = 22.55 t/s, tg_3s = 21.18 t/s 5.30.607.726 I slot print_timing: id 2 | task 5465 | n_gen = 164, tg = 23.25 t/s, tg_3s = 21.16 t/s 5.31.736.462 I slot print_timing: id 1 | task 5417 | n_gen = 239, tg = 22.79 t/s, tg_3s = 24.71 t/s 5.32.705.169 I slot print_timing: id 0 | task 5582 | n_gen = 100, tg = 24.73 t/s, tg_3s = 24.98 t/s 5.33.271.943 I slot print_timing: id 3 | task 4840 | n_gen = 848, tg = 22.73 t/s, tg_3s = 24.78 t/s 5.33.634.695 I slot print_timing: id 2 | task 5465 | n_gen = 239, tg = 23.71 t/s, tg_3s = 24.78 t/s 5.34.767.299 I slot print_timing: id 1 | task 5417 | n_gen = 314, tg = 23.23 t/s, tg_3s = 24.75 t/s 5.35.737.108 I slot print_timing: id 0 | task 5582 | n_gen = 175, tg = 24.73 t/s, tg_3s = 24.74 t/s 5.36.305.253 I slot print_timing: id 3 | task 4840 | n_gen = 923, tg = 22.88 t/s, tg_3s = 24.73 t/s 5.36.628.594 I slot print_timing: id 1 | task 5417 | prompt eval time = 538.45 ms / 109 tokens ( 4.94 ms per token, 202.43 tokens per second) 5.36.628.602 I slot print_timing: id 1 | task 5417 | eval time = 15336.86 ms / 360 tokens ( 42.72 ms per token, 23.41 tokens per second) 5.36.628.603 I slot print_timing: id 1 | task 5417 | total time = 15875.31 ms / 469 tokens 5.36.628.604 I slot print_timing: id 1 | task 5417 | graphs reused = 5111 5.36.628.605 I slot print_timing: id 1 | task 5417 | graph reallocs = 0 / 0 (same size) / (changed size) 5.36.628.687 I slot release: id 1 | task 5417 | stop processing: n_tokens = 1439, truncated = 0 5.36.685.766 I slot print_timing: id 2 | task 5465 | n_gen = 314, tg = 23.92 t/s, tg_3s = 24.58 t/s 5.36.685.913 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.675 5.36.685.936 I slot launch_slot_: id 1 | task 5782 | processing task, is_child = 0 5.37.625.012 I slot print_timing: id 2 | task 5465 | prompt eval time = 469.08 ms / 78 tokens ( 6.01 ms per token, 166.28 tokens per second) 5.37.625.016 I slot print_timing: id 2 | task 5465 | eval time = 14026.86 ms / 327 tokens ( 43.03 ms per token, 23.24 tokens per second) 5.37.625.017 I slot print_timing: id 2 | task 5465 | total time = 14495.94 ms / 405 tokens 5.37.625.018 I slot print_timing: id 2 | task 5465 | graphs reused = 5121 5.37.625.019 I slot print_timing: id 2 | task 5465 | graph reallocs = 0 / 0 (same size) / (changed size) 5.37.625.099 I slot release: id 2 | task 5465 | stop processing: n_tokens = 1375, truncated = 0 5.37.683.220 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.706 5.37.683.251 I slot launch_slot_: id 2 | task 5797 | processing task, is_child = 0 5.38.739.343 I slot print_timing: id 0 | task 5582 | n_gen = 228, tg = 22.61 t/s, tg_3s = 17.65 t/s 5.39.345.108 I slot print_timing: id 3 | task 4840 | n_gen = 977, tg = 22.52 t/s, tg_3s = 17.76 t/s 5.41.255.555 I slot print_timing: id 3 | task 4840 | prompt eval time = 716.52 ms / 75 tokens ( 9.55 ms per token, 104.67 tokens per second) 5.41.255.560 I slot print_timing: id 3 | task 4840 | eval time = 45249.94 ms / 1024 tokens ( 44.23 ms per token, 22.61 tokens per second) 5.41.255.562 I slot print_timing: id 3 | task 4840 | total time = 45966.47 ms / 1099 tokens 5.41.255.562 I slot print_timing: id 3 | task 4840 | graphs reused = 5195 5.41.255.563 I slot print_timing: id 3 | task 4840 | graph reallocs = 0 / 0 (same size) / (changed size) 5.41.255.634 I slot release: id 3 | task 4840 | stop processing: n_tokens = 2069, truncated = 0 5.41.297.385 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.952 (> 0.100 thold), f_keep = 0.469 5.41.327.416 I slot launch_slot_: id 3 | task 5877 | processing task, is_child = 0 5.41.770.586 I slot print_timing: id 0 | task 5582 | n_gen = 295, tg = 22.50 t/s, tg_3s = 22.10 t/s 5.41.929.862 I slot print_timing: id 1 | task 5782 | n_gen = 100, tg = 20.82 t/s, tg_3s = 21.04 t/s 5.42.498.767 I slot print_timing: id 2 | task 5797 | n_gen = 100, tg = 22.90 t/s, tg_3s = 23.13 t/s 5.44.782.609 I slot print_timing: id 0 | task 5582 | n_gen = 370, tg = 22.95 t/s, tg_3s = 24.90 t/s 5.44.943.738 I slot print_timing: id 1 | task 5782 | n_gen = 175, tg = 22.40 t/s, tg_3s = 24.88 t/s 5.44.983.832 I slot print_timing: id 1 | task 5782 | prompt eval time = 489.95 ms / 88 tokens ( 5.57 ms per token, 179.61 tokens per second) 5.44.983.839 I slot print_timing: id 1 | task 5782 | eval time = 7807.93 ms / 176 tokens ( 44.62 ms per token, 22.41 tokens per second) 5.44.983.840 I slot print_timing: id 1 | task 5782 | total time = 8297.89 ms / 264 tokens 5.44.983.841 I slot print_timing: id 1 | task 5782 | graphs reused = 5276 5.44.983.842 I slot print_timing: id 1 | task 5782 | graph reallocs = 0 / 0 (same size) / (changed size) 5.44.983.914 I slot release: id 1 | task 5782 | stop processing: n_tokens = 1234, truncated = 0 5.45.040.881 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.787 5.45.040.908 I slot launch_slot_: id 1 | task 5963 | processing task, is_child = 0 5.45.502.393 I slot print_timing: id 2 | task 5797 | n_gen = 165, tg = 22.38 t/s, tg_3s = 21.64 t/s 5.46.082.471 I slot print_timing: id 3 | task 5877 | n_gen = 100, tg = 22.53 t/s, tg_3s = 22.76 t/s 5.46.202.912 I slot print_timing: id 3 | task 5877 | prompt eval time = 360.98 ms / 50 tokens ( 7.22 ms per token, 138.51 tokens per second) 5.46.202.917 I slot print_timing: id 3 | task 5877 | eval time = 4514.49 ms / 103 tokens ( 44.26 ms per token, 22.59 tokens per second) 5.46.202.918 I slot print_timing: id 3 | task 5877 | total time = 4875.48 ms / 153 tokens 5.46.202.919 I slot print_timing: id 3 | task 5877 | graphs reused = 5291 5.46.202.919 I slot print_timing: id 3 | task 5877 | graph reallocs = 0 / 0 (same size) / (changed size) 5.46.202.989 I slot release: id 3 | task 5877 | stop processing: n_tokens = 1122, truncated = 0 5.46.244.736 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.916 (> 0.100 thold), f_keep = 0.865 5.46.244.762 I slot launch_slot_: id 3 | task 5984 | processing task, is_child = 0 5.47.789.836 I slot print_timing: id 0 | task 5582 | n_gen = 425, tg = 22.21 t/s, tg_3s = 18.29 t/s 5.48.517.575 I slot print_timing: id 2 | task 5797 | n_gen = 230, tg = 22.14 t/s, tg_3s = 21.56 t/s 5.49.884.484 I slot print_timing: id 1 | task 5963 | n_gen = 100, tg = 22.59 t/s, tg_3s = 22.82 t/s 5.50.690.075 I slot print_timing: id 3 | task 5984 | n_gen = 100, tg = 24.81 t/s, tg_3s = 25.06 t/s 5.50.810.314 I slot print_timing: id 0 | task 5582 | n_gen = 500, tg = 22.57 t/s, tg_3s = 24.83 t/s 5.51.535.102 I slot print_timing: id 2 | task 5797 | n_gen = 305, tg = 22.75 t/s, tg_3s = 24.85 t/s 5.51.655.816 I slot print_timing: id 1 | task 5963 | prompt eval time = 461.37 ms / 73 tokens ( 6.32 ms per token, 158.23 tokens per second) 5.51.655.821 I slot print_timing: id 1 | task 5963 | eval time = 6153.53 ms / 144 tokens ( 43.03 ms per token, 23.24 tokens per second) 5.51.655.822 I slot print_timing: id 1 | task 5963 | total time = 6614.90 ms / 217 tokens 5.51.655.823 I slot print_timing: id 1 | task 5963 | graphs reused = 5412 5.51.655.824 I slot print_timing: id 1 | task 5963 | graph reallocs = 0 / 0 (same size) / (changed size) 5.51.655.897 I slot release: id 1 | task 5963 | stop processing: n_tokens = 1187, truncated = 0 5.51.713.113 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.818 5.51.713.141 I slot launch_slot_: id 1 | task 6111 | processing task, is_child = 0 5.53.723.806 I slot print_timing: id 3 | task 5984 | n_gen = 166, tg = 23.49 t/s, tg_3s = 21.76 t/s 5.53.844.249 I slot print_timing: id 0 | task 5582 | n_gen = 566, tg = 22.47 t/s, tg_3s = 21.75 t/s 5.54.571.738 I slot print_timing: id 2 | task 5797 | n_gen = 371, tg = 22.57 t/s, tg_3s = 21.73 t/s 5.56.146.680 I slot print_timing: id 1 | task 6111 | n_gen = 100, tg = 24.76 t/s, tg_3s = 25.01 t/s 5.56.752.945 I slot print_timing: id 3 | task 5984 | n_gen = 241, tg = 23.87 t/s, tg_3s = 24.76 t/s 5.56.873.293 I slot print_timing: id 0 | task 5582 | n_gen = 641, tg = 22.72 t/s, tg_3s = 24.76 t/s 5.57.598.813 I slot print_timing: id 2 | task 5797 | n_gen = 446, tg = 22.91 t/s, tg_3s = 24.78 t/s 5.59.180.781 I slot print_timing: id 1 | task 6111 | n_gen = 175, tg = 24.74 t/s, tg_3s = 24.72 t/s 5.59.787.319 I slot print_timing: id 3 | task 5984 | n_gen = 316, tg = 24.07 t/s, tg_3s = 24.72 t/s 5.59.908.332 I slot print_timing: id 0 | task 5582 | n_gen = 716, tg = 22.91 t/s, tg_3s = 24.71 t/s 6.00.636.895 I slot print_timing: id 2 | task 5797 | n_gen = 521, tg = 23.15 t/s, tg_3s = 24.69 t/s 6.02.216.978 I slot print_timing: id 1 | task 6111 | n_gen = 250, tg = 24.73 t/s, tg_3s = 24.70 t/s 6.02.825.491 I slot print_timing: id 3 | task 5984 | n_gen = 391, tg = 24.18 t/s, tg_3s = 24.69 t/s 6.02.946.706 I slot print_timing: id 0 | task 5582 | n_gen = 791, tg = 23.07 t/s, tg_3s = 24.68 t/s 6.03.677.503 I slot print_timing: id 2 | task 5797 | n_gen = 596, tg = 23.33 t/s, tg_3s = 24.67 t/s 6.05.222.276 I slot print_timing: id 1 | task 6111 | n_gen = 324, tg = 24.71 t/s, tg_3s = 24.62 t/s 6.05.832.750 I slot print_timing: id 3 | task 5984 | n_gen = 465, tg = 24.25 t/s, tg_3s = 24.61 t/s 6.05.954.352 I slot print_timing: id 0 | task 5582 | n_gen = 865, tg = 23.19 t/s, tg_3s = 24.60 t/s 6.06.686.115 I slot print_timing: id 2 | task 5797 | n_gen = 670, tg = 23.46 t/s, tg_3s = 24.60 t/s 6.07.621.000 I slot print_timing: id 1 | task 6111 | prompt eval time = 434.91 ms / 69 tokens ( 6.30 ms per token, 158.65 tokens per second) 6.07.621.008 I slot print_timing: id 1 | task 6111 | eval time = 15472.94 ms / 383 tokens ( 40.51 ms per token, 24.69 tokens per second) 6.07.621.008 I slot print_timing: id 1 | task 6111 | total time = 15907.85 ms / 452 tokens 6.07.621.009 I slot print_timing: id 1 | task 6111 | graphs reused = 5792 6.07.621.010 I slot print_timing: id 1 | task 6111 | graph reallocs = 0 / 0 (same size) / (changed size) 6.07.621.083 I slot release: id 1 | task 6111 | stop processing: n_tokens = 1422, truncated = 0 6.07.678.390 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.683 6.07.678.416 I slot launch_slot_: id 1 | task 6497 | processing task, is_child = 0 6.08.464.883 I slot print_timing: id 3 | task 5984 | prompt eval time = 454.22 ms / 89 tokens ( 5.10 ms per token, 195.94 tokens per second) 6.08.464.890 I slot print_timing: id 3 | task 5984 | eval time = 21765.89 ms / 519 tokens ( 42.02 ms per token, 23.80 tokens per second) 6.08.464.891 I slot print_timing: id 3 | task 5984 | total time = 22220.11 ms / 608 tokens 6.08.464.892 I slot print_timing: id 3 | task 5984 | graphs reused = 5798 6.08.464.893 I slot print_timing: id 3 | task 5984 | graph reallocs = 0 / 0 (same size) / (changed size) 6.08.464.971 I slot release: id 3 | task 5984 | stop processing: n_tokens = 1578, truncated = 0 6.08.507.487 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.615 6.08.507.510 I slot launch_slot_: id 3 | task 6508 | processing task, is_child = 0 6.08.965.316 I slot print_timing: id 0 | task 5582 | n_gen = 919, tg = 22.80 t/s, tg_3s = 17.93 t/s 6.09.696.586 I slot print_timing: id 2 | task 5797 | n_gen = 724, tg = 22.94 t/s, tg_3s = 17.94 t/s 6.11.986.393 I slot print_timing: id 0 | task 5582 | n_gen = 993, tg = 22.92 t/s, tg_3s = 24.49 t/s 6.12.599.642 I slot print_timing: id 1 | task 6497 | n_gen = 100, tg = 22.38 t/s, tg_3s = 22.61 t/s 6.12.722.772 I slot print_timing: id 2 | task 5797 | n_gen = 798, tg = 23.07 t/s, tg_3s = 24.45 t/s 6.13.010.431 I slot print_timing: id 3 | task 6508 | n_gen = 100, tg = 24.48 t/s, tg_3s = 24.72 t/s 6.13.255.664 I slot print_timing: id 0 | task 5582 | prompt eval time = 511.54 ms / 128 tokens ( 4.00 ms per token, 250.22 tokens per second) 6.13.255.668 I slot print_timing: id 0 | task 5582 | eval time = 44554.14 ms / 1024 tokens ( 43.55 ms per token, 22.96 tokens per second) 6.13.255.669 I slot print_timing: id 0 | task 5582 | total time = 45065.68 ms / 1152 tokens 6.13.255.670 I slot print_timing: id 0 | task 5582 | graphs reused = 5901 6.13.255.670 I slot print_timing: id 0 | task 5582 | graph reallocs = 0 / 0 (same size) / (changed size) 6.13.255.744 I slot release: id 0 | task 5582 | stop processing: n_tokens = 2122, truncated = 0 6.13.298.077 I slot print_timing: id 1 | task 6497 | prompt eval time = 498.35 ms / 90 tokens ( 5.54 ms per token, 180.60 tokens per second) 6.13.298.093 I slot print_timing: id 1 | task 6497 | eval time = 5121.31 ms / 117 tokens ( 44.15 ms per token, 22.65 tokens per second) 6.13.298.097 I slot print_timing: id 1 | task 6497 | total time = 5619.65 ms / 207 tokens 6.13.298.097 I slot print_timing: id 1 | task 6497 | graphs reused = 5901 6.13.298.098 I slot print_timing: id 1 | task 6497 | graph reallocs = 0 / 0 (same size) / (changed size) 6.13.298.164 I slot release: id 1 | task 6497 | stop processing: n_tokens = 1177, truncated = 0 6.13.298.463 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.458 6.13.328.743 I slot launch_slot_: id 0 | task 6617 | processing task, is_child = 0 6.13.352.928 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.825 6.13.352.947 I slot launch_slot_: id 1 | task 6618 | processing task, is_child = 0 6.15.735.037 I slot print_timing: id 2 | task 5797 | n_gen = 858, tg = 22.82 t/s, tg_3s = 19.92 t/s 6.16.016.783 I slot print_timing: id 3 | task 6508 | n_gen = 160, tg = 22.55 t/s, tg_3s = 19.96 t/s 6.17.947.265 I slot print_timing: id 0 | task 6617 | n_gen = 100, tg = 24.82 t/s, tg_3s = 25.07 t/s 6.17.947.443 I slot print_timing: id 1 | task 6618 | n_gen = 100, tg = 24.82 t/s, tg_3s = 25.07 t/s 6.18.753.439 I slot print_timing: id 2 | task 5797 | n_gen = 933, tg = 22.97 t/s, tg_3s = 24.85 t/s 6.19.035.439 I slot print_timing: id 3 | task 6508 | n_gen = 235, tg = 23.24 t/s, tg_3s = 24.85 t/s 6.20.974.249 I slot print_timing: id 0 | task 6617 | n_gen = 175, tg = 24.80 t/s, tg_3s = 24.78 t/s 6.20.974.399 I slot print_timing: id 1 | task 6618 | n_gen = 175, tg = 24.80 t/s, tg_3s = 24.78 t/s 6.21.178.168 I slot print_timing: id 0 | task 6617 | prompt eval time = 604.89 ms / 79 tokens ( 7.66 ms per token, 130.60 tokens per second) 6.21.178.175 I slot print_timing: id 0 | task 6617 | eval time = 7220.32 ms / 180 tokens ( 40.34 ms per token, 24.79 tokens per second) 6.21.178.176 I slot print_timing: id 0 | task 6617 | total time = 7825.21 ms / 259 tokens 6.21.178.177 I slot print_timing: id 0 | task 6617 | graphs reused = 6078 6.21.178.178 I slot print_timing: id 0 | task 6617 | graph reallocs = 0 / 0 (same size) / (changed size) 6.21.178.253 I slot release: id 0 | task 6617 | stop processing: n_tokens = 1228, truncated = 0 6.21.221.162 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.876 (> 0.100 thold), f_keep = 0.791 6.21.221.192 I slot launch_slot_: id 0 | task 6801 | processing task, is_child = 0 6.21.759.366 I slot print_timing: id 2 | task 5797 | n_gen = 996, tg = 22.83 t/s, tg_3s = 20.96 t/s 6.21.802.562 I slot print_timing: id 1 | task 6618 | prompt eval time = 602.02 ms / 66 tokens ( 9.12 ms per token, 109.63 tokens per second) 6.21.802.567 I slot print_timing: id 1 | task 6618 | eval time = 7844.62 ms / 184 tokens ( 42.87 ms per token, 23.33 tokens per second) 6.21.802.567 I slot print_timing: id 1 | task 6618 | total time = 8446.64 ms / 250 tokens 6.21.802.568 I slot print_timing: id 1 | task 6618 | graphs reused = 6079 6.21.802.568 I slot print_timing: id 1 | task 6618 | graph reallocs = 0 / 0 (same size) / (changed size) 6.21.802.610 I slot release: id 1 | task 6618 | stop processing: n_tokens = 1220, truncated = 0 6.21.855.899 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.944 (> 0.100 thold), f_keep = 0.796 6.21.855.922 I slot launch_slot_: id 1 | task 6806 | processing task, is_child = 0 6.22.174.709 I slot print_timing: id 3 | task 6508 | n_gen = 294, tg = 22.18 t/s, tg_3s = 18.79 t/s 6.23.261.717 I slot print_timing: id 2 | task 5797 | prompt eval time = 491.97 ms / 92 tokens ( 5.35 ms per token, 187.00 tokens per second) 6.23.261.722 I slot print_timing: id 2 | task 5797 | eval time = 45086.48 ms / 1024 tokens ( 44.07 ms per token, 22.69 tokens per second) 6.23.261.723 I slot print_timing: id 2 | task 5797 | total time = 45578.46 ms / 1116 tokens 6.23.261.724 I slot print_timing: id 2 | task 5797 | graphs reused = 6102 6.23.261.725 I slot print_timing: id 2 | task 5797 | graph reallocs = 0 / 0 (same size) / (changed size) 6.23.261.799 I slot release: id 2 | task 5797 | stop processing: n_tokens = 2086, truncated = 0 6.23.319.244 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.951 (> 0.100 thold), f_keep = 0.465 6.23.354.986 I slot launch_slot_: id 2 | task 6834 | processing task, is_child = 0 6.25.194.876 I slot print_timing: id 3 | task 6508 | n_gen = 358, tg = 22.00 t/s, tg_3s = 21.19 t/s 6.26.517.228 I slot print_timing: id 0 | task 6801 | n_gen = 100, tg = 20.81 t/s, tg_3s = 21.02 t/s 6.26.676.697 I slot print_timing: id 1 | task 6806 | n_gen = 100, tg = 22.49 t/s, tg_3s = 22.71 t/s 6.27.371.703 I slot print_timing: id 0 | task 6801 | prompt eval time = 538.01 ms / 137 tokens ( 3.93 ms per token, 254.64 tokens per second) 6.27.371.711 I slot print_timing: id 0 | task 6801 | eval time = 5612.49 ms / 121 tokens ( 46.77 ms per token, 21.38 tokens per second) 6.27.371.712 I slot print_timing: id 0 | task 6801 | total time = 6150.50 ms / 258 tokens 6.27.371.713 I slot print_timing: id 0 | task 6801 | graphs reused = 6190 6.27.371.714 I slot print_timing: id 0 | task 6801 | graph reallocs = 0 / 0 (same size) / (changed size) 6.27.371.787 I slot release: id 0 | task 6801 | stop processing: n_tokens = 1228, truncated = 0 6.27.420.680 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.791 6.27.420.706 I slot launch_slot_: id 0 | task 6927 | processing task, is_child = 0 6.28.150.527 I slot print_timing: id 2 | task 6834 | n_gen = 100, tg = 22.50 t/s, tg_3s = 22.73 t/s 6.28.230.144 I slot print_timing: id 3 | task 6508 | n_gen = 423, tg = 21.91 t/s, tg_3s = 21.41 t/s 6.29.602.696 I slot print_timing: id 1 | task 6806 | prompt eval time = 418.12 ms / 58 tokens ( 7.21 ms per token, 138.71 tokens per second) 6.29.602.703 I slot print_timing: id 1 | task 6806 | eval time = 7328.64 ms / 163 tokens ( 45.24 ms per token, 22.11 tokens per second) 6.29.602.705 I slot print_timing: id 1 | task 6806 | total time = 7746.76 ms / 221 tokens 6.29.602.706 I slot print_timing: id 1 | task 6806 | graphs reused = 6232 6.29.602.707 I slot print_timing: id 1 | task 6806 | graph reallocs = 0 / 0 (same size) / (changed size) 6.29.602.784 I slot release: id 1 | task 6806 | stop processing: n_tokens = 1191, truncated = 0 6.29.661.902 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.815 6.29.661.927 I slot launch_slot_: id 1 | task 6974 | processing task, is_child = 0 6.31.102.066 I slot print_timing: id 2 | task 6834 | prompt eval time = 396.05 ms / 51 tokens ( 7.77 ms per token, 128.77 tokens per second) 6.31.102.073 I slot print_timing: id 2 | task 6834 | eval time = 7351.01 ms / 164 tokens ( 45.10 ms per token, 22.17 tokens per second) 6.31.102.074 I slot print_timing: id 2 | task 6834 | total time = 7747.07 ms / 215 tokens 6.31.102.075 I slot print_timing: id 2 | task 6834 | graphs reused = 6255 6.31.102.076 I slot print_timing: id 2 | task 6834 | graph reallocs = 0 / 0 (same size) / (changed size) 6.31.102.143 I slot release: id 2 | task 6834 | stop processing: n_tokens = 1184, truncated = 0 6.31.159.057 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.931 (> 0.100 thold), f_keep = 0.820 6.31.159.082 I slot launch_slot_: id 2 | task 7003 | processing task, is_child = 0 6.31.512.601 I slot print_timing: id 3 | task 6508 | n_gen = 487, tg = 21.55 t/s, tg_3s = 19.50 t/s 6.32.616.144 I slot print_timing: id 0 | task 6927 | n_gen = 100, tg = 20.82 t/s, tg_3s = 21.03 t/s 6.34.457.615 I slot print_timing: id 1 | task 6974 | n_gen = 100, tg = 22.65 t/s, tg_3s = 22.88 t/s 6.34.538.372 I slot print_timing: id 3 | task 6508 | n_gen = 561, tg = 21.90 t/s, tg_3s = 24.46 t/s 6.35.221.116 I slot print_timing: id 1 | task 6974 | prompt eval time = 425.41 ms / 63 tokens ( 6.75 ms per token, 148.09 tokens per second) 6.35.221.124 I slot print_timing: id 1 | task 6974 | eval time = 5133.77 ms / 119 tokens ( 43.51 ms per token, 22.99 tokens per second) 6.35.221.125 I slot print_timing: id 1 | task 6974 | total time = 5559.18 ms / 182 tokens 6.35.221.125 I slot print_timing: id 1 | task 6974 | graphs reused = 6344 6.35.221.126 I slot print_timing: id 1 | task 6974 | graph reallocs = 0 / 0 (same size) / (changed size) 6.35.221.195 I slot release: id 1 | task 6974 | stop processing: n_tokens = 1152, truncated = 0 6.35.278.339 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.843 6.35.278.368 I slot launch_slot_: id 1 | task 7097 | processing task, is_child = 0 6.35.711.785 I slot print_timing: id 0 | task 6927 | n_gen = 168, tg = 21.27 t/s, tg_3s = 21.97 t/s 6.35.924.562 I slot print_timing: id 0 | task 6927 | prompt eval time = 439.48 ms / 82 tokens ( 5.36 ms per token, 186.58 tokens per second) 6.35.924.567 I slot print_timing: id 0 | task 6927 | eval time = 8064.36 ms / 173 tokens ( 46.89 ms per token, 21.33 tokens per second) 6.35.924.568 I slot print_timing: id 0 | task 6927 | total time = 8503.85 ms / 255 tokens 6.35.924.568 I slot print_timing: id 0 | task 6927 | graphs reused = 6348 6.35.924.569 I slot print_timing: id 0 | task 6927 | graph reallocs = 0 / 0 (same size) / (changed size) 6.35.924.639 I slot release: id 0 | task 6927 | stop processing: n_tokens = 1225, truncated = 0 6.35.967.253 I slot print_timing: id 2 | task 7003 | n_gen = 100, tg = 22.69 t/s, tg_3s = 22.92 t/s 6.35.967.401 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.793 6.35.967.422 I slot launch_slot_: id 0 | task 7106 | processing task, is_child = 0 6.37.567.156 I slot print_timing: id 3 | task 6508 | n_gen = 618, tg = 21.57 t/s, tg_3s = 18.82 t/s 6.38.974.418 I slot print_timing: id 2 | task 7003 | n_gen = 166, tg = 22.39 t/s, tg_3s = 21.95 t/s 6.39.135.639 I slot print_timing: id 3 | task 6508 | prompt eval time = 458.06 ms / 88 tokens ( 5.21 ms per token, 192.11 tokens per second) 6.39.135.643 I slot print_timing: id 3 | task 6508 | eval time = 30170.05 ms / 657 tokens ( 45.99 ms per token, 21.74 tokens per second) 6.39.135.644 I slot print_timing: id 3 | task 6508 | total time = 30628.12 ms / 745 tokens 6.39.135.645 I slot print_timing: id 3 | task 6508 | graphs reused = 6416 6.39.135.646 I slot print_timing: id 3 | task 6508 | graph reallocs = 0 / 0 (same size) / (changed size) 6.39.135.726 I slot release: id 3 | task 6508 | stop processing: n_tokens = 1715, truncated = 0 6.39.177.462 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.566 6.39.177.488 I slot launch_slot_: id 3 | task 7178 | processing task, is_child = 0 6.40.434.068 I slot print_timing: id 1 | task 7097 | n_gen = 100, tg = 20.97 t/s, tg_3s = 21.18 t/s 6.40.753.525 I slot print_timing: id 0 | task 7106 | n_gen = 100, tg = 22.72 t/s, tg_3s = 22.95 t/s 6.41.992.697 I slot print_timing: id 2 | task 7003 | n_gen = 232, tg = 22.24 t/s, tg_3s = 21.87 t/s 6.43.437.965 I slot print_timing: id 1 | task 7097 | n_gen = 175, tg = 22.52 t/s, tg_3s = 24.97 t/s 6.43.598.095 I slot print_timing: id 3 | task 7178 | n_gen = 100, tg = 24.92 t/s, tg_3s = 25.17 t/s 6.43.757.974 I slot print_timing: id 0 | task 7106 | n_gen = 175, tg = 23.64 t/s, tg_3s = 24.96 t/s 6.44.358.820 I slot print_timing: id 2 | task 7003 | prompt eval time = 444.94 ms / 72 tokens ( 6.18 ms per token, 161.82 tokens per second) 6.44.358.828 I slot print_timing: id 2 | task 7003 | eval time = 12754.79 ms / 291 tokens ( 43.98 ms per token, 22.74 tokens per second) 6.44.358.829 I slot print_timing: id 2 | task 7003 | total time = 13199.73 ms / 363 tokens 6.44.358.830 I slot print_timing: id 2 | task 7003 | graphs reused = 6531 6.44.358.831 I slot print_timing: id 2 | task 7003 | graph reallocs = 0 / 0 (same size) / (changed size) 6.44.358.903 I slot release: id 2 | task 7003 | stop processing: n_tokens = 1333, truncated = 0 6.44.415.466 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.728 6.44.415.505 I slot launch_slot_: id 2 | task 7300 | processing task, is_child = 0 6.46.448.610 I slot print_timing: id 1 | task 7097 | n_gen = 239, tg = 22.17 t/s, tg_3s = 21.26 t/s 6.46.614.778 I slot print_timing: id 3 | task 7178 | n_gen = 164, tg = 23.32 t/s, tg_3s = 21.22 t/s 6.46.774.617 I slot print_timing: id 0 | task 7106 | n_gen = 239, tg = 22.93 t/s, tg_3s = 21.22 t/s 6.47.296.619 I slot print_timing: id 3 | task 7178 | prompt eval time = 447.58 ms / 84 tokens ( 5.33 ms per token, 187.67 tokens per second) 6.47.296.626 I slot print_timing: id 3 | task 7178 | eval time = 7671.54 ms / 181 tokens ( 42.62 ms per token, 23.46 tokens per second) 6.47.296.627 I slot print_timing: id 3 | task 7178 | total time = 8119.12 ms / 265 tokens 6.47.296.628 I slot print_timing: id 3 | task 7178 | graphs reused = 6588 6.47.296.629 I slot print_timing: id 3 | task 7178 | graph reallocs = 0 / 0 (same size) / (changed size) 6.47.296.716 I slot release: id 3 | task 7178 | stop processing: n_tokens = 1235, truncated = 0 6.47.338.416 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.786 6.47.338.440 I slot launch_slot_: id 3 | task 7363 | processing task, is_child = 0 6.49.269.009 I slot print_timing: id 2 | task 7300 | n_gen = 100, tg = 22.75 t/s, tg_3s = 22.98 t/s 6.49.469.114 I slot print_timing: id 1 | task 7097 | n_gen = 305, tg = 22.10 t/s, tg_3s = 21.85 t/s 6.49.789.046 I slot print_timing: id 0 | task 7106 | n_gen = 305, tg = 22.70 t/s, tg_3s = 21.89 t/s 6.49.829.191 I slot print_timing: id 0 | task 7106 | prompt eval time = 428.90 ms / 79 tokens ( 5.43 ms per token, 184.19 tokens per second) 6.49.829.199 I slot print_timing: id 0 | task 7106 | eval time = 13432.86 ms / 306 tokens ( 44.04 ms per token, 22.71 tokens per second) 6.49.829.200 I slot print_timing: id 0 | task 7106 | total time = 13861.76 ms / 385 tokens 6.49.829.201 I slot print_timing: id 0 | task 7106 | graphs reused = 6638 6.49.829.202 I slot print_timing: id 0 | task 7106 | graph reallocs = 0 / 0 (same size) / (changed size) 6.49.829.275 I slot release: id 0 | task 7106 | stop processing: n_tokens = 1355, truncated = 0 6.49.871.596 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.717 6.49.871.625 I slot launch_slot_: id 0 | task 7418 | processing task, is_child = 0 6.52.117.532 I slot print_timing: id 3 | task 7363 | n_gen = 100, tg = 22.81 t/s, tg_3s = 23.04 t/s 6.52.277.908 I slot print_timing: id 2 | task 7300 | n_gen = 166, tg = 22.42 t/s, tg_3s = 21.93 t/s 6.52.477.968 I slot print_timing: id 1 | task 7097 | n_gen = 371, tg = 22.07 t/s, tg_3s = 21.94 t/s 6.54.282.945 I slot print_timing: id 0 | task 7418 | n_gen = 100, tg = 24.90 t/s, tg_3s = 25.15 t/s 6.55.125.191 I slot print_timing: id 3 | task 7363 | n_gen = 175, tg = 23.68 t/s, tg_3s = 24.94 t/s 6.55.286.560 I slot print_timing: id 2 | task 7300 | n_gen = 241, tg = 23.15 t/s, tg_3s = 24.93 t/s 6.55.487.541 I slot print_timing: id 1 | task 7097 | n_gen = 446, tg = 22.50 t/s, tg_3s = 24.92 t/s 6.57.301.982 I slot print_timing: id 0 | task 7418 | n_gen = 175, tg = 24.87 t/s, tg_3s = 24.84 t/s 6.58.155.444 I slot print_timing: id 3 | task 7363 | n_gen = 250, tg = 23.99 t/s, tg_3s = 24.75 t/s 6.58.317.222 I slot print_timing: id 2 | task 7300 | n_gen = 316, tg = 23.51 t/s, tg_3s = 24.75 t/s 6.58.518.681 I slot print_timing: id 1 | task 7097 | n_gen = 521, tg = 22.80 t/s, tg_3s = 24.74 t/s 7.00.336.573 I slot print_timing: id 0 | task 7418 | n_gen = 250, tg = 24.83 t/s, tg_3s = 24.72 t/s 7.01.185.156 I slot print_timing: id 3 | task 7363 | n_gen = 325, tg = 24.17 t/s, tg_3s = 24.75 t/s 7.01.346.437 I slot print_timing: id 2 | task 7300 | n_gen = 391, tg = 23.74 t/s, tg_3s = 24.76 t/s 7.01.427.132 I slot print_timing: id 0 | task 7418 | prompt eval time = 435.00 ms / 78 tokens ( 5.58 ms per token, 179.31 tokens per second) 7.01.427.137 I slot print_timing: id 0 | task 7418 | eval time = 11120.50 ms / 277 tokens ( 40.29 ms per token, 24.82 tokens per second) 7.01.427.137 I slot print_timing: id 0 | task 7418 | total time = 11555.50 ms / 355 tokens 7.01.427.138 I slot print_timing: id 0 | task 7418 | graphs reused = 6912 7.01.427.139 I slot print_timing: id 0 | task 7418 | graph reallocs = 0 / 0 (same size) / (changed size) 7.01.427.212 I slot release: id 0 | task 7418 | stop processing: n_tokens = 1325, truncated = 0 7.01.469.692 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.940 (> 0.100 thold), f_keep = 0.733 7.01.469.720 I slot launch_slot_: id 0 | task 7698 | processing task, is_child = 0 7.01.772.854 I slot print_timing: id 1 | task 7097 | n_gen = 595, tg = 22.79 t/s, tg_3s = 22.74 t/s 7.02.054.789 I slot print_timing: id 2 | task 7300 | prompt eval time = 501.82 ms / 101 tokens ( 4.97 ms per token, 201.27 tokens per second) 7.02.054.795 I slot print_timing: id 2 | task 7300 | eval time = 17137.46 ms / 401 tokens ( 42.84 ms per token, 23.34 tokens per second) 7.02.054.795 I slot print_timing: id 2 | task 7300 | total time = 17639.28 ms / 502 tokens 7.02.054.796 I slot print_timing: id 2 | task 7300 | graphs reused = 6917 7.02.054.796 I slot print_timing: id 2 | task 7300 | graph reallocs = 0 / 0 (same size) / (changed size) 7.02.054.846 I slot release: id 2 | task 7300 | stop processing: n_tokens = 1472, truncated = 0 7.02.108.401 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.940 (> 0.100 thold), f_keep = 0.660 7.02.108.417 I slot launch_slot_: id 2 | task 7707 | processing task, is_child = 0 7.04.187.124 I slot print_timing: id 3 | task 7363 | n_gen = 383, tg = 23.28 t/s, tg_3s = 19.32 t/s 7.04.791.854 I slot print_timing: id 1 | task 7097 | n_gen = 660, tg = 22.66 t/s, tg_3s = 21.53 t/s 7.06.203.689 I slot print_timing: id 0 | task 7698 | n_gen = 100, tg = 22.75 t/s, tg_3s = 22.98 t/s 7.06.526.008 I slot print_timing: id 2 | task 7707 | n_gen = 100, tg = 24.77 t/s, tg_3s = 25.02 t/s 7.07.211.804 I slot print_timing: id 3 | task 7363 | n_gen = 458, tg = 23.52 t/s, tg_3s = 24.80 t/s 7.07.814.070 I slot print_timing: id 1 | task 7097 | n_gen = 735, tg = 22.86 t/s, tg_3s = 24.82 t/s 7.09.233.738 I slot print_timing: id 0 | task 7698 | n_gen = 175, tg = 23.57 t/s, tg_3s = 24.75 t/s 7.09.557.375 I slot print_timing: id 2 | task 7707 | n_gen = 175, tg = 24.76 t/s, tg_3s = 24.74 t/s 7.09.799.280 I slot print_timing: id 1 | task 7097 | prompt eval time = 433.57 ms / 65 tokens ( 6.67 ms per token, 149.92 tokens per second) 7.09.799.288 I slot print_timing: id 1 | task 7097 | eval time = 34087.34 ms / 784 tokens ( 43.53 ms per token, 22.97 tokens per second) 7.09.799.289 I slot print_timing: id 1 | task 7097 | total time = 34520.90 ms / 849 tokens 7.09.799.290 I slot print_timing: id 1 | task 7097 | graphs reused = 7095 7.09.799.290 I slot print_timing: id 1 | task 7097 | graph reallocs = 0 / 0 (same size) / (changed size) 7.09.799.357 I slot release: id 1 | task 7097 | stop processing: n_tokens = 1819, truncated = 0 7.09.855.663 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.534 7.09.855.691 I slot launch_slot_: id 1 | task 7891 | processing task, is_child = 0 7.10.257.846 I slot print_timing: id 3 | task 7363 | n_gen = 524, tg = 23.26 t/s, tg_3s = 21.67 t/s 7.12.057.096 I slot print_timing: id 0 | task 7698 | prompt eval time = 382.06 ms / 62 tokens ( 6.16 ms per token, 162.28 tokens per second) 7.12.057.104 I slot print_timing: id 0 | task 7698 | eval time = 10205.31 ms / 234 tokens ( 43.80 ms per token, 22.83 tokens per second) 7.12.057.105 I slot print_timing: id 0 | task 7698 | total time = 10587.37 ms / 296 tokens 7.12.057.106 I slot print_timing: id 0 | task 7698 | graphs reused = 7136 7.12.057.107 I slot print_timing: id 0 | task 7698 | graph reallocs = 0 / 0 (same size) / (changed size) 7.12.057.182 I slot release: id 0 | task 7698 | stop processing: n_tokens = 1266, truncated = 0 7.12.099.600 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.879 (> 0.100 thold), f_keep = 0.767 7.12.099.627 I slot launch_slot_: id 0 | task 7937 | processing task, is_child = 0 7.12.557.805 I slot print_timing: id 2 | task 7707 | n_gen = 228, tg = 22.63 t/s, tg_3s = 17.66 t/s 7.13.285.411 I slot print_timing: id 3 | task 7363 | n_gen = 586, tg = 22.93 t/s, tg_3s = 20.48 t/s 7.14.814.651 I slot print_timing: id 1 | task 7891 | n_gen = 100, tg = 22.21 t/s, tg_3s = 22.43 t/s 7.15.540.670 I slot print_timing: id 3 | task 7363 | prompt eval time = 439.02 ms / 79 tokens ( 5.56 ms per token, 179.95 tokens per second) 7.15.540.680 I slot print_timing: id 3 | task 7363 | eval time = 27763.21 ms / 642 tokens ( 43.31 ms per token, 23.09 tokens per second) 7.15.540.681 I slot print_timing: id 3 | task 7363 | total time = 28202.22 ms / 721 tokens 7.15.540.682 I slot print_timing: id 3 | task 7363 | graphs reused = 7208 7.15.540.683 I slot print_timing: id 3 | task 7363 | graph reallocs = 0 / 0 (same size) / (changed size) 7.15.540.767 I slot release: id 3 | task 7363 | stop processing: n_tokens = 1691, truncated = 0 7.15.582.470 I slot print_timing: id 2 | task 7707 | n_gen = 302, tg = 23.06 t/s, tg_3s = 24.47 t/s 7.15.582.477 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.574 7.15.582.499 I slot launch_slot_: id 3 | task 8013 | processing task, is_child = 0 7.17.003.598 I slot print_timing: id 0 | task 7937 | n_gen = 100, tg = 22.67 t/s, tg_3s = 22.90 t/s 7.17.843.071 I slot print_timing: id 1 | task 7891 | n_gen = 166, tg = 22.04 t/s, tg_3s = 21.79 t/s 7.18.602.087 I slot print_timing: id 2 | task 7707 | n_gen = 368, tg = 22.83 t/s, tg_3s = 21.86 t/s 7.20.007.147 I slot print_timing: id 0 | task 7937 | n_gen = 175, tg = 23.61 t/s, tg_3s = 24.97 t/s 7.20.007.679 I slot print_timing: id 3 | task 8013 | n_gen = 100, tg = 24.92 t/s, tg_3s = 25.17 t/s 7.20.853.423 I slot print_timing: id 1 | task 7891 | n_gen = 241, tg = 22.86 t/s, tg_3s = 24.91 t/s 7.21.619.285 I slot print_timing: id 2 | task 7707 | n_gen = 443, tg = 23.15 t/s, tg_3s = 24.86 t/s 7.23.033.919 I slot print_timing: id 0 | task 7937 | n_gen = 250, tg = 23.95 t/s, tg_3s = 24.78 t/s 7.23.034.429 I slot print_timing: id 3 | task 8013 | n_gen = 175, tg = 24.86 t/s, tg_3s = 24.78 t/s 7.23.879.724 I slot print_timing: id 1 | task 7891 | n_gen = 316, tg = 23.29 t/s, tg_3s = 24.78 t/s 7.24.649.908 I slot print_timing: id 2 | task 7707 | n_gen = 518, tg = 23.37 t/s, tg_3s = 24.75 t/s 7.26.060.533 I slot print_timing: id 0 | task 7937 | n_gen = 325, tg = 24.14 t/s, tg_3s = 24.78 t/s 7.26.061.054 I slot print_timing: id 3 | task 8013 | n_gen = 250, tg = 24.83 t/s, tg_3s = 24.78 t/s 7.26.909.096 I slot print_timing: id 1 | task 7891 | n_gen = 391, tg = 23.56 t/s, tg_3s = 24.76 t/s 7.27.678.583 I slot print_timing: id 2 | task 7707 | n_gen = 593, tg = 23.54 t/s, tg_3s = 24.76 t/s 7.29.092.389 I slot print_timing: id 0 | task 7937 | n_gen = 400, tg = 24.25 t/s, tg_3s = 24.74 t/s 7.29.092.910 I slot print_timing: id 3 | task 8013 | n_gen = 325, tg = 24.81 t/s, tg_3s = 24.74 t/s 7.29.939.319 I slot print_timing: id 1 | task 7891 | n_gen = 466, tg = 23.75 t/s, tg_3s = 24.75 t/s 7.30.707.827 I slot print_timing: id 2 | task 7707 | n_gen = 668, tg = 23.67 t/s, tg_3s = 24.76 t/s 7.31.113.104 I slot print_timing: id 3 | task 8013 | prompt eval time = 451.68 ms / 85 tokens ( 5.31 ms per token, 188.19 tokens per second) 7.31.113.113 I slot print_timing: id 3 | task 8013 | eval time = 15078.92 ms / 375 tokens ( 40.32 ms per token, 24.80 tokens per second) 7.31.113.114 I slot print_timing: id 3 | task 8013 | total time = 15530.60 ms / 460 tokens 7.31.113.115 I slot print_timing: id 3 | task 8013 | graphs reused = 7579 7.31.113.116 I slot print_timing: id 3 | task 8013 | graph reallocs = 0 / 0 (same size) / (changed size) 7.31.113.192 I slot release: id 3 | task 8013 | stop processing: n_tokens = 1430, truncated = 0 7.31.155.410 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.679 7.31.155.435 I slot launch_slot_: id 3 | task 8391 | processing task, is_child = 0 7.32.127.607 I slot print_timing: id 0 | task 7937 | n_gen = 467, tg = 23.91 t/s, tg_3s = 22.07 t/s 7.32.975.444 I slot print_timing: id 1 | task 7891 | n_gen = 533, tg = 23.52 t/s, tg_3s = 22.07 t/s 7.33.743.403 I slot print_timing: id 2 | task 7707 | n_gen = 735, tg = 23.51 t/s, tg_3s = 22.07 t/s 7.35.164.630 I slot print_timing: id 0 | task 7937 | n_gen = 542, tg = 24.01 t/s, tg_3s = 24.70 t/s 7.35.570.290 I slot print_timing: id 3 | task 8391 | n_gen = 100, tg = 24.70 t/s, tg_3s = 24.95 t/s 7.36.013.106 I slot print_timing: id 1 | task 7891 | n_gen = 608, tg = 23.66 t/s, tg_3s = 24.69 t/s 7.36.578.644 I slot print_timing: id 0 | task 7937 | prompt eval time = 536.98 ms / 134 tokens ( 4.01 ms per token, 249.54 tokens per second) 7.36.578.651 I slot print_timing: id 0 | task 7937 | eval time = 23942.03 ms / 577 tokens ( 41.57 ms per token, 24.06 tokens per second) 7.36.578.652 I slot print_timing: id 0 | task 7937 | total time = 24479.01 ms / 711 tokens 7.36.578.653 I slot print_timing: id 0 | task 7937 | graphs reused = 7701 7.36.578.654 I slot print_timing: id 0 | task 7937 | graph reallocs = 0 / 0 (same size) / (changed size) 7.36.578.726 I slot release: id 0 | task 7937 | stop processing: n_tokens = 1681, truncated = 0 7.36.620.853 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.578 7.36.620.880 I slot launch_slot_: id 0 | task 8519 | processing task, is_child = 0 7.36.958.720 I slot print_timing: id 2 | task 7707 | n_gen = 807, tg = 23.41 t/s, tg_3s = 22.39 t/s 7.38.604.595 I slot print_timing: id 3 | task 8391 | n_gen = 167, tg = 23.57 t/s, tg_3s = 22.08 t/s 7.39.047.180 I slot print_timing: id 1 | task 7891 | n_gen = 675, tg = 23.49 t/s, tg_3s = 22.08 t/s 7.39.975.908 I slot print_timing: id 2 | task 7707 | n_gen = 881, tg = 23.50 t/s, tg_3s = 24.53 t/s 7.40.985.429 I slot print_timing: id 1 | task 7891 | prompt eval time = 501.04 ms / 92 tokens ( 5.45 ms per token, 183.62 tokens per second) 7.40.985.436 I slot print_timing: id 1 | task 7891 | eval time = 30628.69 ms / 723 tokens ( 42.42 ms per token, 23.57 tokens per second) 7.40.985.437 I slot print_timing: id 1 | task 7891 | total time = 31129.73 ms / 815 tokens 7.40.985.438 I slot print_timing: id 1 | task 7891 | graphs reused = 7799 7.40.985.439 I slot print_timing: id 1 | task 7891 | graph reallocs = 0 / 0 (same size) / (changed size) 7.40.985.514 I slot release: id 1 | task 7891 | stop processing: n_tokens = 1784, truncated = 0 7.40.985.864 I slot print_timing: id 3 | task 8391 | prompt eval time = 407.53 ms / 69 tokens ( 5.91 ms per token, 169.31 tokens per second) 7.40.985.871 I slot print_timing: id 3 | task 8391 | eval time = 9422.89 ms / 226 tokens ( 41.88 ms per token, 23.88 tokens per second) 7.40.985.872 I slot print_timing: id 3 | task 8391 | total time = 9830.42 ms / 295 tokens 7.40.985.872 I slot print_timing: id 3 | task 8391 | graphs reused = 7799 7.40.985.873 I slot print_timing: id 3 | task 8391 | graph reallocs = 0 / 0 (same size) / (changed size) 7.40.985.930 I slot release: id 3 | task 8391 | stop processing: n_tokens = 1265, truncated = 0 7.41.031.602 I slot print_timing: id 0 | task 8519 | n_gen = 100, tg = 24.78 t/s, tg_3s = 25.03 t/s 7.41.031.757 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.544 7.41.031.783 I slot launch_slot_: id 1 | task 8621 | processing task, is_child = 0 7.41.058.715 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.768 7.41.058.733 I slot launch_slot_: id 3 | task 8622 | processing task, is_child = 0 7.42.987.118 I slot print_timing: id 2 | task 7707 | n_gen = 935, tg = 23.09 t/s, tg_3s = 17.93 t/s 7.44.031.892 I slot print_timing: id 0 | task 8519 | n_gen = 154, tg = 21.87 t/s, tg_3s = 18.00 t/s 7.44.836.757 I slot print_timing: id 2 | task 7707 | prompt eval time = 420.48 ms / 62 tokens ( 6.78 ms per token, 147.45 tokens per second) 7.44.836.762 I slot print_timing: id 2 | task 7707 | eval time = 42307.85 ms / 981 tokens ( 43.17 ms per token, 23.16 tokens per second) 7.44.836.763 I slot print_timing: id 2 | task 7707 | total time = 42728.33 ms / 1043 tokens 7.44.836.764 I slot print_timing: id 2 | task 7707 | graphs reused = 7870 7.44.836.765 I slot print_timing: id 2 | task 7707 | graph reallocs = 0 / 0 (same size) / (changed size) 7.44.836.842 I slot release: id 2 | task 7707 | stop processing: n_tokens = 2013, truncated = 0 7.44.894.492 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.482 7.44.930.893 I slot launch_slot_: id 2 | task 8698 | processing task, is_child = 0 7.46.374.915 I slot print_timing: id 1 | task 8621 | n_gen = 100, tg = 22.29 t/s, tg_3s = 22.51 t/s 7.46.375.278 I slot print_timing: id 3 | task 8622 | n_gen = 100, tg = 22.29 t/s, tg_3s = 22.51 t/s 7.47.052.925 I slot print_timing: id 0 | task 8519 | n_gen = 218, tg = 21.67 t/s, tg_3s = 21.18 t/s 7.48.380.065 I slot print_timing: id 3 | task 8622 | prompt eval time = 871.32 ms / 75 tokens ( 11.62 ms per token, 86.08 tokens per second) 7.48.380.073 I slot print_timing: id 3 | task 8622 | eval time = 6447.17 ms / 150 tokens ( 43.27 ms per token, 23.11 tokens per second) 7.48.380.074 I slot print_timing: id 3 | task 8622 | total time = 7318.49 ms / 225 tokens 7.48.380.075 I slot print_timing: id 3 | task 8622 | graphs reused = 7941 7.48.380.075 I slot print_timing: id 3 | task 8622 | graph reallocs = 0 / 0 (same size) / (changed size) 7.48.380.158 I slot release: id 3 | task 8622 | stop processing: n_tokens = 1195, truncated = 0 7.48.421.854 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.918 (> 0.100 thold), f_keep = 0.813 7.48.421.882 I slot launch_slot_: id 3 | task 8776 | processing task, is_child = 0 7.49.393.396 I slot print_timing: id 1 | task 8621 | n_gen = 166, tg = 22.12 t/s, tg_3s = 21.87 t/s 7.49.755.886 I slot print_timing: id 2 | task 8698 | n_gen = 100, tg = 22.77 t/s, tg_3s = 23.00 t/s 7.50.076.656 I slot print_timing: id 0 | task 8519 | n_gen = 284, tg = 21.70 t/s, tg_3s = 21.83 t/s 7.52.401.962 I slot print_timing: id 1 | task 8621 | n_gen = 241, tg = 22.92 t/s, tg_3s = 24.93 t/s 7.52.762.166 I slot print_timing: id 2 | task 8698 | n_gen = 175, tg = 23.66 t/s, tg_3s = 24.95 t/s 7.52.842.398 I slot print_timing: id 3 | task 8776 | n_gen = 100, tg = 24.90 t/s, tg_3s = 25.15 t/s 7.53.082.318 I slot print_timing: id 0 | task 8519 | n_gen = 359, tg = 22.31 t/s, tg_3s = 24.95 t/s 7.55.239.290 I slot print_timing: id 0 | task 8519 | prompt eval time = 415.93 ms / 73 tokens ( 5.70 ms per token, 175.51 tokens per second) 7.55.239.295 I slot print_timing: id 0 | task 8519 | eval time = 18202.47 ms / 413 tokens ( 44.18 ms per token, 22.63 tokens per second) 7.55.239.296 I slot print_timing: id 0 | task 8519 | total time = 18618.40 ms / 486 tokens 7.55.239.297 I slot print_timing: id 0 | task 8519 | graphs reused = 8099 7.55.239.298 I slot print_timing: id 0 | task 8519 | graph reallocs = 0 / 0 (same size) / (changed size) 7.55.239.371 I slot release: id 0 | task 8519 | stop processing: n_tokens = 1456, truncated = 0 7.55.281.442 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.667 7.55.281.465 I slot launch_slot_: id 0 | task 8939 | processing task, is_child = 0 7.55.647.133 I slot print_timing: id 1 | task 8621 | n_gen = 314, tg = 22.82 t/s, tg_3s = 22.49 t/s 7.55.767.600 I slot print_timing: id 2 | task 8698 | n_gen = 241, tg = 23.17 t/s, tg_3s = 21.96 t/s 7.55.846.595 I slot print_timing: id 3 | task 8776 | n_gen = 166, tg = 23.64 t/s, tg_3s = 21.97 t/s 7.58.526.381 I slot print_timing: id 2 | task 8698 | prompt eval time = 476.46 ms / 86 tokens ( 5.54 ms per token, 180.50 tokens per second) 7.58.526.384 I slot print_timing: id 2 | task 8698 | eval time = 13119.02 ms / 310 tokens ( 42.46 ms per token, 23.55 tokens per second) 7.58.526.385 I slot print_timing: id 2 | task 8698 | total time = 13595.48 ms / 396 tokens 7.58.526.386 I slot print_timing: id 2 | task 8698 | graphs reused = 8169 7.58.526.386 I slot print_timing: id 2 | task 8698 | graph reallocs = 0 / 0 (same size) / (changed size) 7.58.526.429 I slot release: id 2 | task 8698 | stop processing: n_tokens = 1365, truncated = 0 7.58.576.305 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.711 7.58.576.324 I slot launch_slot_: id 2 | task 9013 | processing task, is_child = 0 7.58.916.445 I slot print_timing: id 1 | task 8621 | n_gen = 387, tg = 22.73 t/s, tg_3s = 22.33 t/s 7.58.916.570 I slot print_timing: id 3 | task 8776 | n_gen = 235, tg = 23.28 t/s, tg_3s = 22.48 t/s 7.59.376.061 I slot print_timing: id 1 | task 8621 | prompt eval time = 873.92 ms / 102 tokens ( 8.57 ms per token, 116.72 tokens per second) 7.59.376.067 I slot print_timing: id 1 | task 8621 | eval time = 17443.39 ms / 397 tokens ( 44.05 ms per token, 22.70 tokens per second) 7.59.376.068 I slot print_timing: id 1 | task 8621 | total time = 18317.31 ms / 499 tokens 7.59.376.069 I slot print_timing: id 1 | task 8621 | graphs reused = 8177 7.59.376.069 I slot print_timing: id 1 | task 8621 | graph reallocs = 0 / 0 (same size) / (changed size) 7.59.376.145 I slot release: id 1 | task 8621 | stop processing: n_tokens = 1467, truncated = 0 7.59.433.283 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.662 7.59.433.310 I slot launch_slot_: id 1 | task 9026 | processing task, is_child = 0 8.00.496.337 I slot print_timing: id 0 | task 8939 | n_gen = 100, tg = 20.75 t/s, tg_3s = 20.96 t/s 8.01.935.526 I slot print_timing: id 3 | task 8776 | n_gen = 298, tg = 22.73 t/s, tg_3s = 20.87 t/s 8.03.416.601 I slot print_timing: id 2 | task 9013 | n_gen = 100, tg = 22.46 t/s, tg_3s = 22.69 t/s 8.03.496.347 I slot print_timing: id 0 | task 8939 | n_gen = 175, tg = 22.39 t/s, tg_3s = 25.00 t/s 8.03.896.593 I slot print_timing: id 1 | task 9026 | n_gen = 100, tg = 24.93 t/s, tg_3s = 25.18 t/s 8.04.939.326 I slot print_timing: id 3 | task 8776 | n_gen = 373, tg = 23.14 t/s, tg_3s = 24.97 t/s 8.06.428.338 I slot print_timing: id 2 | task 9013 | n_gen = 175, tg = 23.45 t/s, tg_3s = 24.90 t/s 8.06.508.557 I slot print_timing: id 0 | task 8939 | n_gen = 250, tg = 23.09 t/s, tg_3s = 24.90 t/s 8.06.911.179 I slot print_timing: id 1 | task 9026 | n_gen = 175, tg = 24.91 t/s, tg_3s = 24.88 t/s 8.07.965.091 I slot print_timing: id 3 | task 8776 | n_gen = 448, tg = 23.40 t/s, tg_3s = 24.79 t/s 8.09.174.221 I slot print_timing: id 1 | task 9026 | prompt eval time = 492.64 ms / 84 tokens ( 5.86 ms per token, 170.51 tokens per second) 8.09.174.226 I slot print_timing: id 1 | task 9026 | eval time = 9248.25 ms / 231 tokens ( 40.21 ms per token, 24.87 tokens per second) 8.09.174.227 I slot print_timing: id 1 | task 9026 | total time = 9740.90 ms / 315 tokens 8.09.174.228 I slot print_timing: id 1 | task 9026 | graphs reused = 8405 8.09.174.229 I slot print_timing: id 1 | task 9026 | graph reallocs = 0 / 0 (same size) / (changed size) 8.09.174.299 I slot release: id 1 | task 9026 | stop processing: n_tokens = 1285, truncated = 0 8.09.231.947 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.756 8.09.231.979 I slot launch_slot_: id 1 | task 9260 | processing task, is_child = 0 8.09.605.039 I slot print_timing: id 0 | task 8939 | n_gen = 318, tg = 22.84 t/s, tg_3s = 21.96 t/s 8.09.605.159 I slot print_timing: id 2 | task 9013 | n_gen = 245, tg = 23.03 t/s, tg_3s = 22.03 t/s 8.11.003.564 I slot print_timing: id 3 | task 8776 | n_gen = 513, tg = 23.13 t/s, tg_3s = 21.39 t/s 8.12.534.695 I slot print_timing: id 2 | task 9013 | prompt eval time = 432.97 ms / 69 tokens ( 6.27 ms per token, 159.36 tokens per second) 8.12.534.703 I slot print_timing: id 2 | task 9013 | eval time = 13525.39 ms / 316 tokens ( 42.94 ms per token, 23.29 tokens per second) 8.12.534.704 I slot print_timing: id 2 | task 9013 | total time = 13958.36 ms / 385 tokens 8.12.534.705 I slot print_timing: id 2 | task 9013 | graphs reused = 8474 8.12.534.706 I slot print_timing: id 2 | task 9013 | graph reallocs = 0 / 0 (same size) / (changed size) 8.12.534.790 I slot release: id 2 | task 9013 | stop processing: n_tokens = 1355, truncated = 0 8.12.591.898 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.717 8.12.591.922 I slot launch_slot_: id 2 | task 9334 | processing task, is_child = 0 8.12.932.989 I slot print_timing: id 0 | task 8939 | n_gen = 391, tg = 22.66 t/s, tg_3s = 21.94 t/s 8.14.007.438 I slot print_timing: id 3 | task 8776 | n_gen = 578, tg = 22.95 t/s, tg_3s = 21.64 t/s 8.14.087.655 I slot print_timing: id 1 | task 9260 | n_gen = 100, tg = 22.59 t/s, tg_3s = 22.81 t/s 8.15.939.823 I slot print_timing: id 0 | task 8939 | n_gen = 464, tg = 22.90 t/s, tg_3s = 24.28 t/s 8.17.027.385 I slot print_timing: id 2 | task 9334 | n_gen = 100, tg = 24.74 t/s, tg_3s = 24.99 t/s 8.17.027.561 I slot print_timing: id 3 | task 8776 | n_gen = 653, tg = 23.15 t/s, tg_3s = 24.83 t/s 8.17.107.852 I slot print_timing: id 1 | task 9260 | n_gen = 175, tg = 23.50 t/s, tg_3s = 24.83 t/s 8.17.349.748 I slot print_timing: id 0 | task 8939 | prompt eval time = 443.60 ms / 85 tokens ( 5.22 ms per token, 191.62 tokens per second) 8.17.349.756 I slot print_timing: id 0 | task 8939 | eval time = 21624.68 ms / 499 tokens ( 43.42 ms per token, 23.03 tokens per second) 8.17.349.757 I slot print_timing: id 0 | task 8939 | total time = 22068.27 ms / 584 tokens 8.17.349.758 I slot print_timing: id 0 | task 8939 | graphs reused = 8580 8.17.349.758 I slot print_timing: id 0 | task 8939 | graph reallocs = 0 / 0 (same size) / (changed size) 8.17.349.829 I slot release: id 0 | task 8939 | stop processing: n_tokens = 1554, truncated = 0 8.17.392.140 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.625 8.17.392.165 I slot launch_slot_: id 0 | task 9445 | processing task, is_child = 0 8.18.549.106 I slot print_timing: id 1 | task 9260 | prompt eval time = 472.48 ms / 74 tokens ( 6.38 ms per token, 156.62 tokens per second) 8.18.549.113 I slot print_timing: id 1 | task 9260 | eval time = 8844.63 ms / 203 tokens ( 43.79 ms per token, 22.84 tokens per second) 8.18.549.115 I slot print_timing: id 1 | task 9260 | total time = 9317.11 ms / 277 tokens 8.18.549.115 I slot print_timing: id 1 | task 9260 | graphs reused = 8599 8.18.549.116 I slot print_timing: id 1 | task 9260 | graph reallocs = 0 / 0 (same size) / (changed size) 8.18.549.187 I slot release: id 1 | task 9260 | stop processing: n_tokens = 1247, truncated = 0 8.18.606.041 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.882 (> 0.100 thold), f_keep = 0.779 8.18.606.073 I slot launch_slot_: id 1 | task 9468 | processing task, is_child = 0 8.20.054.573 I slot print_timing: id 2 | task 9334 | n_gen = 155, tg = 21.91 t/s, tg_3s = 18.17 t/s 8.20.054.749 I slot print_timing: id 3 | task 8776 | n_gen = 708, tg = 22.67 t/s, tg_3s = 18.17 t/s 8.22.278.342 I slot print_timing: id 0 | task 9445 | n_gen = 100, tg = 22.02 t/s, tg_3s = 22.24 t/s 8.23.084.304 I slot print_timing: id 2 | task 9334 | n_gen = 230, tg = 22.77 t/s, tg_3s = 24.75 t/s 8.23.084.478 I slot print_timing: id 3 | task 8776 | n_gen = 783, tg = 22.85 t/s, tg_3s = 24.75 t/s 8.23.164.891 I slot print_timing: id 1 | task 9468 | n_gen = 100, tg = 24.75 t/s, tg_3s = 25.00 t/s 8.25.019.563 I slot print_timing: id 2 | task 9334 | prompt eval time = 434.01 ms / 66 tokens ( 6.58 ms per token, 152.07 tokens per second) 8.25.019.570 I slot print_timing: id 2 | task 9334 | eval time = 11993.62 ms / 278 tokens ( 43.30 ms per token, 23.10 tokens per second) 8.25.019.571 I slot print_timing: id 2 | task 9334 | total time = 12427.63 ms / 344 tokens 8.25.019.572 I slot print_timing: id 2 | task 9334 | graphs reused = 8742 8.25.019.573 I slot print_timing: id 2 | task 9334 | graph reallocs = 0 / 0 (same size) / (changed size) 8.25.019.644 I slot release: id 2 | task 9334 | stop processing: n_tokens = 1314, truncated = 0 8.25.077.486 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.739 8.25.077.512 I slot launch_slot_: id 2 | task 9617 | processing task, is_child = 0 8.25.455.151 I slot print_timing: id 0 | task 9445 | n_gen = 170, tg = 22.03 t/s, tg_3s = 22.03 t/s 8.26.119.400 I slot print_timing: id 3 | task 8776 | n_gen = 848, tg = 22.74 t/s, tg_3s = 21.42 t/s 8.26.199.230 I slot print_timing: id 1 | task 9468 | n_gen = 165, tg = 23.32 t/s, tg_3s = 21.42 t/s 8.28.467.464 I slot print_timing: id 0 | task 9445 | n_gen = 243, tg = 22.65 t/s, tg_3s = 24.23 t/s 8.29.155.850 I slot print_timing: id 3 | task 8776 | n_gen = 923, tg = 22.88 t/s, tg_3s = 24.70 t/s 8.29.236.319 I slot print_timing: id 1 | task 9468 | n_gen = 240, tg = 23.73 t/s, tg_3s = 24.69 t/s 8.29.560.565 I slot print_timing: id 2 | task 9617 | n_gen = 100, tg = 24.68 t/s, tg_3s = 24.93 t/s 8.30.207.429 I slot print_timing: id 0 | task 9445 | prompt eval time = 390.47 ms / 65 tokens ( 6.01 ms per token, 166.47 tokens per second) 8.30.207.437 I slot print_timing: id 0 | task 9445 | eval time = 12424.79 ms / 286 tokens ( 43.60 ms per token, 22.94 tokens per second) 8.30.207.438 I slot print_timing: id 0 | task 9445 | total time = 12815.26 ms / 351 tokens 8.30.207.439 I slot print_timing: id 0 | task 9445 | graphs reused = 8856 8.30.207.439 I slot print_timing: id 0 | task 9445 | graph reallocs = 0 / 0 (same size) / (changed size) 8.30.207.503 I slot release: id 0 | task 9445 | stop processing: n_tokens = 1321, truncated = 0 8.30.249.657 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.735 8.30.249.683 I slot launch_slot_: id 0 | task 9736 | processing task, is_child = 0 8.32.192.508 I slot print_timing: id 3 | task 8776 | n_gen = 989, tg = 22.80 t/s, tg_3s = 21.73 t/s 8.32.272.787 I slot print_timing: id 1 | task 9468 | n_gen = 306, tg = 23.27 t/s, tg_3s = 21.74 t/s 8.32.564.580 I slot print_timing: id 2 | task 9617 | n_gen = 165, tg = 23.38 t/s, tg_3s = 21.64 t/s 8.33.625.463 I slot print_timing: id 3 | task 8776 | prompt eval time = 444.33 ms / 87 tokens ( 5.11 ms per token, 195.80 tokens per second) 8.33.625.471 I slot print_timing: id 3 | task 8776 | eval time = 44759.23 ms / 1024 tokens ( 43.75 ms per token, 22.86 tokens per second) 8.33.625.472 I slot print_timing: id 3 | task 8776 | total time = 45203.57 ms / 1111 tokens 8.33.625.473 I slot print_timing: id 3 | task 8776 | graphs reused = 8927 8.33.625.474 I slot print_timing: id 3 | task 8776 | graph reallocs = 0 / 0 (same size) / (changed size) 8.33.625.548 I slot release: id 3 | task 8776 | stop processing: n_tokens = 2081, truncated = 0 8.33.667.266 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.931 (> 0.100 thold), f_keep = 0.467 8.33.697.284 I slot launch_slot_: id 3 | task 9812 | processing task, is_child = 0 8.35.100.571 I slot print_timing: id 0 | task 9736 | n_gen = 100, tg = 22.44 t/s, tg_3s = 22.67 t/s 8.35.301.703 I slot print_timing: id 1 | task 9468 | n_gen = 371, tg = 22.93 t/s, tg_3s = 21.46 t/s 8.35.583.093 I slot print_timing: id 2 | task 9617 | n_gen = 230, tg = 22.82 t/s, tg_3s = 21.53 t/s 8.36.994.843 I slot print_timing: id 2 | task 9617 | prompt eval time = 471.19 ms / 83 tokens ( 5.68 ms per token, 176.15 tokens per second) 8.36.994.848 I slot print_timing: id 2 | task 9617 | eval time = 11446.13 ms / 265 tokens ( 43.36 ms per token, 23.06 tokens per second) 8.36.994.849 I slot print_timing: id 2 | task 9617 | total time = 11917.32 ms / 348 tokens 8.36.994.854 I slot print_timing: id 2 | task 9617 | graphs reused = 8996 8.36.994.860 I slot print_timing: id 2 | task 9617 | graph reallocs = 0 / 0 (same size) / (changed size) 8.36.994.929 I slot release: id 2 | task 9617 | stop processing: n_tokens = 1318, truncated = 0 8.37.052.607 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.737 8.37.052.635 I slot launch_slot_: id 2 | task 9887 | processing task, is_child = 0 8.38.129.059 I slot print_timing: id 0 | task 9736 | n_gen = 165, tg = 22.04 t/s, tg_3s = 21.46 t/s 8.38.329.203 I slot print_timing: id 1 | task 9468 | n_gen = 436, tg = 22.70 t/s, tg_3s = 21.47 t/s 8.38.536.004 I slot print_timing: id 3 | task 9812 | n_gen = 100, tg = 22.46 t/s, tg_3s = 22.69 t/s 8.38.695.822 I slot print_timing: id 0 | task 9736 | prompt eval time = 439.12 ms / 82 tokens ( 5.36 ms per token, 186.74 tokens per second) 8.38.695.829 I slot print_timing: id 0 | task 9736 | eval time = 8007.01 ms / 179 tokens ( 44.98 ms per token, 22.23 tokens per second) 8.38.695.830 I slot print_timing: id 0 | task 9736 | total time = 8446.13 ms / 261 tokens 8.38.695.831 I slot print_timing: id 0 | task 9736 | graphs reused = 9023 8.38.695.832 I slot print_timing: id 0 | task 9736 | graph reallocs = 0 / 0 (same size) / (changed size) 8.38.695.904 I slot release: id 0 | task 9736 | stop processing: n_tokens = 1231, truncated = 0 8.38.738.048 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.789 8.38.738.075 I slot launch_slot_: id 0 | task 9920 | processing task, is_child = 0 8.40.439.531 I slot print_timing: id 1 | task 9468 | prompt eval time = 559.21 ms / 130 tokens ( 4.30 ms per token, 232.47 tokens per second) 8.40.439.542 I slot print_timing: id 1 | task 9468 | eval time = 21274.24 ms / 481 tokens ( 44.32 ms per token, 22.56 tokens per second) 8.40.439.543 I slot print_timing: id 1 | task 9468 | total time = 21833.45 ms / 611 tokens 8.40.439.544 I slot print_timing: id 1 | task 9468 | graphs reused = 9056 8.40.439.545 I slot print_timing: id 1 | task 9468 | graph reallocs = 0 / 0 (same size) / (changed size) 8.40.439.619 I slot release: id 1 | task 9468 | stop processing: n_tokens = 1581, truncated = 0 8.40.496.425 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.614 8.40.496.451 I slot launch_slot_: id 1 | task 9957 | processing task, is_child = 0 8.41.570.849 I slot print_timing: id 3 | task 9812 | n_gen = 157, tg = 20.96 t/s, tg_3s = 18.78 t/s 8.42.252.316 I slot print_timing: id 2 | task 9887 | n_gen = 100, tg = 20.94 t/s, tg_3s = 21.15 t/s 8.43.530.673 I slot print_timing: id 0 | task 9920 | n_gen = 100, tg = 22.38 t/s, tg_3s = 22.61 t/s 8.44.570.261 I slot print_timing: id 3 | task 9812 | prompt eval time = 430.84 ms / 73 tokens ( 5.90 ms per token, 169.44 tokens per second) 8.44.570.272 I slot print_timing: id 3 | task 9812 | eval time = 10442.12 ms / 232 tokens ( 45.20 ms per token, 22.12 tokens per second) 8.44.570.273 I slot print_timing: id 3 | task 9812 | total time = 10872.96 ms / 305 tokens 8.44.570.274 I slot print_timing: id 3 | task 9812 | graphs reused = 9143 8.44.570.275 I slot print_timing: id 3 | task 9812 | graph reallocs = 0 / 0 (same size) / (changed size) 8.44.570.345 I slot release: id 3 | task 9812 | stop processing: n_tokens = 1274, truncated = 0 8.44.611.920 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.945 (> 0.100 thold), f_keep = 0.762 8.44.611.946 I slot launch_slot_: id 3 | task 10050 | processing task, is_child = 0 8.45.278.326 I slot print_timing: id 1 | task 9957 | n_gen = 100, tg = 23.17 t/s, tg_3s = 23.40 t/s 8.45.278.456 I slot print_timing: id 2 | task 9887 | n_gen = 168, tg = 21.54 t/s, tg_3s = 22.47 t/s 8.45.971.375 I slot print_timing: id 2 | task 9887 | prompt eval time = 472.15 ms / 83 tokens ( 5.69 ms per token, 175.79 tokens per second) 8.45.971.380 I slot print_timing: id 2 | task 9887 | eval time = 8446.58 ms / 185 tokens ( 45.91 ms per token, 21.78 tokens per second) 8.45.971.381 I slot print_timing: id 2 | task 9887 | total time = 8918.73 ms / 268 tokens 8.45.971.382 I slot print_timing: id 2 | task 9887 | graphs reused = 9165 8.45.971.383 I slot print_timing: id 2 | task 9887 | graph reallocs = 0 / 0 (same size) / (changed size) 8.45.971.461 I slot release: id 2 | task 9887 | stop processing: n_tokens = 1238, truncated = 0 8.46.028.982 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.892 (> 0.100 thold), f_keep = 0.784 8.46.029.009 I slot launch_slot_: id 2 | task 10078 | processing task, is_child = 0 8.46.567.779 I slot print_timing: id 0 | task 9920 | n_gen = 156, tg = 20.78 t/s, tg_3s = 18.44 t/s 8.48.301.703 I slot print_timing: id 1 | task 9957 | n_gen = 163, tg = 22.20 t/s, tg_3s = 20.84 t/s 8.48.381.267 I slot print_timing: id 0 | task 9920 | prompt eval time = 368.91 ms / 55 tokens ( 6.71 ms per token, 149.09 tokens per second) 8.48.381.273 I slot print_timing: id 0 | task 9920 | eval time = 9274.28 ms / 201 tokens ( 46.37 ms per token, 21.57 tokens per second) 8.48.381.274 I slot print_timing: id 0 | task 9920 | total time = 9643.18 ms / 256 tokens 8.48.381.275 I slot print_timing: id 0 | task 9920 | graphs reused = 9208 8.48.381.276 I slot print_timing: id 0 | task 9920 | graph reallocs = 0 / 0 (same size) / (changed size) 8.48.381.341 I slot release: id 0 | task 9920 | stop processing: n_tokens = 1226, truncated = 0 8.48.422.920 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.792 8.48.422.946 I slot launch_slot_: id 0 | task 10127 | processing task, is_child = 0 8.49.820.044 I slot print_timing: id 3 | task 10050 | n_gen = 100, tg = 20.53 t/s, tg_3s = 20.74 t/s 8.50.907.184 I slot print_timing: id 2 | task 10078 | n_gen = 100, tg = 22.82 t/s, tg_3s = 23.05 t/s 8.51.307.423 I slot print_timing: id 1 | task 9957 | n_gen = 229, tg = 22.13 t/s, tg_3s = 21.96 t/s 8.52.833.402 I slot print_timing: id 0 | task 10127 | n_gen = 100, tg = 24.88 t/s, tg_3s = 25.13 t/s 8.52.833.842 I slot print_timing: id 3 | task 10050 | n_gen = 175, tg = 22.21 t/s, tg_3s = 24.89 t/s 8.53.917.681 I slot print_timing: id 2 | task 10078 | n_gen = 175, tg = 23.67 t/s, tg_3s = 24.91 t/s 8.54.319.098 I slot print_timing: id 1 | task 9957 | n_gen = 304, tg = 22.76 t/s, tg_3s = 24.90 t/s 8.55.003.407 I slot print_timing: id 3 | task 10050 | prompt eval time = 386.20 ms / 57 tokens ( 6.78 ms per token, 147.59 tokens per second) 8.55.003.414 I slot print_timing: id 3 | task 10050 | eval time = 10005.25 ms / 229 tokens ( 43.88 ms per token, 22.79 tokens per second) 8.55.003.415 I slot print_timing: id 3 | task 10050 | total time = 10391.45 ms / 286 tokens 8.55.003.416 I slot print_timing: id 3 | task 10050 | graphs reused = 9360 8.55.003.417 I slot print_timing: id 3 | task 10050 | graph reallocs = 0 / 0 (same size) / (changed size) 8.55.003.486 I slot release: id 3 | task 10050 | stop processing: n_tokens = 1256, truncated = 0 8.55.045.282 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.773 8.55.045.312 I slot launch_slot_: id 3 | task 10284 | processing task, is_child = 0 8.55.757.195 I slot print_timing: id 2 | task 10078 | prompt eval time = 539.01 ms / 117 tokens ( 4.61 ms per token, 217.07 tokens per second) 8.55.757.198 I slot print_timing: id 2 | task 10078 | eval time = 9189.17 ms / 212 tokens ( 43.55 ms per token, 22.96 tokens per second) 8.55.757.199 I slot print_timing: id 2 | task 10078 | total time = 9728.17 ms / 329 tokens 8.55.757.200 I slot print_timing: id 2 | task 10078 | graphs reused = 9366 8.55.757.200 I slot print_timing: id 2 | task 10078 | graph reallocs = 0 / 0 (same size) / (changed size) 8.55.757.252 I slot release: id 2 | task 10078 | stop processing: n_tokens = 1299, truncated = 0 8.55.810.220 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.747 8.55.810.239 I slot launch_slot_: id 2 | task 10295 | processing task, is_child = 0 8.56.209.568 I slot print_timing: id 0 | task 10127 | n_gen = 166, tg = 22.43 t/s, tg_3s = 19.55 t/s 8.57.352.819 I slot print_timing: id 1 | task 9957 | n_gen = 360, tg = 21.96 t/s, tg_3s = 18.46 t/s 8.59.238.479 I slot print_timing: id 0 | task 10127 | n_gen = 240, tg = 23.02 t/s, tg_3s = 24.43 t/s 8.59.887.214 I slot print_timing: id 0 | task 10127 | prompt eval time = 431.26 ms / 86 tokens ( 5.01 ms per token, 199.41 tokens per second) 8.59.887.223 I slot print_timing: id 0 | task 10127 | eval time = 11033.00 ms / 256 tokens ( 43.27 ms per token, 23.11 tokens per second) 8.59.887.224 I slot print_timing: id 0 | task 10127 | total time = 11464.26 ms / 342 tokens 8.59.887.224 I slot print_timing: id 0 | task 10127 | graphs reused = 9453 8.59.887.225 I slot print_timing: id 0 | task 10127 | graph reallocs = 0 / 0 (same size) / (changed size) 8.59.887.300 I slot release: id 0 | task 10127 | stop processing: n_tokens = 1312, truncated = 0 8.59.887.814 I slot print_timing: id 3 | task 10284 | n_gen = 100, tg = 22.45 t/s, tg_3s = 22.68 t/s 8.59.929.495 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.943 (> 0.100 thold), f_keep = 0.740 8.59.929.522 I slot launch_slot_: id 0 | task 10388 | processing task, is_child = 0 9.00.390.380 I slot print_timing: id 1 | task 9957 | n_gen = 428, tg = 22.03 t/s, tg_3s = 22.39 t/s 9.00.601.322 I slot print_timing: id 2 | task 10295 | n_gen = 100, tg = 23.03 t/s, tg_3s = 23.26 t/s 9.02.897.203 I slot print_timing: id 3 | task 10284 | n_gen = 167, tg = 22.38 t/s, tg_3s = 22.26 t/s 9.03.420.531 I slot print_timing: id 1 | task 9957 | n_gen = 503, tg = 22.40 t/s, tg_3s = 24.75 t/s 9.03.622.162 I slot print_timing: id 2 | task 10295 | n_gen = 175, tg = 23.77 t/s, tg_3s = 24.83 t/s 9.04.305.954 I slot print_timing: id 0 | task 10388 | n_gen = 100, tg = 24.76 t/s, tg_3s = 25.01 t/s 9.04.627.930 I slot print_timing: id 2 | task 10295 | prompt eval time = 492.22 ms / 101 tokens ( 4.87 ms per token, 205.19 tokens per second) 9.04.627.935 I slot print_timing: id 2 | task 10295 | eval time = 8325.46 ms / 200 tokens ( 41.84 ms per token, 23.90 tokens per second) 9.04.627.936 I slot print_timing: id 2 | task 10295 | total time = 8817.68 ms / 301 tokens 9.04.627.937 I slot print_timing: id 2 | task 10295 | graphs reused = 9559 9.04.627.938 I slot print_timing: id 2 | task 10295 | graph reallocs = 0 / 0 (same size) / (changed size) 9.04.628.007 I slot release: id 2 | task 10295 | stop processing: n_tokens = 1271, truncated = 0 9.04.685.542 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.764 9.04.685.568 I slot launch_slot_: id 2 | task 10499 | processing task, is_child = 0 9.05.924.517 I slot print_timing: id 3 | task 10284 | n_gen = 232, tg = 22.11 t/s, tg_3s = 21.47 t/s 9.06.004.569 I slot print_timing: id 0 | task 10388 | prompt eval time = 378.45 ms / 59 tokens ( 6.41 ms per token, 155.90 tokens per second) 9.06.004.576 I slot print_timing: id 0 | task 10388 | eval time = 5696.59 ms / 132 tokens ( 43.49 ms per token, 23.00 tokens per second) 9.06.004.577 I slot print_timing: id 0 | task 10388 | total time = 6075.04 ms / 191 tokens 9.06.004.578 I slot print_timing: id 0 | task 10388 | graphs reused = 9579 9.06.004.579 I slot print_timing: id 0 | task 10388 | graph reallocs = 0 / 0 (same size) / (changed size) 9.06.004.647 I slot release: id 0 | task 10388 | stop processing: n_tokens = 1161, truncated = 0 9.06.047.017 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.836 9.06.047.041 I slot launch_slot_: id 0 | task 10524 | processing task, is_child = 0 9.06.450.562 I slot print_timing: id 1 | task 9957 | n_gen = 559, tg = 21.93 t/s, tg_3s = 18.48 t/s 9.08.947.875 I slot print_timing: id 3 | task 10284 | n_gen = 297, tg = 21.98 t/s, tg_3s = 21.50 t/s 9.09.471.686 I slot print_timing: id 1 | task 9957 | n_gen = 633, tg = 22.20 t/s, tg_3s = 24.49 t/s 9.09.552.803 I slot print_timing: id 2 | task 10499 | n_gen = 100, tg = 22.53 t/s, tg_3s = 22.76 t/s 9.10.521.147 I slot print_timing: id 0 | task 10524 | n_gen = 100, tg = 24.80 t/s, tg_3s = 25.05 t/s 9.11.610.528 I slot print_timing: id 3 | task 10284 | prompt eval time = 433.05 ms / 78 tokens ( 5.55 ms per token, 180.12 tokens per second) 9.11.610.534 I slot print_timing: id 3 | task 10284 | eval time = 16132.15 ms / 363 tokens ( 44.56 ms per token, 22.44 tokens per second) 9.11.610.535 I slot print_timing: id 3 | task 10284 | total time = 16565.20 ms / 441 tokens 9.11.610.536 I slot print_timing: id 3 | task 10284 | graphs reused = 9705 9.11.610.537 I slot print_timing: id 3 | task 10284 | graph reallocs = 0 / 0 (same size) / (changed size) 9.11.610.612 I slot release: id 3 | task 10284 | stop processing: n_tokens = 1411, truncated = 0 9.11.652.323 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.940 (> 0.100 thold), f_keep = 0.688 9.11.652.353 I slot launch_slot_: id 3 | task 10654 | processing task, is_child = 0 9.12.486.724 I slot print_timing: id 1 | task 9957 | n_gen = 700, tg = 22.20 t/s, tg_3s = 22.22 t/s 9.12.576.423 I slot print_timing: id 2 | task 10499 | n_gen = 167, tg = 22.38 t/s, tg_3s = 22.16 t/s 9.13.421.290 I slot print_timing: id 2 | task 10499 | prompt eval time = 473.53 ms / 85 tokens ( 5.57 ms per token, 179.50 tokens per second) 9.13.421.297 I slot print_timing: id 2 | task 10499 | eval time = 8262.18 ms / 188 tokens ( 44.18 ms per token, 22.63 tokens per second) 9.13.421.298 I slot print_timing: id 2 | task 10499 | total time = 8735.71 ms / 273 tokens 9.13.421.299 I slot print_timing: id 2 | task 10499 | graphs reused = 9738 9.13.421.300 I slot print_timing: id 2 | task 10499 | graph reallocs = 0 / 0 (same size) / (changed size) 9.13.421.375 I slot release: id 2 | task 10499 | stop processing: n_tokens = 1243, truncated = 0 9.13.478.845 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.781 9.13.478.871 I slot launch_slot_: id 2 | task 10692 | processing task, is_child = 0 9.13.817.994 I slot print_timing: id 0 | task 10524 | n_gen = 166, tg = 22.64 t/s, tg_3s = 20.02 t/s 9.15.486.863 I slot print_timing: id 1 | task 9957 | n_gen = 765, tg = 22.16 t/s, tg_3s = 21.67 t/s 9.16.414.634 I slot print_timing: id 3 | task 10654 | n_gen = 100, tg = 22.66 t/s, tg_3s = 22.89 t/s 9.16.856.793 I slot print_timing: id 0 | task 10524 | n_gen = 240, tg = 23.14 t/s, tg_3s = 24.35 t/s 9.17.906.545 I slot print_timing: id 2 | task 10692 | n_gen = 100, tg = 24.77 t/s, tg_3s = 25.03 t/s 9.18.511.444 I slot print_timing: id 1 | task 9957 | n_gen = 840, tg = 22.37 t/s, tg_3s = 24.80 t/s 9.19.441.896 I slot print_timing: id 3 | task 10654 | n_gen = 175, tg = 23.52 t/s, tg_3s = 24.77 t/s 9.19.886.440 I slot print_timing: id 0 | task 10524 | n_gen = 315, tg = 23.51 t/s, tg_3s = 24.76 t/s 9.20.937.367 I slot print_timing: id 2 | task 10692 | n_gen = 175, tg = 24.76 t/s, tg_3s = 24.75 t/s 9.21.544.088 I slot print_timing: id 1 | task 9957 | n_gen = 915, tg = 22.55 t/s, tg_3s = 24.73 t/s 9.21.544.276 I slot print_timing: id 2 | task 10692 | prompt eval time = 431.67 ms / 65 tokens ( 6.64 ms per token, 150.58 tokens per second) 9.21.544.280 I slot print_timing: id 2 | task 10692 | eval time = 7633.73 ms / 190 tokens ( 40.39 ms per token, 24.76 tokens per second) 9.21.544.281 I slot print_timing: id 2 | task 10692 | total time = 8065.40 ms / 255 tokens 9.21.544.282 I slot print_timing: id 2 | task 10692 | graphs reused = 9926 9.21.544.282 I slot print_timing: id 2 | task 10692 | graph reallocs = 0 / 0 (same size) / (changed size) 9.21.544.357 I slot release: id 2 | task 10692 | stop processing: n_tokens = 1225, truncated = 0 9.21.602.422 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.793 9.21.602.453 I slot launch_slot_: id 2 | task 10885 | processing task, is_child = 0 9.22.448.052 I slot print_timing: id 3 | task 10654 | n_gen = 239, tg = 22.88 t/s, tg_3s = 21.29 t/s 9.22.891.317 I slot print_timing: id 0 | task 10524 | n_gen = 379, tg = 23.10 t/s, tg_3s = 21.30 t/s 9.24.548.518 I slot print_timing: id 1 | task 9957 | n_gen = 979, tg = 22.46 t/s, tg_3s = 21.30 t/s 9.25.451.725 I slot print_timing: id 3 | task 10654 | n_gen = 313, tg = 23.27 t/s, tg_3s = 24.64 t/s 9.25.899.729 I slot print_timing: id 0 | task 10524 | n_gen = 453, tg = 23.33 t/s, tg_3s = 24.60 t/s 9.26.104.400 I slot print_timing: id 2 | task 10885 | n_gen = 100, tg = 24.58 t/s, tg_3s = 24.83 t/s 9.26.390.807 I slot print_timing: id 1 | task 9957 | prompt eval time = 508.65 ms / 96 tokens ( 5.30 ms per token, 188.73 tokens per second) 9.26.390.815 I slot print_timing: id 1 | task 9957 | eval time = 45385.69 ms / 1024 tokens ( 44.37 ms per token, 22.54 tokens per second) 9.26.390.816 I slot print_timing: id 1 | task 9957 | total time = 45894.35 ms / 1120 tokens 9.26.390.817 I slot print_timing: id 1 | task 9957 | graphs reused = 10030 9.26.390.818 I slot print_timing: id 1 | task 9957 | graph reallocs = 0 / 0 (same size) / (changed size) 9.26.390.895 I slot release: id 1 | task 9957 | stop processing: n_tokens = 2090, truncated = 0 9.26.447.767 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.916 (> 0.100 thold), f_keep = 0.465 9.26.481.982 I slot launch_slot_: id 1 | task 10995 | processing task, is_child = 0 9.28.480.932 I slot print_timing: id 3 | task 10654 | n_gen = 376, tg = 22.82 t/s, tg_3s = 20.80 t/s 9.28.922.897 I slot print_timing: id 0 | task 10524 | n_gen = 516, tg = 23.00 t/s, tg_3s = 20.84 t/s 9.29.124.514 I slot print_timing: id 2 | task 10885 | n_gen = 163, tg = 22.99 t/s, tg_3s = 20.86 t/s 9.30.980.414 I slot print_timing: id 1 | task 10995 | n_gen = 100, tg = 24.74 t/s, tg_3s = 24.99 t/s 9.31.384.890 I slot print_timing: id 3 | task 10654 | prompt eval time = 393.08 ms / 62 tokens ( 6.34 ms per token, 157.73 tokens per second) 9.31.384.897 I slot print_timing: id 3 | task 10654 | eval time = 19339.45 ms / 448 tokens ( 43.26 ms per token, 23.11 tokens per second) 9.31.384.898 I slot print_timing: id 3 | task 10654 | total time = 19732.52 ms / 510 tokens 9.31.384.899 I slot print_timing: id 3 | task 10654 | graphs reused = 10138 9.31.384.900 I slot print_timing: id 3 | task 10654 | graph reallocs = 0 / 0 (same size) / (changed size) 9.31.384.975 I slot release: id 3 | task 10654 | stop processing: n_tokens = 1480, truncated = 0 9.31.426.705 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.656 9.31.426.729 I slot launch_slot_: id 3 | task 11108 | processing task, is_child = 0 9.31.946.576 I slot print_timing: id 0 | task 10524 | n_gen = 583, tg = 22.90 t/s, tg_3s = 22.16 t/s 9.32.146.496 I slot print_timing: id 2 | task 10885 | n_gen = 230, tg = 22.74 t/s, tg_3s = 22.17 t/s 9.34.004.299 I slot print_timing: id 1 | task 10995 | n_gen = 167, tg = 23.63 t/s, tg_3s = 22.16 t/s 9.34.972.313 I slot print_timing: id 0 | task 10524 | n_gen = 658, tg = 23.10 t/s, tg_3s = 24.79 t/s 9.35.174.375 I slot print_timing: id 2 | task 10885 | n_gen = 305, tg = 23.21 t/s, tg_3s = 24.77 t/s 9.35.821.241 I slot print_timing: id 3 | task 11108 | n_gen = 100, tg = 24.77 t/s, tg_3s = 25.02 t/s 9.37.029.199 I slot print_timing: id 1 | task 10995 | n_gen = 242, tg = 23.98 t/s, tg_3s = 24.79 t/s 9.38.005.468 I slot print_timing: id 0 | task 10524 | n_gen = 733, tg = 23.26 t/s, tg_3s = 24.73 t/s 9.38.207.981 I slot print_timing: id 2 | task 10885 | n_gen = 380, tg = 23.49 t/s, tg_3s = 24.72 t/s 9.38.853.251 I slot print_timing: id 3 | task 11108 | n_gen = 175, tg = 24.76 t/s, tg_3s = 24.74 t/s 9.39.863.032 I slot print_timing: id 1 | task 10995 | prompt eval time = 497.27 ms / 90 tokens ( 5.53 ms per token, 180.99 tokens per second) 9.39.863.037 I slot print_timing: id 1 | task 10995 | eval time = 12883.76 ms / 312 tokens ( 41.43 ms per token, 24.14 tokens per second) 9.39.863.038 I slot print_timing: id 1 | task 10995 | total time = 13381.04 ms / 402 tokens 9.39.863.039 I slot print_timing: id 1 | task 10995 | graphs reused = 10335 9.39.863.040 I slot print_timing: id 1 | task 10995 | graph reallocs = 0 / 0 (same size) / (changed size) 9.39.863.110 I slot release: id 1 | task 10995 | stop processing: n_tokens = 1371, truncated = 0 9.39.919.916 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.918 (> 0.100 thold), f_keep = 0.708 9.39.919.948 I slot launch_slot_: id 1 | task 11311 | processing task, is_child = 0 9.41.026.267 I slot print_timing: id 0 | task 10524 | n_gen = 797, tg = 23.07 t/s, tg_3s = 21.19 t/s 9.41.228.570 I slot print_timing: id 2 | task 10885 | n_gen = 444, tg = 23.13 t/s, tg_3s = 21.19 t/s 9.41.552.400 I slot print_timing: id 3 | task 11108 | prompt eval time = 398.11 ms / 67 tokens ( 5.94 ms per token, 168.29 tokens per second) 9.41.552.405 I slot print_timing: id 3 | task 11108 | eval time = 9727.55 ms / 231 tokens ( 42.29 ms per token, 23.64 tokens per second) 9.41.552.406 I slot print_timing: id 3 | task 11108 | total time = 10125.66 ms / 298 tokens 9.41.552.407 I slot print_timing: id 3 | task 11108 | graphs reused = 10362 9.41.552.408 I slot print_timing: id 3 | task 11108 | graph reallocs = 0 / 0 (same size) / (changed size) 9.41.552.483 I slot release: id 3 | task 11108 | stop processing: n_tokens = 1268, truncated = 0 9.41.594.540 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.766 9.41.594.563 I slot launch_slot_: id 3 | task 11343 | processing task, is_child = 0 9.44.048.350 I slot print_timing: id 0 | task 10524 | n_gen = 862, tg = 22.95 t/s, tg_3s = 21.51 t/s 9.44.250.271 I slot print_timing: id 2 | task 10885 | n_gen = 509, tg = 22.91 t/s, tg_3s = 21.51 t/s 9.44.817.124 I slot print_timing: id 1 | task 11311 | n_gen = 100, tg = 22.48 t/s, tg_3s = 22.70 t/s 9.46.071.416 I slot print_timing: id 3 | task 11343 | n_gen = 100, tg = 24.70 t/s, tg_3s = 24.95 t/s 9.47.081.602 I slot print_timing: id 0 | task 10524 | n_gen = 937, tg = 23.08 t/s, tg_3s = 24.73 t/s 9.47.284.579 I slot print_timing: id 2 | task 10885 | n_gen = 584, tg = 23.13 t/s, tg_3s = 24.72 t/s 9.47.851.858 I slot print_timing: id 1 | task 11311 | n_gen = 175, tg = 23.39 t/s, tg_3s = 24.71 t/s 9.49.078.002 I slot print_timing: id 3 | task 11343 | n_gen = 174, tg = 24.66 t/s, tg_3s = 24.61 t/s 9.50.100.587 I slot print_timing: id 0 | task 10524 | n_gen = 1011, tg = 23.18 t/s, tg_3s = 24.51 t/s 9.50.305.775 I slot print_timing: id 2 | task 10885 | n_gen = 658, tg = 23.27 t/s, tg_3s = 24.49 t/s 9.50.633.423 I slot print_timing: id 0 | task 10524 | prompt eval time = 482.29 ms / 101 tokens ( 4.78 ms per token, 209.42 tokens per second) 9.50.633.430 I slot print_timing: id 0 | task 10524 | eval time = 44104.08 ms / 1024 tokens ( 43.11 ms per token, 23.20 tokens per second) 9.50.633.431 I slot print_timing: id 0 | task 10524 | total time = 44586.37 ms / 1125 tokens 9.50.633.432 I slot print_timing: id 0 | task 10524 | graphs reused = 10571 9.50.633.433 I slot print_timing: id 0 | task 10524 | graph reallocs = 0 / 0 (same size) / (changed size) 9.50.633.500 I slot release: id 0 | task 10524 | stop processing: n_tokens = 2095, truncated = 0 9.50.675.460 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.463 9.50.704.543 I slot launch_slot_: id 0 | task 11558 | processing task, is_child = 0 9.51.059.929 I slot print_timing: id 1 | task 11311 | n_gen = 245, tg = 22.92 t/s, tg_3s = 21.82 t/s 9.52.110.738 I slot print_timing: id 3 | task 11343 | n_gen = 239, tg = 23.69 t/s, tg_3s = 21.43 t/s 9.53.319.998 I slot print_timing: id 2 | task 10885 | n_gen = 723, tg = 23.11 t/s, tg_3s = 21.56 t/s 9.54.092.034 I slot print_timing: id 1 | task 11311 | n_gen = 319, tg = 23.25 t/s, tg_3s = 24.41 t/s 9.54.253.754 I slot print_timing: id 2 | task 10885 | prompt eval time = 474.26 ms / 86 tokens ( 5.51 ms per token, 181.34 tokens per second) 9.54.253.762 I slot print_timing: id 2 | task 10885 | eval time = 32177.04 ms / 746 tokens ( 43.19 ms per token, 23.15 tokens per second) 9.54.253.763 I slot print_timing: id 2 | task 10885 | total time = 32651.29 ms / 832 tokens 9.54.253.763 I slot print_timing: id 2 | task 10885 | graphs reused = 10647 9.54.253.764 I slot print_timing: id 2 | task 10885 | graph reallocs = 0 / 0 (same size) / (changed size) 9.54.253.846 I slot release: id 2 | task 10885 | stop processing: n_tokens = 1802, truncated = 0 9.54.311.669 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.539 9.54.311.694 I slot launch_slot_: id 2 | task 11639 | processing task, is_child = 0 9.55.117.507 I slot print_timing: id 3 | task 11343 | n_gen = 303, tg = 23.14 t/s, tg_3s = 21.29 t/s 9.55.558.439 I slot print_timing: id 0 | task 11558 | n_gen = 100, tg = 22.40 t/s, tg_3s = 22.63 t/s 9.57.123.374 I slot print_timing: id 1 | task 11311 | n_gen = 384, tg = 22.92 t/s, tg_3s = 21.44 t/s 9.58.127.992 I slot print_timing: id 3 | task 11343 | n_gen = 378, tg = 23.47 t/s, tg_3s = 24.91 t/s 9.58.570.730 I slot print_timing: id 0 | task 11558 | n_gen = 175, tg = 23.41 t/s, tg_3s = 24.90 t/s 9.58.771.662 I slot print_timing: id 2 | task 11639 | n_gen = 100, tg = 24.86 t/s, tg_3s = 25.11 t/s 10.00.148.539 I slot print_timing: id 1 | task 11311 | n_gen = 459, tg = 23.21 t/s, tg_3s = 24.79 t/s 10.00.593.672 I slot print_timing: id 1 | task 11311 | prompt eval time = 492.62 ms / 87 tokens ( 5.66 ms per token, 176.61 tokens per second) 10.00.593.677 I slot print_timing: id 1 | task 11311 | eval time = 20181.09 ms / 470 tokens ( 43.03 ms per token, 23.24 tokens per second) 10.00.593.678 I slot print_timing: id 1 | task 11311 | total time = 20673.71 ms / 557 tokens 10.00.593.679 I slot print_timing: id 1 | task 11311 | graphs reused = 10789 10.00.593.680 I slot print_timing: id 1 | task 11311 | graph reallocs = 0 / 0 (same size) / (changed size) 10.00.593.757 I slot release: id 1 | task 11311 | stop processing: n_tokens = 1527, truncated = 0 10.00.650.880 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.636 10.00.650.903 I slot launch_slot_: id 1 | task 11787 | processing task, is_child = 0 10.01.157.179 I slot print_timing: id 3 | task 11343 | n_gen = 443, tg = 23.15 t/s, tg_3s = 21.46 t/s 10.01.597.260 I slot print_timing: id 0 | task 11558 | n_gen = 240, tg = 22.85 t/s, tg_3s = 21.48 t/s 10.01.807.045 I slot print_timing: id 2 | task 11639 | n_gen = 165, tg = 23.37 t/s, tg_3s = 21.41 t/s 10.04.192.665 I slot print_timing: id 3 | task 11343 | n_gen = 518, tg = 23.36 t/s, tg_3s = 24.71 t/s 10.04.514.400 I slot print_timing: id 0 | task 11558 | prompt eval time = 434.41 ms / 94 tokens ( 4.62 ms per token, 216.39 tokens per second) 10.04.514.405 I slot print_timing: id 0 | task 11558 | eval time = 13375.43 ms / 312 tokens ( 43.01 ms per token, 23.25 tokens per second) 10.04.514.406 I slot print_timing: id 0 | task 11558 | total time = 13809.84 ms / 406 tokens 10.04.514.407 I slot print_timing: id 0 | task 11558 | graphs reused = 10871 10.04.514.408 I slot print_timing: id 0 | task 11558 | graph reallocs = 0 / 0 (same size) / (changed size) 10.04.514.479 I slot release: id 0 | task 11558 | stop processing: n_tokens = 1375, truncated = 0 10.04.556.869 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.706 10.04.556.895 I slot launch_slot_: id 0 | task 11875 | processing task, is_child = 0 10.04.863.963 I slot print_timing: id 2 | task 11639 | n_gen = 234, tg = 23.13 t/s, tg_3s = 22.57 t/s 10.05.425.562 I slot print_timing: id 1 | task 11787 | n_gen = 100, tg = 22.96 t/s, tg_3s = 23.19 t/s 10.07.203.865 I slot print_timing: id 3 | task 11343 | n_gen = 585, tg = 23.23 t/s, tg_3s = 22.25 t/s 10.07.888.626 I slot print_timing: id 2 | task 11639 | n_gen = 308, tg = 23.44 t/s, tg_3s = 24.47 t/s 10.08.452.821 I slot print_timing: id 1 | task 11787 | n_gen = 175, tg = 23.71 t/s, tg_3s = 24.77 t/s 10.08.935.314 I slot print_timing: id 0 | task 11875 | n_gen = 100, tg = 24.80 t/s, tg_3s = 25.05 t/s 10.09.742.347 I slot print_timing: id 2 | task 11639 | prompt eval time = 476.86 ms / 86 tokens ( 5.54 ms per token, 180.35 tokens per second) 10.09.742.352 I slot print_timing: id 2 | task 11639 | eval time = 14953.78 ms / 354 tokens ( 42.36 ms per token, 23.61 tokens per second) 10.09.742.353 I slot print_timing: id 2 | task 11639 | total time = 15430.64 ms / 440 tokens 10.09.742.354 I slot print_timing: id 2 | task 11639 | graphs reused = 10990 10.09.742.355 I slot print_timing: id 2 | task 11639 | graph reallocs = 0 / 0 (same size) / (changed size) 10.09.742.430 I slot release: id 2 | task 11639 | stop processing: n_tokens = 1409, truncated = 0 10.09.799.798 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.892 (> 0.100 thold), f_keep = 0.689 10.09.799.826 I slot launch_slot_: id 2 | task 11998 | processing task, is_child = 0 10.10.240.997 I slot print_timing: id 3 | task 11343 | n_gen = 650, tg = 23.03 t/s, tg_3s = 21.40 t/s 10.11.468.421 I slot print_timing: id 1 | task 11787 | n_gen = 238, tg = 22.89 t/s, tg_3s = 20.89 t/s 10.11.951.619 I slot print_timing: id 0 | task 11875 | n_gen = 163, tg = 23.11 t/s, tg_3s = 20.89 t/s 10.13.248.855 I slot print_timing: id 3 | task 11343 | n_gen = 723, tg = 23.15 t/s, tg_3s = 24.27 t/s 10.14.338.068 I slot print_timing: id 2 | task 11998 | n_gen = 100, tg = 24.72 t/s, tg_3s = 24.97 t/s 10.14.499.790 I slot print_timing: id 1 | task 11787 | n_gen = 313, tg = 23.31 t/s, tg_3s = 24.74 t/s 10.14.984.693 I slot print_timing: id 0 | task 11875 | n_gen = 238, tg = 23.60 t/s, tg_3s = 24.73 t/s 10.16.279.379 I slot print_timing: id 3 | task 11343 | n_gen = 798, tg = 23.29 t/s, tg_3s = 24.75 t/s 10.17.371.911 I slot print_timing: id 2 | task 11998 | n_gen = 175, tg = 24.72 t/s, tg_3s = 24.72 t/s 10.17.412.305 I slot print_timing: id 1 | task 11787 | prompt eval time = 462.85 ms / 70 tokens ( 6.61 ms per token, 151.24 tokens per second) 10.17.412.309 I slot print_timing: id 1 | task 11787 | eval time = 16298.55 ms / 385 tokens ( 42.44 ms per token, 23.56 tokens per second) 10.17.412.312 I slot print_timing: id 1 | task 11787 | total time = 16761.40 ms / 455 tokens 10.17.412.312 I slot print_timing: id 1 | task 11787 | graphs reused = 11163 10.17.412.313 I slot print_timing: id 1 | task 11787 | graph reallocs = 0 / 0 (same size) / (changed size) 10.17.412.377 I slot release: id 1 | task 11787 | stop processing: n_tokens = 1425, truncated = 0 10.17.469.384 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.945 (> 0.100 thold), f_keep = 0.681 10.17.469.411 I slot launch_slot_: id 1 | task 12177 | processing task, is_child = 0 10.18.008.681 I slot print_timing: id 0 | task 11875 | n_gen = 304, tg = 23.19 t/s, tg_3s = 21.83 t/s 10.18.375.236 I slot print_timing: id 0 | task 11875 | prompt eval time = 385.77 ms / 63 tokens ( 6.12 ms per token, 163.31 tokens per second) 10.18.375.244 I slot print_timing: id 0 | task 11875 | eval time = 13432.56 ms / 313 tokens ( 43.05 ms per token, 23.23 tokens per second) 10.18.375.245 I slot print_timing: id 0 | task 11875 | total time = 13818.33 ms / 376 tokens 10.18.375.246 I slot print_timing: id 0 | task 11875 | graphs reused = 11174 10.18.375.247 I slot print_timing: id 0 | task 11875 | graph reallocs = 0 / 0 (same size) / (changed size) 10.18.375.315 I slot release: id 0 | task 11875 | stop processing: n_tokens = 1346, truncated = 0 10.18.418.053 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.721 10.18.418.075 I slot launch_slot_: id 0 | task 12193 | processing task, is_child = 0 10.19.308.792 I slot print_timing: id 3 | task 11343 | n_gen = 856, tg = 22.96 t/s, tg_3s = 19.15 t/s 10.20.398.881 I slot print_timing: id 2 | task 11998 | n_gen = 233, tg = 23.05 t/s, tg_3s = 19.16 t/s 10.22.214.830 I slot print_timing: id 1 | task 12177 | n_gen = 100, tg = 22.87 t/s, tg_3s = 23.10 t/s 10.22.336.031 I slot print_timing: id 3 | task 11343 | n_gen = 931, tg = 23.09 t/s, tg_3s = 24.78 t/s 10.22.818.587 I slot print_timing: id 0 | task 12193 | n_gen = 100, tg = 24.76 t/s, tg_3s = 25.01 t/s 10.22.818.743 I slot print_timing: id 1 | task 12177 | prompt eval time = 415.84 ms / 56 tokens ( 7.43 ms per token, 134.67 tokens per second) 10.22.818.746 I slot print_timing: id 1 | task 12177 | eval time = 4933.49 ms / 115 tokens ( 43.28 ms per token, 23.11 tokens per second) 10.22.818.747 I slot print_timing: id 1 | task 12177 | total time = 5349.33 ms / 171 tokens 10.22.818.748 I slot print_timing: id 1 | task 12177 | graphs reused = 11273 10.22.818.749 I slot print_timing: id 1 | task 12177 | graph reallocs = 0 / 0 (same size) / (changed size) 10.22.818.819 I slot release: id 1 | task 12177 | stop processing: n_tokens = 1141, truncated = 0 10.22.874.958 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.941 (> 0.100 thold), f_keep = 0.851 10.22.874.995 I slot launch_slot_: id 1 | task 12296 | processing task, is_child = 0 10.23.428.184 I slot print_timing: id 2 | task 11998 | n_gen = 299, tg = 22.76 t/s, tg_3s = 21.79 t/s 10.25.341.893 I slot print_timing: id 3 | task 11343 | n_gen = 996, tg = 22.99 t/s, tg_3s = 21.62 t/s 10.25.832.188 I slot print_timing: id 0 | task 12193 | n_gen = 165, tg = 23.39 t/s, tg_3s = 21.57 t/s 10.26.447.576 I slot print_timing: id 2 | task 11998 | n_gen = 373, tg = 23.09 t/s, tg_3s = 24.51 t/s 10.26.488.489 I slot print_timing: id 3 | task 11343 | prompt eval time = 469.21 ms / 101 tokens ( 4.65 ms per token, 215.26 tokens per second) 10.26.488.497 I slot print_timing: id 3 | task 11343 | eval time = 44424.71 ms / 1024 tokens ( 43.43 ms per token, 23.03 tokens per second) 10.26.488.498 I slot print_timing: id 3 | task 11343 | total time = 44893.92 ms / 1125 tokens 10.26.488.499 I slot print_timing: id 3 | task 11343 | graphs reused = 11349 10.26.488.499 I slot print_timing: id 3 | task 11343 | graph reallocs = 0 / 0 (same size) / (changed size) 10.26.488.578 I slot release: id 3 | task 11343 | stop processing: n_tokens = 2095, truncated = 0 10.26.530.258 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.463 10.26.559.922 I slot launch_slot_: id 3 | task 12378 | processing task, is_child = 0 10.27.733.476 I slot print_timing: id 1 | task 12296 | n_gen = 100, tg = 22.35 t/s, tg_3s = 22.58 t/s 10.28.736.680 I slot print_timing: id 1 | task 12296 | prompt eval time = 429.52 ms / 61 tokens ( 7.04 ms per token, 142.02 tokens per second) 10.28.736.687 I slot print_timing: id 1 | task 12296 | eval time = 5432.16 ms / 125 tokens ( 43.81 ms per token, 22.83 tokens per second) 10.28.736.688 I slot print_timing: id 1 | task 12296 | total time = 5861.68 ms / 186 tokens 10.28.736.689 I slot print_timing: id 1 | task 12296 | graphs reused = 11390 10.28.736.690 I slot print_timing: id 1 | task 12296 | graph reallocs = 0 / 0 (same size) / (changed size) 10.28.736.761 I slot release: id 1 | task 12296 | stop processing: n_tokens = 1156, truncated = 0 10.28.793.722 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.840 10.28.793.749 I slot launch_slot_: id 1 | task 12425 | processing task, is_child = 0 10.29.188.723 I slot print_timing: id 0 | task 12193 | n_gen = 229, tg = 21.99 t/s, tg_3s = 19.07 t/s 10.29.451.053 I slot print_timing: id 2 | task 11998 | n_gen = 427, tg = 22.28 t/s, tg_3s = 17.98 t/s 10.31.437.775 I slot print_timing: id 3 | task 12378 | n_gen = 100, tg = 22.29 t/s, tg_3s = 22.52 t/s 10.32.204.421 I slot print_timing: id 0 | task 12193 | n_gen = 302, tg = 22.49 t/s, tg_3s = 24.21 t/s 10.32.486.528 I slot print_timing: id 2 | task 11998 | n_gen = 502, tg = 22.62 t/s, tg_3s = 24.71 t/s 10.33.292.169 I slot print_timing: id 1 | task 12425 | n_gen = 100, tg = 24.73 t/s, tg_3s = 24.98 t/s 10.34.464.076 I slot print_timing: id 3 | task 12378 | n_gen = 175, tg = 23.30 t/s, tg_3s = 24.78 t/s 10.35.229.215 I slot print_timing: id 0 | task 12193 | n_gen = 377, tg = 22.91 t/s, tg_3s = 24.80 t/s 10.35.511.914 I slot print_timing: id 2 | task 11998 | n_gen = 577, tg = 22.88 t/s, tg_3s = 24.79 t/s 10.36.318.190 I slot print_timing: id 1 | task 12425 | n_gen = 175, tg = 24.75 t/s, tg_3s = 24.79 t/s 10.37.084.168 I slot print_timing: id 2 | task 11998 | prompt eval time = 534.04 ms / 118 tokens ( 4.53 ms per token, 220.96 tokens per second) 10.37.084.174 I slot print_timing: id 2 | task 11998 | eval time = 26750.29 ms / 616 tokens ( 43.50 ms per token, 22.99 tokens per second) 10.37.084.175 I slot print_timing: id 2 | task 11998 | total time = 27284.33 ms / 734 tokens 10.37.084.176 I slot print_timing: id 2 | task 11998 | graphs reused = 11581 10.37.084.177 I slot print_timing: id 2 | task 11998 | graph reallocs = 0 / 0 (same size) / (changed size) 10.37.084.252 I slot release: id 2 | task 11998 | stop processing: n_tokens = 1704, truncated = 0 10.37.141.810 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.943 (> 0.100 thold), f_keep = 0.570 10.37.141.842 I slot launch_slot_: id 2 | task 12622 | processing task, is_child = 0 10.37.554.781 I slot print_timing: id 3 | task 12378 | n_gen = 243, tg = 22.92 t/s, tg_3s = 22.00 t/s 10.37.757.986 I slot print_timing: id 3 | task 12378 | prompt eval time = 437.13 ms / 84 tokens ( 5.20 ms per token, 192.16 tokens per second) 10.37.757.992 I slot print_timing: id 3 | task 12378 | eval time = 10760.92 ms / 248 tokens ( 43.57 ms per token, 22.95 tokens per second) 10.37.757.993 I slot print_timing: id 3 | task 12378 | total time = 11198.05 ms / 332 tokens 10.37.757.994 I slot print_timing: id 3 | task 12378 | graphs reused = 11585 10.37.757.995 I slot print_timing: id 3 | task 12378 | graph reallocs = 0 / 0 (same size) / (changed size) 10.37.758.079 I slot release: id 3 | task 12378 | stop processing: n_tokens = 1301, truncated = 0 10.37.800.645 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.875 (> 0.100 thold), f_keep = 0.746 10.37.800.675 I slot launch_slot_: id 3 | task 12631 | processing task, is_child = 0 10.38.252.793 I slot print_timing: id 0 | task 12193 | n_gen = 433, tg = 22.23 t/s, tg_3s = 18.52 t/s 10.39.221.331 I slot print_timing: id 0 | task 12193 | prompt eval time = 401.65 ms / 67 tokens ( 5.99 ms per token, 166.81 tokens per second) 10.39.221.336 I slot print_timing: id 0 | task 12193 | eval time = 20401.59 ms / 456 tokens ( 44.84 ms per token, 22.30 tokens per second) 10.39.221.337 I slot print_timing: id 0 | task 12193 | total time = 20803.25 ms / 523 tokens 10.39.221.337 I slot print_timing: id 0 | task 12193 | graphs reused = 11605 10.39.221.338 I slot print_timing: id 0 | task 12193 | graph reallocs = 0 / 0 (same size) / (changed size) 10.39.221.398 I slot release: id 0 | task 12193 | stop processing: n_tokens = 1493, truncated = 0 10.39.263.445 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.650 10.39.263.471 I slot launch_slot_: id 0 | task 12657 | processing task, is_child = 0 10.39.609.312 I slot print_timing: id 1 | task 12425 | n_gen = 229, tg = 22.09 t/s, tg_3s = 16.41 t/s 10.42.340.260 I slot print_timing: id 2 | task 12622 | n_gen = 100, tg = 20.69 t/s, tg_3s = 20.90 t/s 10.42.620.641 I slot print_timing: id 1 | task 12425 | n_gen = 303, tg = 22.65 t/s, tg_3s = 24.57 t/s 10.42.661.031 I slot print_timing: id 3 | task 12631 | n_gen = 100, tg = 22.87 t/s, tg_3s = 23.10 t/s 10.43.662.276 I slot print_timing: id 0 | task 12657 | n_gen = 100, tg = 24.91 t/s, tg_3s = 25.16 t/s 10.45.344.460 I slot print_timing: id 2 | task 12622 | n_gen = 175, tg = 22.34 t/s, tg_3s = 24.97 t/s 10.45.625.197 I slot print_timing: id 1 | task 12425 | n_gen = 378, tg = 23.08 t/s, tg_3s = 24.96 t/s 10.45.665.652 I slot print_timing: id 3 | task 12631 | n_gen = 175, tg = 23.73 t/s, tg_3s = 24.96 t/s 10.46.668.406 I slot print_timing: id 0 | task 12657 | n_gen = 175, tg = 24.93 t/s, tg_3s = 24.95 t/s 10.48.364.425 I slot print_timing: id 2 | task 12622 | n_gen = 250, tg = 23.03 t/s, tg_3s = 24.83 t/s 10.48.648.453 I slot print_timing: id 1 | task 12425 | n_gen = 453, tg = 23.35 t/s, tg_3s = 24.81 t/s 10.48.689.161 I slot print_timing: id 3 | task 12631 | n_gen = 250, tg = 24.04 t/s, tg_3s = 24.81 t/s 10.49.704.566 I slot print_timing: id 0 | task 12657 | n_gen = 250, tg = 24.86 t/s, tg_3s = 24.70 t/s 10.50.027.275 I slot print_timing: id 1 | task 12425 | prompt eval time = 494.48 ms / 88 tokens ( 5.62 ms per token, 177.97 tokens per second) 10.50.027.283 I slot print_timing: id 1 | task 12425 | eval time = 20739.04 ms / 487 tokens ( 42.67 ms per token, 23.43 tokens per second) 10.50.027.284 I slot print_timing: id 1 | task 12425 | total time = 21233.52 ms / 575 tokens 10.50.027.285 I slot print_timing: id 1 | task 12425 | graphs reused = 11860 10.50.027.286 I slot print_timing: id 1 | task 12425 | graph reallocs = 0 / 0 (same size) / (changed size) 10.50.027.362 I slot release: id 1 | task 12425 | stop processing: n_tokens = 1545, truncated = 0 10.50.084.377 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.628 10.50.084.403 I slot launch_slot_: id 1 | task 12918 | processing task, is_child = 0 10.51.199.392 I slot print_timing: id 2 | task 12622 | prompt eval time = 412.85 ms / 59 tokens ( 7.00 ms per token, 142.91 tokens per second) 10.51.199.398 I slot print_timing: id 2 | task 12622 | eval time = 13644.69 ms / 308 tokens ( 44.45 ms per token, 22.50 tokens per second) 10.51.199.399 I slot print_timing: id 2 | task 12622 | total time = 14057.54 ms / 367 tokens 10.51.199.400 I slot print_timing: id 2 | task 12622 | graphs reused = 11873 10.51.199.401 I slot print_timing: id 2 | task 12622 | graph reallocs = 0 / 0 (same size) / (changed size) 10.51.199.473 I slot release: id 2 | task 12622 | stop processing: n_tokens = 1337, truncated = 0 10.51.256.905 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.726 10.51.256.935 I slot launch_slot_: id 2 | task 12936 | processing task, is_child = 0 10.51.730.561 I slot print_timing: id 3 | task 12631 | n_gen = 303, tg = 22.54 t/s, tg_3s = 17.43 t/s 10.52.741.691 I slot print_timing: id 0 | task 12657 | n_gen = 303, tg = 23.14 t/s, tg_3s = 17.45 t/s 10.54.758.961 I slot print_timing: id 3 | task 12631 | n_gen = 378, tg = 22.95 t/s, tg_3s = 24.77 t/s 10.55.038.346 I slot print_timing: id 1 | task 12918 | n_gen = 100, tg = 22.44 t/s, tg_3s = 22.66 t/s 10.55.723.417 I slot print_timing: id 2 | task 12936 | n_gen = 100, tg = 24.79 t/s, tg_3s = 25.04 t/s 10.55.763.421 I slot print_timing: id 0 | task 12657 | n_gen = 378, tg = 23.45 t/s, tg_3s = 24.82 t/s 10.57.785.360 I slot print_timing: id 3 | task 12631 | n_gen = 453, tg = 23.23 t/s, tg_3s = 24.78 t/s 10.58.067.263 I slot print_timing: id 1 | task 12918 | n_gen = 175, tg = 23.38 t/s, tg_3s = 24.76 t/s 10.58.753.617 I slot print_timing: id 2 | task 12936 | n_gen = 175, tg = 24.78 t/s, tg_3s = 24.75 t/s 10.58.793.578 I slot print_timing: id 0 | task 12657 | n_gen = 453, tg = 23.66 t/s, tg_3s = 24.75 t/s 11.00.810.230 I slot print_timing: id 3 | task 12631 | n_gen = 528, tg = 23.44 t/s, tg_3s = 24.79 t/s 11.01.091.434 I slot print_timing: id 1 | task 12918 | n_gen = 250, tg = 23.79 t/s, tg_3s = 24.80 t/s 11.01.778.540 I slot print_timing: id 2 | task 12936 | n_gen = 250, tg = 24.78 t/s, tg_3s = 24.79 t/s 11.01.818.636 I slot print_timing: id 0 | task 12657 | n_gen = 528, tg = 23.81 t/s, tg_3s = 24.79 t/s 11.02.464.898 I slot print_timing: id 2 | task 12936 | prompt eval time = 473.51 ms / 78 tokens ( 6.07 ms per token, 164.73 tokens per second) 11.02.464.904 I slot print_timing: id 2 | task 12936 | eval time = 10734.44 ms / 267 tokens ( 40.36 ms per token, 24.78 tokens per second) 11.02.464.906 I slot print_timing: id 2 | task 12936 | total time = 11207.95 ms / 345 tokens 11.02.464.907 I slot print_timing: id 2 | task 12936 | graphs reused = 12136 11.02.464.908 I slot print_timing: id 2 | task 12936 | graph reallocs = 0 / 0 (same size) / (changed size) 11.02.464.987 I slot release: id 2 | task 12936 | stop processing: n_tokens = 1315, truncated = 0 11.02.523.063 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.899 (> 0.100 thold), f_keep = 0.738 11.02.523.101 I slot launch_slot_: id 2 | task 13206 | processing task, is_child = 0 11.03.837.968 I slot print_timing: id 3 | task 12631 | n_gen = 591, tg = 23.13 t/s, tg_3s = 20.81 t/s 11.04.121.604 I slot print_timing: id 1 | task 12918 | n_gen = 313, tg = 23.12 t/s, tg_3s = 20.79 t/s 11.04.849.732 I slot print_timing: id 0 | task 12657 | n_gen = 591, tg = 23.45 t/s, tg_3s = 20.78 t/s 11.06.876.795 I slot print_timing: id 3 | task 12631 | n_gen = 666, tg = 23.30 t/s, tg_3s = 24.68 t/s 11.07.078.777 I slot print_timing: id 2 | task 13206 | n_gen = 100, tg = 24.62 t/s, tg_3s = 24.87 t/s 11.07.159.437 I slot print_timing: id 1 | task 12918 | n_gen = 388, tg = 23.41 t/s, tg_3s = 24.69 t/s 11.07.856.037 I slot print_timing: id 0 | task 12657 | n_gen = 665, tg = 23.57 t/s, tg_3s = 24.61 t/s 11.09.887.525 I slot print_timing: id 3 | task 12631 | n_gen = 740, tg = 23.42 t/s, tg_3s = 24.58 t/s 11.10.090.583 I slot print_timing: id 2 | task 13206 | n_gen = 174, tg = 24.60 t/s, tg_3s = 24.57 t/s 11.10.171.657 I slot print_timing: id 1 | task 12918 | n_gen = 462, tg = 23.59 t/s, tg_3s = 24.57 t/s 11.10.862.112 I slot print_timing: id 0 | task 12657 | n_gen = 739, tg = 23.67 t/s, tg_3s = 24.62 t/s 11.12.892.292 I slot print_timing: id 3 | task 12631 | n_gen = 814, tg = 23.52 t/s, tg_3s = 24.63 t/s 11.13.095.010 I slot print_timing: id 2 | task 13206 | n_gen = 248, tg = 24.61 t/s, tg_3s = 24.63 t/s 11.13.176.245 I slot print_timing: id 1 | task 12918 | n_gen = 536, tg = 23.72 t/s, tg_3s = 24.63 t/s 11.13.867.477 I slot print_timing: id 0 | task 12657 | n_gen = 813, tg = 23.76 t/s, tg_3s = 24.62 t/s 11.15.904.886 I slot print_timing: id 3 | task 12631 | n_gen = 888, tg = 23.61 t/s, tg_3s = 24.56 t/s 11.16.107.644 I slot print_timing: id 2 | task 13206 | n_gen = 322, tg = 24.60 t/s, tg_3s = 24.56 t/s 11.16.188.788 I slot print_timing: id 1 | task 12918 | n_gen = 610, tg = 23.82 t/s, tg_3s = 24.56 t/s 11.16.879.600 I slot print_timing: id 0 | task 12657 | n_gen = 887, tg = 23.82 t/s, tg_3s = 24.57 t/s 11.18.933.560 I slot print_timing: id 3 | task 12631 | n_gen = 962, tg = 23.67 t/s, tg_3s = 24.43 t/s 11.19.138.492 I slot print_timing: id 2 | task 13206 | n_gen = 396, tg = 24.56 t/s, tg_3s = 24.42 t/s 11.19.220.756 I slot print_timing: id 1 | task 12918 | n_gen = 684, tg = 23.89 t/s, tg_3s = 24.41 t/s 11.19.885.382 I slot print_timing: id 0 | task 12657 | n_gen = 960, tg = 23.86 t/s, tg_3s = 24.29 t/s 11.21.487.160 I slot print_timing: id 3 | task 12631 | prompt eval time = 531.16 ms / 139 tokens ( 3.82 ms per token, 261.69 tokens per second) 11.21.487.167 I slot print_timing: id 3 | task 12631 | eval time = 43155.32 ms / 1024 tokens ( 42.19 ms per token, 23.71 tokens per second) 11.21.487.169 I slot print_timing: id 3 | task 12631 | total time = 43686.48 ms / 1163 tokens 11.21.487.178 I slot print_timing: id 3 | task 12631 | graphs reused = 12585 11.21.487.179 I slot print_timing: id 3 | task 12631 | graph reallocs = 0 / 0 (same size) / (changed size) 11.21.487.261 I slot release: id 3 | task 12631 | stop processing: n_tokens = 2133, truncated = 0 11.21.529.421 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.455 11.21.558.620 I slot launch_slot_: id 3 | task 13662 | processing task, is_child = 0 11.22.161.041 I slot print_timing: id 2 | task 13206 | n_gen = 460, tg = 24.03 t/s, tg_3s = 21.17 t/s 11.22.242.283 I slot print_timing: id 1 | task 12918 | prompt eval time = 541.39 ms / 112 tokens ( 4.83 ms per token, 206.87 tokens per second) 11.22.242.287 I slot print_timing: id 1 | task 12918 | eval time = 31616.49 ms / 748 tokens ( 42.32 ms per token, 23.63 tokens per second) 11.22.242.288 I slot print_timing: id 1 | task 12918 | total time = 32157.88 ms / 860 tokens 11.22.242.289 I slot print_timing: id 1 | task 12918 | graphs reused = 12589 11.22.242.289 I slot print_timing: id 1 | task 12918 | graph reallocs = 0 / 0 (same size) / (changed size) 11.22.242.334 I slot release: id 1 | task 12918 | stop processing: n_tokens = 1830, truncated = 0 11.22.295.861 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.531 11.22.295.885 I slot launch_slot_: id 1 | task 13672 | processing task, is_child = 0 11.22.907.241 I slot print_timing: id 0 | task 12657 | n_gen = 1013, tg = 23.42 t/s, tg_3s = 17.54 t/s 11.23.355.293 I slot print_timing: id 0 | task 12657 | prompt eval time = 424.56 ms / 73 tokens ( 5.82 ms per token, 171.94 tokens per second) 11.23.355.301 I slot print_timing: id 0 | task 12657 | eval time = 43667.25 ms / 1024 tokens ( 42.69 ms per token, 23.43 tokens per second) 11.23.355.302 I slot print_timing: id 0 | task 12657 | total time = 44091.81 ms / 1097 tokens 11.23.355.303 I slot print_timing: id 0 | task 12657 | graphs reused = 12601 11.23.355.304 I slot print_timing: id 0 | task 12657 | graph reallocs = 0 / 0 (same size) / (changed size) 11.23.355.375 I slot release: id 0 | task 12657 | stop processing: n_tokens = 2067, truncated = 0 11.23.397.355 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.470 11.23.397.610 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 18.695 MiB) 11.23.397.615 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 22.798 MiB) 11.23.397.618 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 20.227 MiB) 11.23.397.620 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 24.275 MiB) 11.23.397.622 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 22.470 MiB) 11.23.425.663 I slot launch_slot_: id 0 | task 13689 | processing task, is_child = 0 11.25.163.369 I slot print_timing: id 2 | task 13206 | n_gen = 513, tg = 23.16 t/s, tg_3s = 17.65 t/s 11.26.853.630 I slot print_timing: id 3 | task 13662 | n_gen = 100, tg = 20.37 t/s, tg_3s = 20.58 t/s 11.27.214.971 I slot print_timing: id 1 | task 13672 | n_gen = 100, tg = 22.52 t/s, tg_3s = 22.75 t/s 11.27.858.595 I slot print_timing: id 0 | task 13689 | n_gen = 100, tg = 24.83 t/s, tg_3s = 25.08 t/s 11.28.180.205 I slot print_timing: id 2 | task 13206 | n_gen = 588, tg = 23.36 t/s, tg_3s = 24.86 t/s 11.29.869.077 I slot print_timing: id 3 | task 13662 | n_gen = 175, tg = 22.09 t/s, tg_3s = 24.87 t/s 11.30.231.976 I slot print_timing: id 1 | task 13672 | n_gen = 175, tg = 23.47 t/s, tg_3s = 24.86 t/s 11.30.875.939 I slot print_timing: id 0 | task 13689 | n_gen = 175, tg = 24.84 t/s, tg_3s = 24.86 t/s 11.31.197.450 I slot print_timing: id 2 | task 13206 | n_gen = 663, tg = 23.52 t/s, tg_3s = 24.86 t/s 11.31.639.917 I slot print_timing: id 0 | task 13689 | prompt eval time = 446.39 ms / 87 tokens ( 5.13 ms per token, 194.90 tokens per second) 11.31.639.925 I slot print_timing: id 0 | task 13689 | eval time = 7767.85 ms / 194 tokens ( 40.25 ms per token, 24.85 tokens per second) 11.31.639.926 I slot print_timing: id 0 | task 13689 | total time = 8214.24 ms / 281 tokens 11.31.639.926 I slot print_timing: id 0 | task 13689 | graphs reused = 12794 11.31.639.927 I slot print_timing: id 0 | task 13689 | graph reallocs = 0 / 0 (same size) / (changed size) 11.31.640.001 I slot release: id 0 | task 13689 | stop processing: n_tokens = 1250, truncated = 0 11.31.682.423 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.777 11.31.682.449 I slot launch_slot_: id 0 | task 13886 | processing task, is_child = 0 11.32.897.214 I slot print_timing: id 3 | task 13662 | n_gen = 242, tg = 22.10 t/s, tg_3s = 22.13 t/s 11.33.260.885 I slot print_timing: id 1 | task 13672 | n_gen = 242, tg = 23.08 t/s, tg_3s = 22.12 t/s 11.34.234.768 I slot print_timing: id 2 | task 13206 | n_gen = 730, tg = 23.38 t/s, tg_3s = 22.06 t/s 11.35.929.870 I slot print_timing: id 3 | task 13662 | n_gen = 317, tg = 22.68 t/s, tg_3s = 24.73 t/s 11.36.090.956 I slot print_timing: id 0 | task 13886 | n_gen = 100, tg = 24.69 t/s, tg_3s = 24.94 t/s 11.36.293.157 I slot print_timing: id 1 | task 13672 | n_gen = 317, tg = 23.45 t/s, tg_3s = 24.73 t/s 11.37.261.830 I slot print_timing: id 2 | task 13206 | n_gen = 805, tg = 23.51 t/s, tg_3s = 24.78 t/s 11.38.962.346 I slot print_timing: id 3 | task 13662 | n_gen = 392, tg = 23.04 t/s, tg_3s = 24.73 t/s 11.39.123.176 I slot print_timing: id 0 | task 13886 | n_gen = 175, tg = 24.71 t/s, tg_3s = 24.73 t/s 11.39.325.286 I slot print_timing: id 1 | task 13672 | n_gen = 392, tg = 23.69 t/s, tg_3s = 24.74 t/s 11.39.892.057 I slot print_timing: id 0 | task 13886 | prompt eval time = 399.14 ms / 67 tokens ( 5.96 ms per token, 167.86 tokens per second) 11.39.892.062 I slot print_timing: id 0 | task 13886 | eval time = 7810.45 ms / 194 tokens ( 40.47 ms per token, 24.71 tokens per second) 11.39.892.063 I slot print_timing: id 0 | task 13886 | total time = 8209.60 ms / 261 tokens 11.39.892.064 I slot print_timing: id 0 | task 13886 | graphs reused = 12986 11.39.892.065 I slot print_timing: id 0 | task 13886 | graph reallocs = 0 / 0 (same size) / (changed size) 11.39.892.135 I slot release: id 0 | task 13886 | stop processing: n_tokens = 1231, truncated = 0 11.39.934.581 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.924 (> 0.100 thold), f_keep = 0.789 11.39.934.604 I slot launch_slot_: id 0 | task 14083 | processing task, is_child = 0 11.40.278.275 I slot print_timing: id 2 | task 13206 | n_gen = 872, tg = 23.40 t/s, tg_3s = 22.21 t/s 11.41.988.020 I slot print_timing: id 3 | task 13662 | n_gen = 458, tg = 22.86 t/s, tg_3s = 21.81 t/s 11.42.351.913 I slot print_timing: id 1 | task 13672 | n_gen = 458, tg = 23.40 t/s, tg_3s = 21.81 t/s 11.43.284.046 I slot print_timing: id 2 | task 13206 | n_gen = 945, tg = 23.47 t/s, tg_3s = 24.29 t/s 11.44.382.998 I slot print_timing: id 0 | task 14083 | n_gen = 100, tg = 24.59 t/s, tg_3s = 24.84 t/s 11.44.997.782 I slot print_timing: id 3 | task 13662 | n_gen = 532, tg = 23.08 t/s, tg_3s = 24.59 t/s 11.45.364.853 I slot print_timing: id 1 | task 13672 | n_gen = 532, tg = 23.55 t/s, tg_3s = 24.56 t/s 11.46.306.228 I slot print_timing: id 2 | task 13206 | n_gen = 1019, tg = 23.54 t/s, tg_3s = 24.49 t/s 11.46.511.132 I slot print_timing: id 2 | task 13206 | prompt eval time = 533.99 ms / 109 tokens ( 4.90 ms per token, 204.12 tokens per second) 11.46.511.142 I slot print_timing: id 2 | task 13206 | eval time = 43454.04 ms / 1024 tokens ( 42.48 ms per token, 23.54 tokens per second) 11.46.511.143 I slot print_timing: id 2 | task 13206 | total time = 43988.02 ms / 1133 tokens 11.46.511.143 I slot print_timing: id 2 | task 13206 | graphs reused = 13136 11.46.511.144 I slot print_timing: id 2 | task 13206 | graph reallocs = 0 / 0 (same size) / (changed size) 11.46.511.219 I slot release: id 2 | task 13206 | stop processing: n_tokens = 2103, truncated = 0 11.46.568.779 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.462 11.46.569.038 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 30.839 MiB) 11.46.569.042 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 28.213 MiB) 11.46.569.044 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 19.407 MiB) 11.46.569.047 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 18.094 MiB) 11.46.569.049 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 19.352 MiB) 11.46.569.051 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 20.829 MiB) 11.46.569.052 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 22.169 MiB) 11.46.569.054 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 26.900 MiB) 11.46.569.056 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 21.157 MiB) 11.46.569.058 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 19.078 MiB) 11.46.569.060 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 17.369 MiB) 11.46.569.062 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 21.813 MiB) 11.46.569.064 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 22.360 MiB) 11.46.569.066 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 18.367 MiB) 11.46.606.143 I slot launch_slot_: id 2 | task 14238 | processing task, is_child = 0 11.47.402.210 I slot print_timing: id 0 | task 14083 | n_gen = 164, tg = 23.14 t/s, tg_3s = 21.20 t/s 11.48.006.630 I slot print_timing: id 3 | task 13662 | n_gen = 596, tg = 22.87 t/s, tg_3s = 21.27 t/s 11.48.368.977 I slot print_timing: id 1 | task 13672 | n_gen = 596, tg = 23.29 t/s, tg_3s = 21.30 t/s 11.50.428.373 I slot print_timing: id 0 | task 14083 | n_gen = 239, tg = 23.63 t/s, tg_3s = 24.78 t/s 11.51.035.710 I slot print_timing: id 2 | task 14238 | n_gen = 100, tg = 24.70 t/s, tg_3s = 24.95 t/s 11.51.035.862 I slot print_timing: id 3 | task 13662 | n_gen = 671, tg = 23.07 t/s, tg_3s = 24.76 t/s 11.51.398.982 I slot print_timing: id 1 | task 13672 | n_gen = 671, tg = 23.44 t/s, tg_3s = 24.75 t/s 11.53.461.645 I slot print_timing: id 0 | task 14083 | n_gen = 314, tg = 23.88 t/s, tg_3s = 24.73 t/s 11.54.074.508 I slot print_timing: id 2 | task 14238 | n_gen = 175, tg = 24.69 t/s, tg_3s = 24.68 t/s 11.54.074.650 I slot print_timing: id 3 | task 13662 | n_gen = 746, tg = 23.22 t/s, tg_3s = 24.68 t/s 11.54.439.457 I slot print_timing: id 1 | task 13672 | n_gen = 746, tg = 23.56 t/s, tg_3s = 24.67 t/s 11.54.845.151 I slot print_timing: id 2 | task 14238 | prompt eval time = 421.14 ms / 69 tokens ( 6.10 ms per token, 163.84 tokens per second) 11.54.845.157 I slot print_timing: id 2 | task 14238 | eval time = 7817.85 ms / 194 tokens ( 40.51 ms per token, 24.69 tokens per second) 11.54.845.158 I slot print_timing: id 2 | task 14238 | total time = 8238.99 ms / 263 tokens 11.54.845.159 I slot print_timing: id 2 | task 14238 | graphs reused = 13327 11.54.845.160 I slot print_timing: id 2 | task 14238 | graph reallocs = 0 / 0 (same size) / (changed size) 11.54.845.238 I slot release: id 2 | task 14238 | stop processing: n_tokens = 1232, truncated = 0 11.54.903.380 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.788 11.54.903.404 I slot launch_slot_: id 2 | task 14435 | processing task, is_child = 0 11.56.500.970 I slot print_timing: id 0 | task 14083 | n_gen = 379, tg = 23.41 t/s, tg_3s = 21.39 t/s 11.57.109.072 I slot print_timing: id 3 | task 13662 | n_gen = 811, tg = 23.07 t/s, tg_3s = 21.42 t/s 11.57.473.646 I slot print_timing: id 1 | task 13672 | n_gen = 811, tg = 23.37 t/s, tg_3s = 21.42 t/s 11.59.380.258 I slot print_timing: id 2 | task 14435 | n_gen = 100, tg = 24.65 t/s, tg_3s = 24.90 t/s 11.59.501.662 I slot print_timing: id 0 | task 14083 | n_gen = 453, tg = 23.61 t/s, tg_3s = 24.66 t/s 12.00.109.571 I slot print_timing: id 3 | task 13662 | n_gen = 885, tg = 23.19 t/s, tg_3s = 24.66 t/s 12.00.474.172 I slot print_timing: id 1 | task 13672 | n_gen = 885, tg = 23.48 t/s, tg_3s = 24.66 t/s 12.02.420.325 I slot print_timing: id 2 | task 14435 | n_gen = 175, tg = 24.66 t/s, tg_3s = 24.67 t/s 12.02.542.003 I slot print_timing: id 0 | task 14083 | n_gen = 528, tg = 23.75 t/s, tg_3s = 24.67 t/s 12.03.150.060 I slot print_timing: id 3 | task 13662 | n_gen = 960, tg = 23.30 t/s, tg_3s = 24.67 t/s 12.03.514.395 I slot print_timing: id 1 | task 13672 | n_gen = 960, tg = 23.57 t/s, tg_3s = 24.67 t/s 12.04.702.121 I slot print_timing: id 2 | task 14435 | prompt eval time = 459.98 ms / 76 tokens ( 6.05 ms per token, 165.23 tokens per second) 12.04.702.129 I slot print_timing: id 2 | task 14435 | eval time = 9338.73 ms / 231 tokens ( 40.60 ms per token, 24.63 tokens per second) 12.04.702.130 I slot print_timing: id 2 | task 14435 | total time = 9798.71 ms / 307 tokens 12.04.702.131 I slot print_timing: id 2 | task 14435 | graphs reused = 13555 12.04.702.131 I slot print_timing: id 2 | task 14435 | graph reallocs = 0 / 0 (same size) / (changed size) 12.04.702.201 I slot release: id 2 | task 14435 | stop processing: n_tokens = 1277, truncated = 0 12.04.760.897 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.879 (> 0.100 thold), f_keep = 0.760 12.04.760.924 I slot launch_slot_: id 2 | task 14669 | processing task, is_child = 0 12.05.550.410 I slot print_timing: id 0 | task 14083 | n_gen = 589, tg = 23.34 t/s, tg_3s = 20.28 t/s 12.06.166.679 I slot print_timing: id 3 | task 13662 | n_gen = 1021, tg = 23.09 t/s, tg_3s = 20.22 t/s 12.06.289.809 I slot print_timing: id 3 | task 13662 | prompt eval time = 435.36 ms / 79 tokens ( 5.51 ms per token, 181.46 tokens per second) 12.06.289.816 I slot print_timing: id 3 | task 13662 | eval time = 44295.82 ms / 1024 tokens ( 43.30 ms per token, 23.09 tokens per second) 12.06.289.818 I slot print_timing: id 3 | task 13662 | total time = 44731.18 ms / 1103 tokens 12.06.289.819 I slot print_timing: id 3 | task 13662 | graphs reused = 13577 12.06.289.820 I slot print_timing: id 3 | task 13662 | graph reallocs = 0 / 0 (same size) / (changed size) 12.06.289.895 I slot release: id 3 | task 13662 | stop processing: n_tokens = 2072, truncated = 0 12.06.331.965 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.469 12.06.332.211 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 15.413 MiB) 12.06.332.216 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 21.376 MiB) 12.06.348.723 I slot launch_slot_: id 3 | task 14696 | processing task, is_child = 0 12.06.713.548 I slot print_timing: id 1 | task 13672 | n_gen = 1017, tg = 23.15 t/s, tg_3s = 17.82 t/s 12.07.038.865 I slot print_timing: id 1 | task 13672 | prompt eval time = 523.67 ms / 101 tokens ( 5.18 ms per token, 192.87 tokens per second) 12.07.038.877 I slot print_timing: id 1 | task 13672 | eval time = 44219.30 ms / 1024 tokens ( 43.23 ms per token, 23.13 tokens per second) 12.07.038.878 I slot print_timing: id 1 | task 13672 | total time = 44742.97 ms / 1125 tokens 12.07.038.879 I slot print_timing: id 1 | task 13672 | graphs reused = 13582 12.07.038.880 I slot print_timing: id 1 | task 13672 | graph reallocs = 0 / 0 (same size) / (changed size) 12.07.039.004 I slot release: id 1 | task 13672 | stop processing: n_tokens = 2094, truncated = 0 12.07.099.909 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.464 12.07.100.199 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 26.900 MiB) 12.07.100.205 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 22.935 MiB) 12.07.100.207 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 28.760 MiB) 12.07.100.210 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 20.528 MiB) 12.07.100.212 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 25.752 MiB) 12.07.100.214 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 25.943 MiB) 12.07.100.219 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 22.989 MiB) 12.07.100.221 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 21.841 MiB) 12.07.100.223 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 19.352 MiB) 12.07.100.225 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 18.531 MiB) 12.07.100.356 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 25.423 MiB) 12.07.100.791 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 25.752 MiB) 12.07.101.126 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 24.111 MiB) 12.07.143.103 I slot launch_slot_: id 1 | task 14706 | processing task, is_child = 0 12.08.576.564 I slot print_timing: id 0 | task 14083 | n_gen = 642, tg = 22.71 t/s, tg_3s = 17.51 t/s 12.10.224.667 I slot print_timing: id 2 | task 14669 | n_gen = 100, tg = 20.24 t/s, tg_3s = 20.45 t/s 12.11.272.357 I slot print_timing: id 3 | task 14696 | n_gen = 100, tg = 22.10 t/s, tg_3s = 22.32 t/s 12.11.594.378 I slot print_timing: id 0 | task 14083 | n_gen = 717, tg = 22.92 t/s, tg_3s = 24.85 t/s 12.11.634.794 I slot print_timing: id 1 | task 14706 | n_gen = 100, tg = 24.82 t/s, tg_3s = 25.07 t/s 12.13.253.028 I slot print_timing: id 2 | task 14669 | n_gen = 175, tg = 21.97 t/s, tg_3s = 24.77 t/s 12.14.018.649 I slot print_timing: id 3 | task 14696 | prompt eval time = 444.03 ms / 81 tokens ( 5.48 ms per token, 182.42 tokens per second) 12.14.018.657 I slot print_timing: id 3 | task 14696 | eval time = 7225.89 ms / 168 tokens ( 43.27 ms per token, 23.11 tokens per second) 12.14.018.658 I slot print_timing: id 3 | task 14696 | total time = 7669.91 ms / 249 tokens 12.14.018.659 I slot print_timing: id 3 | task 14696 | graphs reused = 13738 12.14.018.660 I slot print_timing: id 3 | task 14696 | graph reallocs = 0 / 0 (same size) / (changed size) 12.14.018.736 I slot release: id 3 | task 14696 | stop processing: n_tokens = 1217, truncated = 0 12.14.060.227 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.798 12.14.060.258 I slot launch_slot_: id 3 | task 14868 | processing task, is_child = 0 12.14.628.973 I slot print_timing: id 0 | task 14083 | n_gen = 784, tg = 22.85 t/s, tg_3s = 22.08 t/s 12.14.669.067 I slot print_timing: id 1 | task 14706 | n_gen = 167, tg = 23.64 t/s, tg_3s = 22.08 t/s 12.16.283.898 I slot print_timing: id 2 | task 14669 | n_gen = 242, tg = 22.01 t/s, tg_3s = 22.11 t/s 12.17.654.215 I slot print_timing: id 0 | task 14083 | n_gen = 859, tg = 23.00 t/s, tg_3s = 24.79 t/s 12.17.694.757 I slot print_timing: id 1 | task 14706 | n_gen = 242, tg = 23.98 t/s, tg_3s = 24.79 t/s 12.18.461.687 I slot print_timing: id 3 | task 14868 | n_gen = 100, tg = 24.78 t/s, tg_3s = 25.03 t/s 12.19.309.974 I slot print_timing: id 2 | task 14669 | n_gen = 317, tg = 22.61 t/s, tg_3s = 24.78 t/s 12.19.592.911 I slot print_timing: id 1 | task 14706 | prompt eval time = 502.54 ms / 94 tokens ( 5.35 ms per token, 187.05 tokens per second) 12.19.592.919 I slot print_timing: id 1 | task 14706 | eval time = 11947.25 ms / 289 tokens ( 41.48 ms per token, 24.11 tokens per second) 12.19.592.920 I slot print_timing: id 1 | task 14706 | total time = 12449.79 ms / 383 tokens 12.19.592.921 I slot print_timing: id 1 | task 14706 | graphs reused = 13864 12.19.592.922 I slot print_timing: id 1 | task 14706 | graph reallocs = 0 / 0 (same size) / (changed size) 12.19.593.000 I slot release: id 1 | task 14706 | stop processing: n_tokens = 1351, truncated = 0 12.19.650.587 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.899 (> 0.100 thold), f_keep = 0.719 12.19.650.611 I slot launch_slot_: id 1 | task 14999 | processing task, is_child = 0 12.20.691.861 I slot print_timing: id 0 | task 14083 | n_gen = 922, tg = 22.83 t/s, tg_3s = 20.74 t/s 12.21.499.930 I slot print_timing: id 3 | task 14868 | n_gen = 163, tg = 23.03 t/s, tg_3s = 20.74 t/s 12.22.348.220 I slot print_timing: id 2 | task 14669 | n_gen = 380, tg = 22.28 t/s, tg_3s = 20.74 t/s 12.23.680.769 I slot print_timing: id 0 | task 14083 | prompt eval time = 422.45 ms / 80 tokens ( 5.28 ms per token, 189.37 tokens per second) 12.23.680.777 I slot print_timing: id 0 | task 14083 | eval time = 43323.70 ms / 996 tokens ( 43.54 ms per token, 22.97 tokens per second) 12.23.680.778 I slot print_timing: id 0 | task 14083 | total time = 43746.15 ms / 1076 tokens 12.23.680.779 I slot print_timing: id 0 | task 14083 | graphs reused = 13949 12.23.680.780 I slot print_timing: id 0 | task 14083 | graph reallocs = 0 / 0 (same size) / (changed size) 12.23.680.853 I slot release: id 0 | task 14083 | stop processing: n_tokens = 2046, truncated = 0 12.23.723.527 I slot print_timing: id 3 | task 14868 | prompt eval time = 406.33 ms / 63 tokens ( 6.45 ms per token, 155.05 tokens per second) 12.23.723.530 I slot print_timing: id 3 | task 14868 | eval time = 9256.93 ms / 218 tokens ( 42.66 ms per token, 23.44 tokens per second) 12.23.723.531 I slot print_timing: id 3 | task 14868 | total time = 9663.26 ms / 281 tokens 12.23.723.532 I slot print_timing: id 3 | task 14868 | graphs reused = 13949 12.23.723.532 I slot print_timing: id 3 | task 14868 | graph reallocs = 0 / 0 (same size) / (changed size) 12.23.723.593 I slot release: id 3 | task 14868 | stop processing: n_tokens = 1251, truncated = 0 12.23.723.601 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.777 12.23.723.624 I slot launch_slot_: id 3 | task 15089 | processing task, is_child = 0 12.23.723.889 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 25.423 MiB) 12.23.723.894 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 20.172 MiB) 12.23.724.059 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 18.531 MiB) 12.23.724.319 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 18.367 MiB) 12.23.724.621 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 22.196 MiB) 12.23.724.927 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 21.649 MiB) 12.23.725.160 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 22.032 MiB) 12.23.725.366 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 18.846 MiB) 12.23.725.530 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 19.899 MiB) 12.23.725.732 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 18.367 MiB) 12.23.725.932 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 18.354 MiB) 12.23.726.176 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 26.408 MiB) 12.23.726.369 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 34.941 MiB) 12.24.485.926 I slot print_timing: id 1 | task 14999 | n_gen = 100, tg = 23.08 t/s, tg_3s = 23.32 t/s 12.25.380.762 I slot print_timing: id 2 | task 14669 | n_gen = 451, tg = 22.45 t/s, tg_3s = 23.41 t/s 12.27.512.088 I slot print_timing: id 1 | task 14999 | n_gen = 185, tg = 25.15 t/s, tg_3s = 28.09 t/s 12.27.655.568 I slot print_timing: id 3 | task 15089 | n_gen = 100, tg = 28.04 t/s, tg_3s = 28.32 t/s 12.28.409.019 I slot print_timing: id 2 | task 14669 | n_gen = 536, tg = 23.18 t/s, tg_3s = 28.07 t/s 12.28.981.843 I slot print_timing: id 1 | task 14999 | prompt eval time = 546.75 ms / 109 tokens ( 5.02 ms per token, 199.36 tokens per second) 12.28.981.850 I slot print_timing: id 1 | task 14999 | eval time = 8784.47 ms / 226 tokens ( 39.04 ms per token, 25.61 tokens per second) 12.28.981.852 I slot print_timing: id 1 | task 14999 | total time = 9331.23 ms / 335 tokens 12.28.981.852 I slot print_timing: id 1 | task 14999 | graphs reused = 14083 12.28.981.853 I slot print_timing: id 1 | task 14999 | graph reallocs = 0 / 0 (same size) / (changed size) 12.28.981.917 I slot release: id 1 | task 14999 | stop processing: n_tokens = 1305, truncated = 0 12.30.683.217 I slot print_timing: id 3 | task 15089 | n_gen = 192, tg = 29.12 t/s, tg_3s = 30.39 t/s 12.31.423.938 I slot print_timing: id 2 | task 14669 | n_gen = 631, tg = 24.15 t/s, tg_3s = 31.51 t/s 12.31.609.512 I slot print_timing: id 3 | task 15089 | prompt eval time = 377.70 ms / 64 tokens ( 5.90 ms per token, 169.45 tokens per second) 12.31.609.520 I slot print_timing: id 3 | task 15089 | eval time = 7485.23 ms / 222 tokens ( 33.87 ms per token, 29.52 tokens per second) 12.31.609.521 I slot print_timing: id 3 | task 15089 | total time = 7862.94 ms / 286 tokens 12.31.609.522 I slot print_timing: id 3 | task 15089 | graphs reused = 14167 12.31.609.523 I slot print_timing: id 3 | task 15089 | graph reallocs = 0 / 0 (same size) / (changed size) 12.31.609.583 I slot release: id 3 | task 15089 | stop processing: n_tokens = 1257, truncated = 0 12.34.442.907 I slot print_timing: id 2 | task 14669 | n_gen = 785, tg = 26.93 t/s, tg_3s = 51.01 t/s 12.37.446.392 I slot print_timing: id 2 | task 14669 | n_gen = 942, tg = 29.30 t/s, tg_3s = 52.27 t/s 12.39.026.527 I slot print_timing: id 2 | task 14669 | prompt eval time = 572.72 ms / 134 tokens ( 4.27 ms per token, 233.97 tokens per second) 12.39.026.533 I slot print_timing: id 2 | task 14669 | eval time = 33692.88 ms / 1024 tokens ( 32.94 ms per token, 30.36 tokens per second) 12.39.026.534 I slot print_timing: id 2 | task 14669 | total time = 34265.60 ms / 1158 tokens 12.39.026.535 I slot print_timing: id 2 | task 14669 | graphs reused = 14551 12.39.026.535 I slot print_timing: id 2 | task 14669 | graph reallocs = 0 / 0 (same size) / (changed size) 12.39.026.584 I slot release: id 2 | task 14669 | stop processing: n_tokens = 2128, truncated = 0 12.39.046.905 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 2046, t_last = 353526575034 12.39.047.157 I slot launch_slot_: id 0 | task 15700 | processing task, is_child = 0 12.39.047.281 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 20.665 MiB) 12.39.047.285 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 21.649 MiB) 12.39.047.426 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 24.302 MiB) 12.39.047.605 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 27.283 MiB) 12.39.047.769 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 24.111 MiB) 12.39.047.908 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 34.777 MiB) 12.39.048.034 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 21.485 MiB) 12.39.048.230 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 26.736 MiB) 12.39.048.400 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 17.875 MiB) 12.39.048.596 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 29.184 MiB) 12.39.048.771 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 17.848 MiB) 12.39.048.929 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 21.143 MiB) 12.39.071.591 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 20.172 MiB) 12.39.071.896 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 25.082 MiB) 12.39.072.065 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 20.555 MiB) 12.39.072.209 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 19.024 MiB) 12.39.072.330 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 27.228 MiB) 12.39.072.433 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 27.885 MiB) 12.39.072.615 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 26.244 MiB) 12.39.072.756 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 17.547 MiB) 12.39.072.921 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 18.695 MiB) 12.39.073.094 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 18.258 MiB) 12.39.073.245 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 21.649 MiB) 12.39.073.362 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 19.707 MiB) 12.39.073.491 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 19.352 MiB) 12.39.096.226 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 18.531 MiB) 12.39.096.473 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 20.391 MiB) 12.39.096.944 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 20.159 MiB) 12.39.097.156 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 24.097 MiB) 12.39.097.319 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 21.157 MiB) 12.39.097.518 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 25.095 MiB) 12.39.097.645 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 24.165 MiB) 12.39.097.802 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 20.993 MiB) 12.39.098.000 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 16.617 MiB) 12.39.098.158 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 22.853 MiB) 12.39.098.285 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 19.680 MiB) 12.39.098.456 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 17.205 MiB) 12.39.098.596 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 24.097 MiB) 12.39.098.782 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 22.839 MiB) 12.39.098.930 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 19.078 MiB) 12.39.122.322 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1305, t_last = 353531876097 12.39.122.516 I slot launch_slot_: id 1 | task 15701 | processing task, is_child = 0 12.39.122.728 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1257, t_last = 353534503763 12.39.122.849 I slot launch_slot_: id 3 | task 15702 | processing task, is_child = 0 12.39.122.977 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 2128, t_last = 353541920764 12.39.123.130 I slot launch_slot_: id 2 | task 15703 | processing task, is_child = 0 12.42.897.054 I slot print_timing: id 0 | task 15700 | prompt processing, n_tokens = 578, progress = 0.84, t = 3.77 s / 153.16 tokens per second 12.43.509.087 I slot print_timing: id 1 | task 15701 | prompt processing, n_tokens = 336, progress = 0.39, t = 3.77 s / 89.06 tokens per second 12.43.510.382 I slot print_timing: id 2 | task 15703 | prompt processing, n_tokens = 546, progress = 0.80, t = 3.77 s / 144.76 tokens per second 12.43.512.663 I slot print_timing: id 3 | task 15702 | prompt processing, n_tokens = 351, progress = 0.40, t = 3.77 s / 93.07 tokens per second 12.45.220.059 I slot print_timing: id 0 | task 15700 | prompt processing, n_tokens = 687, progress = 0.99, t = 6.10 s / 112.68 tokens per second 12.45.823.615 I slot print_timing: id 1 | task 15701 | prompt processing, n_tokens = 745, progress = 0.87, t = 6.10 s / 122.22 tokens per second 12.45.825.036 I slot print_timing: id 2 | task 15703 | prompt processing, n_tokens = 679, progress = 0.99, t = 6.09 s / 111.41 tokens per second 12.45.826.350 I slot print_timing: id 3 | task 15702 | prompt processing, n_tokens = 768, progress = 0.89, t = 6.09 s / 126.02 tokens per second 12.46.609.788 I slot print_timing: id 1 | task 15701 | prompt processing, n_tokens = 848, progress = 1.00, t = 7.49 s / 113.29 tokens per second 12.46.611.636 I slot print_timing: id 3 | task 15702 | prompt processing, n_tokens = 863, progress = 1.00, t = 7.48 s / 115.32 tokens per second 12.46.742.649 I slot print_timing: id 0 | task 15700 | prompt eval time = 7486.52 ms / 691 tokens ( 10.83 ms per token, 92.30 tokens per second) 12.46.742.656 I slot print_timing: id 0 | task 15700 | eval time = 132.98 ms / 2 tokens ( 132.98 ms per token, 7.52 tokens per second) 12.46.742.657 I slot print_timing: id 0 | task 15700 | total time = 7619.50 ms / 693 tokens 12.46.742.658 I slot print_timing: id 0 | task 15700 | graphs reused = 14551 12.46.742.659 I slot print_timing: id 0 | task 15700 | graph reallocs = 0 / 0 (same size) / (changed size) 12.46.742.712 I slot release: id 0 | task 15700 | stop processing: n_tokens = 692, truncated = 0 12.46.743.027 I slot print_timing: id 2 | task 15703 | prompt eval time = 7484.52 ms / 683 tokens ( 10.96 ms per token, 91.25 tokens per second) 12.46.743.031 I slot print_timing: id 2 | task 15703 | eval time = 133.25 ms / 2 tokens ( 133.25 ms per token, 7.50 tokens per second) 12.46.743.032 I slot print_timing: id 2 | task 15703 | total time = 7617.77 ms / 685 tokens 12.46.743.032 I slot print_timing: id 2 | task 15703 | graphs reused = 14551 12.46.743.033 I slot print_timing: id 2 | task 15703 | graph reallocs = 0 / 0 (same size) / (changed size) 12.46.743.075 I slot release: id 2 | task 15703 | stop processing: n_tokens = 684, truncated = 0 12.46.790.750 I slot print_timing: id 1 | task 15701 | prompt eval time = 7618.44 ms / 852 tokens ( 8.94 ms per token, 111.83 tokens per second) 12.46.790.758 I slot print_timing: id 1 | task 15701 | eval time = 47.86 ms / 2 tokens ( 47.86 ms per token, 20.89 tokens per second) 12.46.790.761 I slot print_timing: id 1 | task 15701 | total time = 7666.31 ms / 854 tokens 12.46.790.763 I slot print_timing: id 1 | task 15701 | graphs reused = 14551 12.46.790.764 I slot print_timing: id 1 | task 15701 | graph reallocs = 0 / 0 (same size) / (changed size) 12.46.790.837 I slot release: id 1 | task 15701 | stop processing: n_tokens = 853, truncated = 0 12.46.791.054 I slot print_timing: id 3 | task 15702 | prompt eval time = 7617.40 ms / 867 tokens ( 8.79 ms per token, 113.82 tokens per second) 12.46.791.058 I slot print_timing: id 3 | task 15702 | eval time = 47.81 ms / 2 tokens ( 47.81 ms per token, 20.92 tokens per second) 12.46.791.059 I slot print_timing: id 3 | task 15702 | total time = 7665.21 ms / 869 tokens 12.46.791.060 I slot print_timing: id 3 | task 15702 | graphs reused = 14551 12.46.791.061 I slot print_timing: id 3 | task 15702 | graph reallocs = 0 / 0 (same size) / (changed size) 12.46.791.119 I slot release: id 3 | task 15702 | stop processing: n_tokens = 868, truncated = 0 12.46.791.127 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 692, t_last = 353549636892 12.46.791.297 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 24.439 MiB) 12.46.791.303 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 25.806 MiB) 12.46.791.306 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 16.070 MiB) 12.46.791.315 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 19.516 MiB) 12.46.791.319 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 23.618 MiB) 12.46.791.324 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 26.900 MiB) 12.46.804.134 I slot launch_slot_: id 0 | task 15711 | processing task, is_child = 0 12.46.804.262 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 20.336 MiB) 12.46.804.266 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 20.172 MiB) 12.46.804.268 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 24.275 MiB) 12.46.804.270 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 18.531 MiB) 12.46.804.271 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 17.766 MiB) 12.46.804.790 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 23.126 MiB) 12.46.805.031 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 20.665 MiB) 12.46.805.249 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 22.634 MiB) 12.46.816.135 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 24.275 MiB) 12.46.816.142 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 24.275 MiB) 12.46.816.144 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 23.290 MiB) 12.46.816.584 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 23.646 MiB) 12.46.816.781 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 18.012 MiB) 12.46.816.938 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 29.034 MiB) 12.46.826.041 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 17.697 MiB) 12.46.826.046 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 16.945 MiB) 12.46.826.048 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 18.914 MiB) 12.46.826.442 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 18.695 MiB) 12.46.826.880 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 20.500 MiB) 12.46.827.054 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 19.571 MiB) 12.46.827.190 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 20.829 MiB) 12.46.827.353 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 24.589 MiB) 12.46.837.111 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 684, t_last = 353549637255 12.46.837.281 I slot launch_slot_: id 2 | task 15712 | processing task, is_child = 0 12.46.837.455 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 853, t_last = 353549685017 12.46.837.585 I slot launch_slot_: id 1 | task 15713 | processing task, is_child = 0 12.46.837.665 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 868, t_last = 353549685299 12.46.837.799 I slot launch_slot_: id 3 | task 15714 | processing task, is_child = 0 12.51.135.441 I slot print_timing: id 0 | task 15711 | prompt processing, n_tokens = 589, progress = 0.87, t = 4.30 s / 137.05 tokens per second 12.51.178.350 I slot print_timing: id 1 | task 15713 | prompt processing, n_tokens = 589, progress = 0.86, t = 4.30 s / 137.06 tokens per second 12.51.180.402 I slot print_timing: id 2 | task 15712 | prompt processing, n_tokens = 589, progress = 0.81, t = 4.30 s / 137.09 tokens per second 12.51.182.874 I slot print_timing: id 3 | task 15714 | prompt processing, n_tokens = 589, progress = 0.81, t = 4.30 s / 137.10 tokens per second 12.52.296.926 I slot print_timing: id 0 | task 15711 | prompt processing, n_tokens = 676, progress = 0.99, t = 5.46 s / 123.83 tokens per second 12.52.335.878 I slot print_timing: id 1 | task 15713 | prompt processing, n_tokens = 682, progress = 0.99, t = 5.46 s / 124.93 tokens per second 12.52.338.367 I slot print_timing: id 2 | task 15712 | prompt processing, n_tokens = 721, progress = 0.99, t = 5.46 s / 132.10 tokens per second 12.52.340.555 I slot print_timing: id 3 | task 15714 | prompt processing, n_tokens = 726, progress = 0.99, t = 5.46 s / 133.03 tokens per second 12.52.480.978 I slot print_timing: id 0 | task 15711 | prompt eval time = 5601.06 ms / 680 tokens ( 8.24 ms per token, 121.41 tokens per second) 12.52.480.983 I slot print_timing: id 0 | task 15711 | eval time = 42.11 ms / 2 tokens ( 42.11 ms per token, 23.75 tokens per second) 12.52.480.984 I slot print_timing: id 0 | task 15711 | total time = 5643.16 ms / 682 tokens 12.52.480.984 I slot print_timing: id 0 | task 15711 | graphs reused = 14552 12.52.480.985 I slot print_timing: id 0 | task 15711 | graph reallocs = 0 / 0 (same size) / (changed size) 12.52.481.021 I slot release: id 0 | task 15711 | stop processing: n_tokens = 681, truncated = 0 12.52.481.107 I slot print_timing: id 1 | task 15713 | prompt eval time = 5601.02 ms / 686 tokens ( 8.16 ms per token, 122.48 tokens per second) 12.52.481.109 I slot print_timing: id 1 | task 15713 | eval time = 42.14 ms / 2 tokens ( 42.14 ms per token, 23.73 tokens per second) 12.52.481.109 I slot print_timing: id 1 | task 15713 | total time = 5643.16 ms / 688 tokens 12.52.481.110 I slot print_timing: id 1 | task 15713 | graphs reused = 14552 12.52.481.110 I slot print_timing: id 1 | task 15713 | graph reallocs = 0 / 0 (same size) / (changed size) 12.52.481.130 I slot release: id 1 | task 15713 | stop processing: n_tokens = 687, truncated = 0 12.52.481.219 I slot print_timing: id 2 | task 15712 | prompt eval time = 5600.23 ms / 725 tokens ( 7.72 ms per token, 129.46 tokens per second) 12.52.481.221 I slot print_timing: id 2 | task 15712 | eval time = 42.15 ms / 2 tokens ( 42.15 ms per token, 23.73 tokens per second) 12.52.481.221 I slot print_timing: id 2 | task 15712 | total time = 5642.38 ms / 727 tokens 12.52.481.221 I slot print_timing: id 2 | task 15712 | graphs reused = 14552 12.52.481.222 I slot print_timing: id 2 | task 15712 | graph reallocs = 0 / 0 (same size) / (changed size) 12.52.481.244 I slot release: id 2 | task 15712 | stop processing: n_tokens = 726, truncated = 0 12.52.481.329 I slot print_timing: id 3 | task 15714 | prompt eval time = 5599.73 ms / 730 tokens ( 7.67 ms per token, 130.36 tokens per second) 12.52.481.330 I slot print_timing: id 3 | task 15714 | eval time = 42.16 ms / 2 tokens ( 42.16 ms per token, 23.72 tokens per second) 12.52.481.330 I slot print_timing: id 3 | task 15714 | total time = 5641.89 ms / 732 tokens 12.52.481.331 I slot print_timing: id 3 | task 15714 | graphs reused = 14552 12.52.481.331 I slot print_timing: id 3 | task 15714 | graph reallocs = 0 / 0 (same size) / (changed size) 12.52.481.346 I slot release: id 3 | task 15714 | stop processing: n_tokens = 731, truncated = 0 12.52.490.455 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.875 (> 0.100 thold), f_keep = 0.902 12.52.490.520 I slot launch_slot_: id 0 | task 15721 | processing task, is_child = 0 12.52.490.600 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 21.485 MiB) 12.52.490.603 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 24.986 MiB) 12.52.490.605 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 26.080 MiB) 12.52.490.606 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 18.846 MiB) 12.52.490.607 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 18.367 MiB) 12.52.490.608 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 23.454 MiB) 12.52.490.610 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 28.733 MiB) 12.52.498.072 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 18.695 MiB) 12.52.498.077 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 15.960 MiB) 12.52.498.078 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 20.883 MiB) 12.52.498.081 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 21.212 MiB) 12.52.498.359 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 238.907 MiB) 12.52.513.354 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 687, t_last = 353555375310 12.52.513.482 I slot launch_slot_: id 1 | task 15722 | processing task, is_child = 0 12.52.513.595 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 726, t_last = 353555375424 12.52.513.694 I slot launch_slot_: id 2 | task 15723 | processing task, is_child = 0 12.52.513.753 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 731, t_last = 353555375526 12.52.513.857 I slot launch_slot_: id 3 | task 15724 | processing task, is_child = 0 12.56.401.648 I slot print_timing: id 0 | task 15721 | prompt eval time = 2108.84 ms / 88 tokens ( 23.96 ms per token, 41.73 tokens per second) 12.56.401.651 I slot print_timing: id 0 | task 15721 | eval time = 1778.94 ms / 2 tokens ( 1778.94 ms per token, 0.56 tokens per second) 12.56.401.651 I slot print_timing: id 0 | task 15721 | total time = 3887.78 ms / 90 tokens 12.56.401.652 I slot print_timing: id 0 | task 15721 | graphs reused = 14552 12.56.401.652 I slot print_timing: id 0 | task 15721 | graph reallocs = 0 / 0 (same size) / (changed size) 12.56.401.694 I slot release: id 0 | task 15721 | stop processing: n_tokens = 703, truncated = 0 12.56.401.706 I slot print_timing: id 1 | task 15722 | prompt processing, n_tokens = 344, progress = 0.40, t = 3.89 s / 88.51 tokens per second 12.56.402.814 I slot print_timing: id 2 | task 15723 | prompt processing, n_tokens = 648, progress = 0.85, t = 3.89 s / 166.74 tokens per second 12.56.405.688 I slot print_timing: id 3 | task 15724 | prompt processing, n_tokens = 648, progress = 0.84, t = 3.89 s / 166.74 tokens per second 12.57.694.153 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 703, t_last = 353559295874 12.57.694.240 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 311.095 MiB) 12.57.759.652 I slot launch_slot_: id 0 | task 15729 | processing task, is_child = 0 12.57.759.768 I slot print_timing: id 1 | task 15722 | prompt processing, n_tokens = 740, progress = 0.86, t = 5.18 s / 142.88 tokens per second 12.57.761.251 I slot print_timing: id 2 | task 15723 | prompt processing, n_tokens = 757, progress = 0.99, t = 5.18 s / 146.17 tokens per second 12.57.762.464 I slot print_timing: id 3 | task 15724 | prompt processing, n_tokens = 767, progress = 0.99, t = 5.18 s / 148.10 tokens per second 12.58.624.360 I slot print_timing: id 1 | task 15722 | prompt processing, n_tokens = 856, progress = 1.00, t = 6.11 s / 140.13 tokens per second 12.59.209.532 I slot print_timing: id 2 | task 15723 | prompt eval time = 6108.64 ms / 761 tokens ( 8.03 ms per token, 124.58 tokens per second) 12.59.209.538 I slot print_timing: id 2 | task 15723 | eval time = 585.75 ms / 2 tokens ( 585.75 ms per token, 1.71 tokens per second) 12.59.209.539 I slot print_timing: id 2 | task 15723 | total time = 6694.38 ms / 763 tokens 12.59.209.539 I slot print_timing: id 2 | task 15723 | graphs reused = 14552 12.59.209.539 I slot print_timing: id 2 | task 15723 | graph reallocs = 0 / 0 (same size) / (changed size) 12.59.209.579 I slot release: id 2 | task 15723 | stop processing: n_tokens = 762, truncated = 0 12.59.209.668 I slot print_timing: id 3 | task 15724 | prompt eval time = 6108.66 ms / 771 tokens ( 7.92 ms per token, 126.21 tokens per second) 12.59.209.671 I slot print_timing: id 3 | task 15724 | eval time = 585.76 ms / 2 tokens ( 585.76 ms per token, 1.71 tokens per second) 12.59.209.671 I slot print_timing: id 3 | task 15724 | total time = 6694.42 ms / 773 tokens 12.59.209.671 I slot print_timing: id 3 | task 15724 | graphs reused = 14552 12.59.209.672 I slot print_timing: id 3 | task 15724 | graph reallocs = 0 / 0 (same size) / (changed size) 12.59.209.696 I slot release: id 3 | task 15724 | stop processing: n_tokens = 772, truncated = 0 12.59.249.208 I slot print_timing: id 1 | task 15722 | prompt eval time = 6694.40 ms / 860 tokens ( 7.78 ms per token, 128.47 tokens per second) 12.59.249.210 I slot print_timing: id 1 | task 15722 | eval time = 39.76 ms / 2 tokens ( 39.76 ms per token, 25.15 tokens per second) 12.59.249.211 I slot print_timing: id 1 | task 15722 | total time = 6734.17 ms / 862 tokens 12.59.249.211 I slot print_timing: id 1 | task 15722 | graphs reused = 14552 12.59.249.212 I slot print_timing: id 1 | task 15722 | graph reallocs = 0 / 0 (same size) / (changed size) 12.59.249.250 I slot release: id 1 | task 15722 | stop processing: n_tokens = 861, truncated = 0 12.59.249.254 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 762, t_last = 353562103759 12.59.257.227 I slot launch_slot_: id 2 | task 15733 | processing task, is_child = 0 12.59.257.304 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 276.075 MiB) 12.59.264.760 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 276.430 MiB) 12.59.270.983 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 772, t_last = 353562103876 12.59.271.098 I slot launch_slot_: id 3 | task 15734 | processing task, is_child = 0 12.59.271.165 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 861, t_last = 353562143430 12.59.271.271 I slot launch_slot_: id 1 | task 15735 | processing task, is_child = 0 13.02.006.916 I slot print_timing: id 0 | task 15729 | prompt processing, n_tokens = 880, progress = 1.00, t = 4.25 s / 207.19 tokens per second 13.03.469.925 I slot print_timing: id 1 | task 15735 | prompt processing, n_tokens = 655, progress = 0.41, t = 4.20 s / 156.05 tokens per second 13.03.471.610 I slot print_timing: id 2 | task 15733 | prompt processing, n_tokens = 403, progress = 0.44, t = 4.20 s / 96.01 tokens per second 13.03.474.443 I slot print_timing: id 3 | task 15734 | prompt processing, n_tokens = 295, progress = 0.36, t = 4.20 s / 70.29 tokens per second 13.06.154.951 I slot print_timing: id 0 | task 15729 | prompt eval time = 5710.25 ms / 884 tokens ( 6.46 ms per token, 154.81 tokens per second) 13.06.154.954 I slot print_timing: id 0 | task 15729 | eval time = 2685.03 ms / 2 tokens ( 2685.03 ms per token, 0.37 tokens per second) 13.06.154.954 I slot print_timing: id 0 | task 15729 | total time = 8395.28 ms / 886 tokens 13.06.154.955 I slot print_timing: id 0 | task 15729 | graphs reused = 14553 13.06.154.955 I slot print_timing: id 0 | task 15729 | graph reallocs = 0 / 0 (same size) / (changed size) 13.06.154.993 I slot release: id 0 | task 15729 | stop processing: n_tokens = 885, truncated = 0 13.06.155.006 I slot print_timing: id 1 | task 15735 | prompt processing, n_tokens = 1097, progress = 0.68, t = 6.88 s / 159.39 tokens per second 13.06.156.571 I slot print_timing: id 2 | task 15733 | prompt processing, n_tokens = 781, progress = 0.85, t = 6.88 s / 113.48 tokens per second 13.06.159.192 I slot print_timing: id 3 | task 15734 | prompt processing, n_tokens = 655, progress = 0.81, t = 6.88 s / 95.18 tokens per second 13.07.700.103 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 885, t_last = 353569049173 13.07.816.061 I slot launch_slot_: id 0 | task 15741 | processing task, is_child = 0 13.07.816.191 I slot print_timing: id 1 | task 15735 | prompt processing, n_tokens = 1609, progress = 1.00, t = 8.43 s / 190.92 tokens per second 13.07.818.170 I slot print_timing: id 2 | task 15733 | prompt processing, n_tokens = 915, progress = 1.00, t = 8.43 s / 108.57 tokens per second 13.07.819.747 I slot print_timing: id 3 | task 15734 | prompt processing, n_tokens = 807, progress = 1.00, t = 8.43 s / 95.76 tokens per second 13.08.731.148 I slot print_timing: id 1 | task 15735 | prompt eval time = 9007.47 ms / 1613 tokens ( 5.58 ms per token, 179.07 tokens per second) 13.08.731.151 I slot print_timing: id 1 | task 15735 | eval time = 451.34 ms / 2 tokens ( 451.34 ms per token, 2.22 tokens per second) 13.08.731.152 I slot print_timing: id 1 | task 15735 | total time = 9458.81 ms / 1615 tokens 13.08.731.152 I slot print_timing: id 1 | task 15735 | graphs reused = 14553 13.08.731.153 I slot print_timing: id 1 | task 15735 | graph reallocs = 0 / 0 (same size) / (changed size) 13.08.731.220 I slot release: id 1 | task 15735 | stop processing: n_tokens = 1614, truncated = 0 13.08.731.320 I slot print_timing: id 2 | task 15733 | prompt eval time = 9007.50 ms / 919 tokens ( 9.80 ms per token, 102.03 tokens per second) 13.08.731.325 I slot print_timing: id 2 | task 15733 | eval time = 451.37 ms / 2 tokens ( 451.37 ms per token, 2.22 tokens per second) 13.08.731.326 I slot print_timing: id 2 | task 15733 | total time = 9458.87 ms / 921 tokens 13.08.731.326 I slot print_timing: id 2 | task 15733 | graphs reused = 14553 13.08.731.326 I slot print_timing: id 2 | task 15733 | graph reallocs = 0 / 0 (same size) / (changed size) 13.08.731.355 I slot release: id 2 | task 15733 | stop processing: n_tokens = 920, truncated = 0 13.08.731.443 I slot print_timing: id 3 | task 15734 | prompt eval time = 9007.06 ms / 811 tokens ( 11.11 ms per token, 90.04 tokens per second) 13.08.731.445 I slot print_timing: id 3 | task 15734 | eval time = 451.36 ms / 2 tokens ( 451.36 ms per token, 2.22 tokens per second) 13.08.731.445 I slot print_timing: id 3 | task 15734 | total time = 9458.42 ms / 813 tokens 13.08.731.446 I slot print_timing: id 3 | task 15734 | graphs reused = 14553 13.08.731.446 I slot print_timing: id 3 | task 15734 | graph reallocs = 0 / 0 (same size) / (changed size) 13.08.731.473 I slot release: id 3 | task 15734 | stop processing: n_tokens = 812, truncated = 0 13.09.043.324 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1614, t_last = 353571625400 13.09.043.431 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 276.047 MiB) 13.09.723.170 I slot launch_slot_: id 1 | task 15746 | processing task, is_child = 0 13.09.733.068 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 275.842 MiB) 13.09.738.740 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 920, t_last = 353571625535 13.09.738.880 I slot launch_slot_: id 2 | task 15747 | processing task, is_child = 0 13.09.738.942 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 812, t_last = 353571625653 13.09.739.039 I slot launch_slot_: id 3 | task 15748 | processing task, is_child = 0 13.13.421.534 I slot print_timing: id 0 | task 15741 | prompt eval time = 3803.22 ms / 827 tokens ( 4.60 ms per token, 217.45 tokens per second) 13.13.421.538 I slot print_timing: id 0 | task 15741 | eval time = 1802.23 ms / 2 tokens ( 1802.23 ms per token, 0.55 tokens per second) 13.13.421.539 I slot print_timing: id 0 | task 15741 | total time = 5605.45 ms / 829 tokens 13.13.421.540 I slot print_timing: id 0 | task 15741 | graphs reused = 14553 13.13.421.540 I slot print_timing: id 0 | task 15741 | graph reallocs = 0 / 0 (same size) / (changed size) 13.13.421.583 I slot release: id 0 | task 15741 | stop processing: n_tokens = 828, truncated = 0 13.13.421.595 I slot print_timing: id 1 | task 15746 | prompt processing, n_tokens = 264, progress = 0.34, t = 3.68 s / 71.72 tokens per second 13.13.422.283 I slot print_timing: id 2 | task 15747 | prompt processing, n_tokens = 527, progress = 0.84, t = 3.68 s / 143.18 tokens per second 13.13.424.767 I slot print_timing: id 3 | task 15748 | prompt processing, n_tokens = 527, progress = 0.81, t = 3.68 s / 143.18 tokens per second 13.14.677.027 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 828, t_last = 353576315763 13.14.677.108 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 253.178 MiB) 13.14.816.635 I slot launch_slot_: id 0 | task 15753 | processing task, is_child = 0 13.14.816.765 I slot print_timing: id 1 | task 15746 | prompt processing, n_tokens = 680, progress = 0.87, t = 4.94 s / 137.75 tokens per second 13.14.819.054 I slot print_timing: id 2 | task 15747 | prompt processing, n_tokens = 623, progress = 0.99, t = 4.94 s / 126.21 tokens per second 13.14.820.263 I slot print_timing: id 3 | task 15748 | prompt processing, n_tokens = 650, progress = 0.99, t = 4.94 s / 131.68 tokens per second 13.15.437.434 I slot print_timing: id 1 | task 15746 | prompt processing, n_tokens = 776, progress = 0.99, t = 5.70 s / 136.23 tokens per second 13.15.576.981 I slot print_timing: id 2 | task 15747 | prompt eval time = 5696.39 ms / 627 tokens ( 9.09 ms per token, 110.07 tokens per second) 13.15.576.984 I slot print_timing: id 2 | task 15747 | eval time = 139.95 ms / 2 tokens ( 139.95 ms per token, 7.15 tokens per second) 13.15.576.984 I slot print_timing: id 2 | task 15747 | total time = 5836.33 ms / 629 tokens 13.15.576.985 I slot print_timing: id 2 | task 15747 | graphs reused = 14553 13.15.576.985 I slot print_timing: id 2 | task 15747 | graph reallocs = 0 / 0 (same size) / (changed size) 13.15.577.017 I slot release: id 2 | task 15747 | stop processing: n_tokens = 628, truncated = 0 13.15.577.148 I slot print_timing: id 3 | task 15748 | prompt eval time = 5696.40 ms / 654 tokens ( 8.71 ms per token, 114.81 tokens per second) 13.15.577.153 I slot print_timing: id 3 | task 15748 | eval time = 139.99 ms / 2 tokens ( 139.99 ms per token, 7.14 tokens per second) 13.15.577.153 I slot print_timing: id 3 | task 15748 | total time = 5836.40 ms / 656 tokens 13.15.577.154 I slot print_timing: id 3 | task 15748 | graphs reused = 14553 13.15.577.154 I slot print_timing: id 3 | task 15748 | graph reallocs = 0 / 0 (same size) / (changed size) 13.15.577.176 I slot release: id 3 | task 15748 | stop processing: n_tokens = 655, truncated = 0 13.16.338.744 I slot print_timing: id 1 | task 15746 | prompt eval time = 5836.43 ms / 780 tokens ( 7.48 ms per token, 133.64 tokens per second) 13.16.338.750 I slot print_timing: id 1 | task 15746 | eval time = 761.85 ms / 2 tokens ( 761.85 ms per token, 1.31 tokens per second) 13.16.338.750 I slot print_timing: id 1 | task 15746 | total time = 6598.28 ms / 782 tokens 13.16.338.750 I slot print_timing: id 1 | task 15746 | graphs reused = 14553 13.16.338.751 I slot print_timing: id 1 | task 15746 | graph reallocs = 0 / 0 (same size) / (changed size) 13.16.338.791 I slot release: id 1 | task 15746 | stop processing: n_tokens = 781, truncated = 0 13.16.338.800 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.871 (> 0.100 thold), f_keep = 0.879 13.16.338.878 I slot launch_slot_: id 2 | task 15757 | processing task, is_child = 0 13.16.348.266 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 275.391 MiB) 13.16.354.293 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.868 (> 0.100 thold), f_keep = 0.843 13.16.354.359 I slot launch_slot_: id 3 | task 15758 | processing task, is_child = 0 13.16.354.422 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 781, t_last = 353579232971 13.16.354.522 I slot launch_slot_: id 1 | task 15759 | processing task, is_child = 0 13.17.928.200 I slot print_timing: id 0 | task 15753 | prompt eval time = 3031.39 ms / 631 tokens ( 4.80 ms per token, 208.16 tokens per second) 13.17.928.206 I slot print_timing: id 0 | task 15753 | eval time = 80.16 ms / 2 tokens ( 80.16 ms per token, 12.48 tokens per second) 13.17.928.207 I slot print_timing: id 0 | task 15753 | total time = 3111.55 ms / 633 tokens 13.17.928.207 I slot print_timing: id 0 | task 15753 | graphs reused = 14553 13.17.928.208 I slot print_timing: id 0 | task 15753 | graph reallocs = 0 / 0 (same size) / (changed size) 13.17.928.247 I slot release: id 0 | task 15753 | stop processing: n_tokens = 632, truncated = 0 13.17.928.347 I slot print_timing: id 2 | task 15757 | prompt eval time = 1492.08 ms / 82 tokens ( 18.20 ms per token, 54.96 tokens per second) 13.17.928.352 I slot print_timing: id 2 | task 15757 | eval time = 80.19 ms / 2 tokens ( 80.19 ms per token, 12.47 tokens per second) 13.17.928.353 I slot print_timing: id 2 | task 15757 | total time = 1572.27 ms / 84 tokens 13.17.928.353 I slot print_timing: id 2 | task 15757 | graphs reused = 14553 13.17.928.353 I slot print_timing: id 2 | task 15757 | graph reallocs = 0 / 0 (same size) / (changed size) 13.17.928.375 I slot release: id 2 | task 15757 | stop processing: n_tokens = 635, truncated = 0 13.17.928.474 I slot print_timing: id 3 | task 15758 | prompt eval time = 1490.98 ms / 84 tokens ( 17.75 ms per token, 56.34 tokens per second) 13.17.928.476 I slot print_timing: id 3 | task 15758 | eval time = 80.19 ms / 2 tokens ( 80.19 ms per token, 12.47 tokens per second) 13.17.928.477 I slot print_timing: id 3 | task 15758 | total time = 1571.17 ms / 86 tokens 13.17.928.477 I slot print_timing: id 3 | task 15758 | graphs reused = 14553 13.17.928.477 I slot print_timing: id 3 | task 15758 | graph reallocs = 0 / 0 (same size) / (changed size) 13.17.928.495 I slot release: id 3 | task 15758 | stop processing: n_tokens = 637, truncated = 0 13.18.713.031 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 632, t_last = 353580822427 13.19.049.501 I slot launch_slot_: id 0 | task 15765 | processing task, is_child = 0 13.19.049.584 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 276.841 MiB) 13.19.069.319 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 635, t_last = 353580822555 13.19.069.443 I slot launch_slot_: id 2 | task 15766 | processing task, is_child = 0 13.19.069.505 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 353580822675 13.19.069.604 I slot launch_slot_: id 3 | task 15767 | processing task, is_child = 0 13.21.155.479 I slot print_timing: id 1 | task 15759 | prompt eval time = 3649.41 ms / 760 tokens ( 4.80 ms per token, 208.25 tokens per second) 13.21.155.482 I slot print_timing: id 1 | task 15759 | eval time = 1150.10 ms / 2 tokens ( 1150.10 ms per token, 0.87 tokens per second) 13.21.155.482 I slot print_timing: id 1 | task 15759 | total time = 4799.51 ms / 762 tokens 13.21.155.483 I slot print_timing: id 1 | task 15759 | graphs reused = 14553 13.21.155.483 I slot print_timing: id 1 | task 15759 | graph reallocs = 0 / 0 (same size) / (changed size) 13.21.155.519 I slot release: id 1 | task 15759 | stop processing: n_tokens = 761, truncated = 0 13.21.726.316 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 761, t_last = 353584049699 13.21.726.396 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 250.853 MiB) 13.21.846.145 I slot launch_slot_: id 1 | task 15771 | processing task, is_child = 0 13.24.121.053 I slot print_timing: id 0 | task 15765 | prompt processing, n_tokens = 741, progress = 0.87, t = 5.05 s / 146.69 tokens per second 13.24.242.029 I slot print_timing: id 2 | task 15766 | prompt processing, n_tokens = 741, progress = 0.85, t = 5.05 s / 146.73 tokens per second 13.24.244.410 I slot print_timing: id 3 | task 15767 | prompt processing, n_tokens = 741, progress = 0.83, t = 5.05 s / 146.73 tokens per second 13.25.603.176 I slot print_timing: id 0 | task 15765 | prompt processing, n_tokens = 848, progress = 1.00, t = 6.53 s / 129.79 tokens per second 13.25.725.069 I slot print_timing: id 1 | task 15771 | prompt processing, n_tokens = 298, progress = 0.35, t = 3.76 s / 79.36 tokens per second 13.25.725.079 I slot print_timing: id 2 | task 15766 | prompt processing, n_tokens = 867, progress = 1.00, t = 6.53 s / 132.73 tokens per second 13.25.727.559 I slot print_timing: id 3 | task 15767 | prompt processing, n_tokens = 889, progress = 1.00, t = 6.53 s / 136.10 tokens per second 13.26.070.721 I slot print_timing: id 1 | task 15771 | prompt processing, n_tokens = 345, progress = 0.40, t = 4.22 s / 81.71 tokens per second 13.26.881.709 I slot print_timing: id 0 | task 15765 | prompt eval time = 7000.80 ms / 852 tokens ( 8.22 ms per token, 121.70 tokens per second) 13.26.881.712 I slot print_timing: id 0 | task 15765 | eval time = 811.29 ms / 2 tokens ( 811.29 ms per token, 1.23 tokens per second) 13.26.881.713 I slot print_timing: id 0 | task 15765 | total time = 7812.10 ms / 854 tokens 13.26.881.713 I slot print_timing: id 0 | task 15765 | graphs reused = 14553 13.26.881.714 I slot print_timing: id 0 | task 15765 | graph reallocs = 0 / 0 (same size) / (changed size) 13.26.881.751 I slot release: id 0 | task 15765 | stop processing: n_tokens = 853, truncated = 0 13.26.881.891 I slot print_timing: id 2 | task 15766 | prompt eval time = 6999.66 ms / 871 tokens ( 8.04 ms per token, 124.43 tokens per second) 13.26.881.893 I slot print_timing: id 2 | task 15766 | eval time = 811.32 ms / 2 tokens ( 811.32 ms per token, 1.23 tokens per second) 13.26.881.894 I slot print_timing: id 2 | task 15766 | total time = 7810.98 ms / 873 tokens 13.26.881.894 I slot print_timing: id 2 | task 15766 | graphs reused = 14553 13.26.881.895 I slot print_timing: id 2 | task 15766 | graph reallocs = 0 / 0 (same size) / (changed size) 13.26.881.923 I slot release: id 2 | task 15766 | stop processing: n_tokens = 872, truncated = 0 13.26.882.060 I slot print_timing: id 3 | task 15767 | prompt eval time = 6999.72 ms / 893 tokens ( 7.84 ms per token, 127.58 tokens per second) 13.26.882.062 I slot print_timing: id 3 | task 15767 | eval time = 811.35 ms / 2 tokens ( 811.35 ms per token, 1.23 tokens per second) 13.26.882.062 I slot print_timing: id 3 | task 15767 | total time = 7811.07 ms / 895 tokens 13.26.882.062 I slot print_timing: id 3 | task 15767 | graphs reused = 14553 13.26.882.063 I slot print_timing: id 3 | task 15767 | graph reallocs = 0 / 0 (same size) / (changed size) 13.26.882.088 I slot release: id 3 | task 15767 | stop processing: n_tokens = 894, truncated = 0 13.26.882.096 I slot print_timing: id 1 | task 15771 | prompt processing, n_tokens = 741, progress = 0.86, t = 5.03 s / 147.21 tokens per second 13.26.889.837 I slot print_timing: id 1 | task 15771 | prompt processing, n_tokens = 857, progress = 1.00, t = 5.04 s / 169.98 tokens per second 13.27.309.185 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.892 (> 0.100 thold), f_keep = 0.898 13.27.309.257 I slot launch_slot_: id 0 | task 15778 | processing task, is_child = 0 13.27.309.335 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.794 MiB) 13.27.325.403 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 872, t_last = 353589776103 13.27.325.524 I slot launch_slot_: id 2 | task 15779 | processing task, is_child = 0 13.27.325.589 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 894, t_last = 353589776268 13.27.325.688 I slot launch_slot_: id 3 | task 15780 | processing task, is_child = 0 13.28.453.731 I slot print_timing: id 1 | task 15771 | prompt eval time = 5461.16 ms / 861 tokens ( 6.34 ms per token, 157.66 tokens per second) 13.28.453.737 I slot print_timing: id 1 | task 15771 | eval time = 1144.55 ms / 2 tokens ( 1144.55 ms per token, 0.87 tokens per second) 13.28.453.737 I slot print_timing: id 1 | task 15771 | total time = 6605.70 ms / 863 tokens 13.28.453.738 I slot print_timing: id 1 | task 15771 | graphs reused = 14553 13.28.453.738 I slot print_timing: id 1 | task 15771 | graph reallocs = 0 / 0 (same size) / (changed size) 13.28.453.778 I slot release: id 1 | task 15771 | stop processing: n_tokens = 862, truncated = 0 13.29.240.564 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 862, t_last = 353591347958 13.29.240.642 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 253.397 MiB) 13.29.248.157 I slot launch_slot_: id 1 | task 15783 | processing task, is_child = 0 13.30.733.036 I slot print_timing: id 0 | task 15778 | prompt eval time = 1914.86 ms / 93 tokens ( 20.59 ms per token, 48.57 tokens per second) 13.30.733.042 I slot print_timing: id 0 | task 15778 | eval time = 1492.47 ms / 2 tokens ( 1492.47 ms per token, 0.67 tokens per second) 13.30.733.042 I slot print_timing: id 0 | task 15778 | total time = 3407.34 ms / 95 tokens 13.30.733.043 I slot print_timing: id 0 | task 15778 | graphs reused = 14553 13.30.733.043 I slot print_timing: id 0 | task 15778 | graph reallocs = 0 / 0 (same size) / (changed size) 13.30.733.087 I slot release: id 0 | task 15778 | stop processing: n_tokens = 860, truncated = 0 13.30.733.389 I slot print_timing: id 2 | task 15779 | prompt processing, n_tokens = 617, progress = 0.83, t = 3.41 s / 181.15 tokens per second 13.30.735.374 I slot print_timing: id 3 | task 15780 | prompt processing, n_tokens = 390, progress = 0.43, t = 3.41 s / 114.51 tokens per second 13.31.671.872 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 860, t_last = 353593627267 13.31.671.972 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.797 MiB) 13.32.132.888 I slot launch_slot_: id 0 | task 15786 | processing task, is_child = 0 13.32.133.056 I slot print_timing: id 2 | task 15779 | prompt processing, n_tokens = 740, progress = 0.99, t = 4.34 s / 170.31 tokens per second 13.32.135.273 I slot print_timing: id 3 | task 15780 | prompt processing, n_tokens = 686, progress = 0.76, t = 4.34 s / 157.89 tokens per second 13.33.270.936 I slot print_timing: id 1 | task 15783 | prompt processing, n_tokens = 281, progress = 0.35, t = 4.02 s / 69.86 tokens per second 13.33.271.760 I slot print_timing: id 3 | task 15780 | prompt processing, n_tokens = 902, progress = 1.00, t = 5.94 s / 151.76 tokens per second 13.34.543.978 I slot print_timing: id 2 | task 15779 | prompt eval time = 5943.81 ms / 744 tokens ( 7.99 ms per token, 125.17 tokens per second) 13.34.543.981 I slot print_timing: id 2 | task 15779 | eval time = 1273.30 ms / 2 tokens ( 1273.30 ms per token, 0.79 tokens per second) 13.34.543.982 I slot print_timing: id 2 | task 15779 | total time = 7217.10 ms / 746 tokens 13.34.543.982 I slot print_timing: id 2 | task 15779 | graphs reused = 14553 13.34.543.983 I slot print_timing: id 2 | task 15779 | graph reallocs = 0 / 0 (same size) / (changed size) 13.34.544.022 I slot release: id 2 | task 15779 | stop processing: n_tokens = 745, truncated = 0 13.34.544.150 I slot print_timing: id 1 | task 15783 | prompt processing, n_tokens = 686, progress = 0.86, t = 5.30 s / 129.54 tokens per second 13.35.163.107 I slot print_timing: id 3 | task 15780 | prompt eval time = 7217.15 ms / 906 tokens ( 7.97 ms per token, 125.53 tokens per second) 13.35.163.113 I slot print_timing: id 3 | task 15780 | eval time = 618.97 ms / 2 tokens ( 618.97 ms per token, 1.62 tokens per second) 13.35.163.113 I slot print_timing: id 3 | task 15780 | total time = 7836.12 ms / 908 tokens 13.35.163.114 I slot print_timing: id 3 | task 15780 | graphs reused = 14553 13.35.163.114 I slot print_timing: id 3 | task 15780 | graph reallocs = 0 / 0 (same size) / (changed size) 13.35.163.153 I slot release: id 3 | task 15780 | stop processing: n_tokens = 907, truncated = 0 13.35.163.161 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.890 (> 0.100 thold), f_keep = 0.784 13.35.163.238 I slot launch_slot_: id 3 | task 15790 | processing task, is_child = 0 13.35.174.904 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 745, t_last = 353597438202 13.35.175.034 I slot launch_slot_: id 2 | task 15791 | processing task, is_child = 0 13.35.175.042 I slot print_timing: id 0 | task 15786 | prompt processing, n_tokens = 378, progress = 0.42, t = 3.03 s / 124.75 tokens per second 13.35.176.819 I slot print_timing: id 1 | task 15783 | prompt processing, n_tokens = 793, progress = 0.99, t = 5.91 s / 134.07 tokens per second 13.36.402.081 I slot print_timing: id 0 | task 15786 | prompt processing, n_tokens = 686, progress = 0.77, t = 4.27 s / 160.69 tokens per second 13.37.438.262 I slot print_timing: id 1 | task 15783 | prompt eval time = 7153.89 ms / 797 tokens ( 8.98 ms per token, 111.41 tokens per second) 13.37.438.265 I slot print_timing: id 1 | task 15783 | eval time = 1036.20 ms / 2 tokens ( 1036.20 ms per token, 0.97 tokens per second) 13.37.438.266 I slot print_timing: id 1 | task 15783 | total time = 8190.09 ms / 799 tokens 13.37.438.266 I slot print_timing: id 1 | task 15783 | graphs reused = 14553 13.37.438.267 I slot print_timing: id 1 | task 15783 | graph reallocs = 0 / 0 (same size) / (changed size) 13.37.438.308 I slot release: id 1 | task 15783 | stop processing: n_tokens = 798, truncated = 0 13.37.438.466 I slot print_timing: id 0 | task 15786 | prompt processing, n_tokens = 890, progress = 1.00, t = 5.31 s / 167.76 tokens per second 13.37.823.583 I slot print_timing: id 3 | task 15790 | prompt eval time = 2259.83 ms / 88 tokens ( 25.68 ms per token, 38.94 tokens per second) 13.37.823.587 I slot print_timing: id 3 | task 15790 | eval time = 385.12 ms / 2 tokens ( 385.12 ms per token, 2.60 tokens per second) 13.37.823.588 I slot print_timing: id 3 | task 15790 | total time = 2644.95 ms / 90 tokens 13.37.823.588 I slot print_timing: id 3 | task 15790 | graphs reused = 14553 13.37.823.589 I slot print_timing: id 3 | task 15790 | graph reallocs = 0 / 0 (same size) / (changed size) 13.37.823.625 I slot release: id 3 | task 15790 | stop processing: n_tokens = 800, truncated = 0 13.37.823.632 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.891 13.37.823.705 I slot launch_slot_: id 1 | task 15795 | processing task, is_child = 0 13.37.823.784 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 275.719 MiB) 13.37.834.084 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 800, t_last = 353600717805 13.37.834.197 I slot launch_slot_: id 3 | task 15796 | processing task, is_child = 0 13.39.196.353 I slot print_timing: id 0 | task 15786 | prompt eval time = 5690.56 ms / 894 tokens ( 6.37 ms per token, 157.10 tokens per second) 13.39.196.359 I slot print_timing: id 0 | task 15786 | eval time = 1372.88 ms / 2 tokens ( 1372.88 ms per token, 0.73 tokens per second) 13.39.196.360 I slot print_timing: id 0 | task 15786 | total time = 7063.45 ms / 896 tokens 13.39.196.360 I slot print_timing: id 0 | task 15786 | graphs reused = 14553 13.39.196.361 I slot print_timing: id 0 | task 15786 | graph reallocs = 0 / 0 (same size) / (changed size) 13.39.196.407 I slot release: id 0 | task 15786 | stop processing: n_tokens = 895, truncated = 0 13.39.198.449 I slot print_timing: id 2 | task 15791 | prompt processing, n_tokens = 686, progress = 0.79, t = 4.02 s / 170.75 tokens per second 13.40.100.825 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 895, t_last = 353602090587 13.40.111.755 I slot launch_slot_: id 0 | task 15799 | processing task, is_child = 0 13.40.111.886 I slot print_timing: id 2 | task 15791 | prompt processing, n_tokens = 859, progress = 1.00, t = 4.92 s / 174.52 tokens per second 13.40.912.006 I slot print_timing: id 1 | task 15795 | prompt eval time = 2266.61 ms / 74 tokens ( 30.63 ms per token, 32.65 tokens per second) 13.40.912.010 I slot print_timing: id 1 | task 15795 | eval time = 811.18 ms / 2 tokens ( 811.18 ms per token, 1.23 tokens per second) 13.40.912.011 I slot print_timing: id 1 | task 15795 | total time = 3077.80 ms / 76 tokens 13.40.912.011 I slot print_timing: id 1 | task 15795 | graphs reused = 14553 13.40.912.012 I slot print_timing: id 1 | task 15795 | graph reallocs = 0 / 0 (same size) / (changed size) 13.40.912.050 I slot release: id 1 | task 15795 | stop processing: n_tokens = 786, truncated = 0 13.40.912.470 I slot print_timing: id 3 | task 15796 | prompt processing, n_tokens = 325, progress = 0.39, t = 3.08 s / 105.67 tokens per second 13.41.978.073 I slot print_timing: id 2 | task 15791 | prompt eval time = 5733.65 ms / 863 tokens ( 6.64 ms per token, 150.51 tokens per second) 13.41.978.078 I slot print_timing: id 2 | task 15791 | eval time = 1065.88 ms / 2 tokens ( 1065.88 ms per token, 0.94 tokens per second) 13.41.978.078 I slot print_timing: id 2 | task 15791 | total time = 6799.53 ms / 865 tokens 13.41.978.079 I slot print_timing: id 2 | task 15791 | graphs reused = 14553 13.41.978.079 I slot print_timing: id 2 | task 15791 | graph reallocs = 0 / 0 (same size) / (changed size) 13.41.978.123 I slot release: id 2 | task 15791 | stop processing: n_tokens = 864, truncated = 0 13.41.978.130 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 786, t_last = 353603806230 13.41.978.207 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.698 MiB) 13.41.987.729 I slot launch_slot_: id 1 | task 15802 | processing task, is_child = 0 13.41.995.312 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 864, t_last = 353604872303 13.41.995.430 I slot launch_slot_: id 2 | task 15803 | processing task, is_child = 0 13.41.995.646 I slot print_timing: id 3 | task 15796 | prompt processing, n_tokens = 678, progress = 0.81, t = 4.14 s / 163.70 tokens per second 13.43.307.954 I slot print_timing: id 3 | task 15796 | prompt processing, n_tokens = 837, progress = 1.00, t = 5.08 s / 164.71 tokens per second 13.45.057.726 I slot print_timing: id 0 | task 15799 | prompt processing, n_tokens = 678, progress = 0.85, t = 4.95 s / 137.09 tokens per second 13.45.059.255 I slot print_timing: id 1 | task 15802 | prompt processing, n_tokens = 202, progress = 0.24, t = 3.06 s / 65.97 tokens per second 13.45.059.268 I slot print_timing: id 2 | task 15803 | prompt processing, n_tokens = 393, progress = 0.33, t = 3.06 s / 128.35 tokens per second 13.46.264.350 I slot print_timing: id 3 | task 15796 | prompt eval time = 7221.52 ms / 841 tokens ( 8.59 ms per token, 116.46 tokens per second) 13.46.264.355 I slot print_timing: id 3 | task 15796 | eval time = 1206.63 ms / 2 tokens ( 1206.63 ms per token, 0.83 tokens per second) 13.46.264.356 I slot print_timing: id 3 | task 15796 | total time = 8428.16 ms / 843 tokens 13.46.264.356 I slot print_timing: id 3 | task 15796 | graphs reused = 14553 13.46.264.357 I slot print_timing: id 3 | task 15796 | graph reallocs = 0 / 0 (same size) / (changed size) 13.46.264.396 I slot release: id 3 | task 15796 | stop processing: n_tokens = 842, truncated = 0 13.46.264.408 I slot print_timing: id 0 | task 15799 | prompt processing, n_tokens = 794, progress = 0.99, t = 6.15 s / 129.05 tokens per second 13.46.266.255 I slot print_timing: id 1 | task 15802 | prompt processing, n_tokens = 313, progress = 0.38, t = 4.27 s / 73.32 tokens per second 13.46.267.145 I slot print_timing: id 2 | task 15803 | prompt processing, n_tokens = 686, progress = 0.57, t = 4.27 s / 160.71 tokens per second 13.47.831.595 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 842, t_last = 353609158576 13.47.831.681 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 276.102 MiB) 13.47.840.841 I slot launch_slot_: id 3 | task 15808 | processing task, is_child = 0 13.47.840.854 I slot print_timing: id 1 | task 15802 | prompt processing, n_tokens = 678, progress = 0.82, t = 5.84 s / 116.18 tokens per second 13.47.842.361 I slot print_timing: id 2 | task 15803 | prompt processing, n_tokens = 1028, progress = 0.86, t = 5.84 s / 176.15 tokens per second 13.48.896.589 I slot print_timing: id 0 | task 15799 | prompt eval time = 7719.82 ms / 798 tokens ( 9.67 ms per token, 103.37 tokens per second) 13.48.896.593 I slot print_timing: id 0 | task 15799 | eval time = 1064.99 ms / 2 tokens ( 1064.99 ms per token, 0.94 tokens per second) 13.48.896.593 I slot print_timing: id 0 | task 15799 | total time = 8784.82 ms / 800 tokens 13.48.896.594 I slot print_timing: id 0 | task 15799 | graphs reused = 14553 13.48.896.594 I slot print_timing: id 0 | task 15799 | graph reallocs = 0 / 0 (same size) / (changed size) 13.48.896.635 I slot release: id 0 | task 15799 | stop processing: n_tokens = 799, truncated = 0 13.48.896.647 I slot print_timing: id 1 | task 15802 | prompt processing, n_tokens = 825, progress = 1.00, t = 6.90 s / 119.55 tokens per second 13.48.898.577 I slot print_timing: id 2 | task 15803 | prompt processing, n_tokens = 1198, progress = 1.00, t = 6.90 s / 173.60 tokens per second 13.49.520.464 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 799, t_last = 353611790815 13.49.520.542 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 276.102 MiB) 13.49.529.116 I slot launch_slot_: id 0 | task 15811 | processing task, is_child = 0 13.50.627.811 I slot print_timing: id 1 | task 15802 | prompt eval time = 7524.88 ms / 829 tokens ( 9.08 ms per token, 110.17 tokens per second) 13.50.627.818 I slot print_timing: id 1 | task 15802 | eval time = 1107.48 ms / 2 tokens ( 1107.48 ms per token, 0.90 tokens per second) 13.50.627.818 I slot print_timing: id 1 | task 15802 | total time = 8632.36 ms / 831 tokens 13.50.627.819 I slot print_timing: id 1 | task 15802 | graphs reused = 14553 13.50.627.819 I slot print_timing: id 1 | task 15802 | graph reallocs = 0 / 0 (same size) / (changed size) 13.50.627.860 I slot release: id 1 | task 15802 | stop processing: n_tokens = 830, truncated = 0 13.50.628.016 I slot print_timing: id 2 | task 15803 | prompt eval time = 7524.91 ms / 1202 tokens ( 6.26 ms per token, 159.74 tokens per second) 13.50.628.020 I slot print_timing: id 2 | task 15803 | eval time = 1107.56 ms / 2 tokens ( 1107.56 ms per token, 0.90 tokens per second) 13.50.628.020 I slot print_timing: id 2 | task 15803 | total time = 8632.47 ms / 1204 tokens 13.50.628.020 I slot print_timing: id 2 | task 15803 | graphs reused = 14553 13.50.628.021 I slot print_timing: id 2 | task 15803 | graph reallocs = 0 / 0 (same size) / (changed size) 13.50.628.074 I slot release: id 2 | task 15803 | stop processing: n_tokens = 1203, truncated = 0 13.51.179.117 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 830, t_last = 353613522041 13.51.864.131 I slot launch_slot_: id 1 | task 15814 | processing task, is_child = 0 13.51.864.228 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 277.142 MiB) 13.51.871.912 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.875 13.51.871.968 I slot launch_slot_: id 2 | task 15815 | processing task, is_child = 0 13.51.873.238 I slot print_timing: id 3 | task 15808 | prompt processing, n_tokens = 1028, progress = 0.85, t = 3.34 s / 308.22 tokens per second 13.53.207.115 I slot print_timing: id 0 | task 15811 | prompt processing, n_tokens = 609, progress = 0.54, t = 3.68 s / 165.58 tokens per second 13.53.527.043 I slot print_timing: id 3 | task 15808 | prompt processing, n_tokens = 1204, progress = 1.00, t = 5.36 s / 224.49 tokens per second 13.54.722.065 I slot print_timing: id 0 | task 15811 | prompt processing, n_tokens = 1028, progress = 0.91, t = 5.19 s / 197.97 tokens per second 13.55.894.023 I slot print_timing: id 2 | task 15815 | prompt eval time = 2849.82 ms / 109 tokens ( 26.15 ms per token, 38.25 tokens per second) 13.55.894.025 I slot print_timing: id 2 | task 15815 | eval time = 1172.09 ms / 2 tokens ( 1172.09 ms per token, 0.85 tokens per second) 13.55.894.027 I slot print_timing: id 2 | task 15815 | total time = 4021.90 ms / 111 tokens 13.55.894.027 I slot print_timing: id 2 | task 15815 | graphs reused = 14553 13.55.894.028 I slot print_timing: id 2 | task 15815 | graph reallocs = 0 / 0 (same size) / (changed size) 13.55.894.076 I slot release: id 2 | task 15815 | stop processing: n_tokens = 1163, truncated = 0 13.55.894.232 I slot print_timing: id 3 | task 15808 | prompt eval time = 6878.27 ms / 1208 tokens ( 5.69 ms per token, 175.63 tokens per second) 13.55.894.235 I slot print_timing: id 3 | task 15808 | eval time = 1172.18 ms / 2 tokens ( 1172.18 ms per token, 0.85 tokens per second) 13.55.894.235 I slot print_timing: id 3 | task 15808 | total time = 8050.45 ms / 1210 tokens 13.55.894.235 I slot print_timing: id 3 | task 15808 | graphs reused = 14553 13.55.894.236 I slot print_timing: id 3 | task 15808 | graph reallocs = 0 / 0 (same size) / (changed size) 13.55.894.271 I slot release: id 3 | task 15808 | stop processing: n_tokens = 1209, truncated = 0 13.55.894.280 I slot print_timing: id 0 | task 15811 | prompt processing, n_tokens = 1121, progress = 1.00, t = 6.36 s / 176.13 tokens per second 13.55.896.666 I slot print_timing: id 1 | task 15814 | prompt processing, n_tokens = 593, progress = 0.86, t = 4.02 s / 147.44 tokens per second 13.56.283.860 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1163, t_last = 353618788256 13.56.283.969 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 275.336 MiB) 13.56.294.079 I slot launch_slot_: id 2 | task 15820 | processing task, is_child = 0 13.56.307.818 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1209, t_last = 353618788451 13.56.307.956 I slot launch_slot_: id 3 | task 15821 | processing task, is_child = 0 13.56.307.964 I slot print_timing: id 1 | task 15814 | prompt processing, n_tokens = 686, progress = 0.99, t = 4.41 s / 155.50 tokens per second 13.57.011.954 I slot print_timing: id 0 | task 15811 | prompt eval time = 6754.73 ms / 1125 tokens ( 6.00 ms per token, 166.55 tokens per second) 13.57.011.956 I slot print_timing: id 0 | task 15811 | eval time = 728.10 ms / 2 tokens ( 728.10 ms per token, 1.37 tokens per second) 13.57.011.958 I slot print_timing: id 0 | task 15811 | total time = 7482.83 ms / 1127 tokens 13.57.011.958 I slot print_timing: id 0 | task 15811 | graphs reused = 14553 13.57.011.958 I slot print_timing: id 0 | task 15811 | graph reallocs = 0 / 0 (same size) / (changed size) 13.57.012.009 I slot release: id 0 | task 15811 | stop processing: n_tokens = 1126, truncated = 0 13.57.700.281 I slot print_timing: id 1 | task 15814 | prompt eval time = 5140.15 ms / 690 tokens ( 7.45 ms per token, 134.24 tokens per second) 13.57.700.287 I slot print_timing: id 1 | task 15814 | eval time = 688.14 ms / 2 tokens ( 688.14 ms per token, 1.45 tokens per second) 13.57.700.287 I slot print_timing: id 1 | task 15814 | total time = 5828.29 ms / 692 tokens 13.57.700.288 I slot print_timing: id 1 | task 15814 | graphs reused = 14553 13.57.700.288 I slot print_timing: id 1 | task 15814 | graph reallocs = 0 / 0 (same size) / (changed size) 13.57.700.320 I slot release: id 1 | task 15814 | stop processing: n_tokens = 691, truncated = 0 13.57.700.327 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1126, t_last = 353619906189 13.57.700.422 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 311.259 MiB) 13.57.709.761 I slot launch_slot_: id 0 | task 15824 | processing task, is_child = 0 13.57.718.400 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 691, t_last = 353620594500 13.57.718.520 I slot launch_slot_: id 1 | task 15825 | processing task, is_child = 0 14.01.163.045 I slot print_timing: id 2 | task 15820 | prompt processing, n_tokens = 704, progress = 0.99, t = 4.26 s / 165.43 tokens per second 14.01.164.942 I slot print_timing: id 3 | task 15821 | prompt processing, n_tokens = 661, progress = 0.83, t = 4.26 s / 155.33 tokens per second 14.03.242.640 I slot print_timing: id 0 | task 15824 | prompt processing, n_tokens = 661, progress = 0.86, t = 5.52 s / 119.66 tokens per second 14.03.244.317 I slot print_timing: id 1 | task 15825 | prompt processing, n_tokens = 577, progress = 0.82, t = 5.52 s / 104.46 tokens per second 14.03.245.785 I slot print_timing: id 3 | task 15821 | prompt processing, n_tokens = 797, progress = 1.00, t = 6.93 s / 114.99 tokens per second 14.03.936.679 I slot print_timing: id 2 | task 15820 | prompt eval time = 6931.47 ms / 708 tokens ( 9.79 ms per token, 102.14 tokens per second) 14.03.936.682 I slot print_timing: id 2 | task 15820 | eval time = 694.04 ms / 2 tokens ( 694.04 ms per token, 1.44 tokens per second) 14.03.936.683 I slot print_timing: id 2 | task 15820 | total time = 7625.52 ms / 710 tokens 14.03.936.683 I slot print_timing: id 2 | task 15820 | graphs reused = 14553 14.03.936.684 I slot print_timing: id 2 | task 15820 | graph reallocs = 0 / 0 (same size) / (changed size) 14.03.936.725 I slot release: id 2 | task 15820 | stop processing: n_tokens = 709, truncated = 0 14.03.936.878 I slot print_timing: id 0 | task 15824 | prompt processing, n_tokens = 765, progress = 0.99, t = 6.22 s / 123.03 tokens per second 14.03.938.288 I slot print_timing: id 1 | task 15825 | prompt processing, n_tokens = 698, progress = 0.99, t = 6.22 s / 112.26 tokens per second 14.04.018.685 I slot print_timing: id 3 | task 15821 | prompt eval time = 7625.56 ms / 801 tokens ( 9.52 ms per token, 105.04 tokens per second) 14.04.018.690 I slot print_timing: id 3 | task 15821 | eval time = 81.81 ms / 2 tokens ( 81.81 ms per token, 12.22 tokens per second) 14.04.018.690 I slot print_timing: id 3 | task 15821 | total time = 7707.38 ms / 803 tokens 14.04.018.691 I slot print_timing: id 3 | task 15821 | graphs reused = 14553 14.04.018.691 I slot print_timing: id 3 | task 15821 | graph reallocs = 0 / 0 (same size) / (changed size) 14.04.018.742 I slot release: id 3 | task 15821 | stop processing: n_tokens = 802, truncated = 0 14.04.018.748 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 709, t_last = 353626830905 14.04.018.829 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 275.473 MiB) 14.04.022.926 I slot launch_slot_: id 2 | task 15831 | processing task, is_child = 0 14.04.030.932 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 802, t_last = 353626912922 14.04.031.051 I slot launch_slot_: id 3 | task 15832 | processing task, is_child = 0 14.04.612.247 I slot print_timing: id 0 | task 15824 | prompt eval time = 6299.97 ms / 769 tokens ( 8.19 ms per token, 122.06 tokens per second) 14.04.612.250 I slot print_timing: id 0 | task 15824 | eval time = 593.74 ms / 2 tokens ( 593.74 ms per token, 1.68 tokens per second) 14.04.612.250 I slot print_timing: id 0 | task 15824 | total time = 6893.72 ms / 771 tokens 14.04.612.251 I slot print_timing: id 0 | task 15824 | graphs reused = 14553 14.04.612.251 I slot print_timing: id 0 | task 15824 | graph reallocs = 0 / 0 (same size) / (changed size) 14.04.612.287 I slot release: id 0 | task 15824 | stop processing: n_tokens = 770, truncated = 0 14.04.612.436 I slot print_timing: id 1 | task 15825 | prompt eval time = 6299.92 ms / 702 tokens ( 8.97 ms per token, 111.43 tokens per second) 14.04.612.440 I slot print_timing: id 1 | task 15825 | eval time = 593.84 ms / 2 tokens ( 593.84 ms per token, 1.68 tokens per second) 14.04.612.441 I slot print_timing: id 1 | task 15825 | total time = 6893.76 ms / 704 tokens 14.04.612.441 I slot print_timing: id 1 | task 15825 | graphs reused = 14553 14.04.612.442 I slot print_timing: id 1 | task 15825 | graph reallocs = 0 / 0 (same size) / (changed size) 14.04.612.472 I slot release: id 1 | task 15825 | stop processing: n_tokens = 703, truncated = 0 14.04.823.930 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.883 (> 0.100 thold), f_keep = 0.856 14.04.824.003 I slot launch_slot_: id 1 | task 15835 | processing task, is_child = 0 14.04.824.077 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.808 MiB) 14.05.082.584 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 770, t_last = 353627506467 14.05.082.733 I slot launch_slot_: id 0 | task 15836 | processing task, is_child = 0 14.08.397.008 I slot print_timing: id 0 | task 15836 | prompt processing, n_tokens = 194, progress = 0.27, t = 3.31 s / 58.54 tokens per second 14.08.397.515 I slot print_timing: id 2 | task 15831 | prompt processing, n_tokens = 746, progress = 0.99, t = 4.37 s / 170.87 tokens per second 14.08.399.776 I slot print_timing: id 3 | task 15832 | prompt processing, n_tokens = 683, progress = 0.99, t = 4.37 s / 156.45 tokens per second 14.09.190.177 I slot print_timing: id 1 | task 15835 | prompt eval time = 3314.14 ms / 80 tokens ( 41.43 ms per token, 24.14 tokens per second) 14.09.190.182 I slot print_timing: id 1 | task 15835 | eval time = 793.18 ms / 2 tokens ( 793.18 ms per token, 1.26 tokens per second) 14.09.190.182 I slot print_timing: id 1 | task 15835 | total time = 4107.32 ms / 82 tokens 14.09.190.183 I slot print_timing: id 1 | task 15835 | graphs reused = 14553 14.09.190.183 I slot print_timing: id 1 | task 15835 | graph reallocs = 0 / 0 (same size) / (changed size) 14.09.190.217 I slot release: id 1 | task 15835 | stop processing: n_tokens = 683, truncated = 0 14.09.190.470 I slot print_timing: id 0 | task 15836 | prompt processing, n_tokens = 577, progress = 0.81, t = 4.11 s / 140.48 tokens per second 14.09.644.202 I slot print_timing: id 2 | task 15831 | prompt eval time = 5159.27 ms / 750 tokens ( 6.88 ms per token, 145.37 tokens per second) 14.09.644.205 I slot print_timing: id 2 | task 15831 | eval time = 453.87 ms / 2 tokens ( 453.87 ms per token, 2.20 tokens per second) 14.09.644.206 I slot print_timing: id 2 | task 15831 | total time = 5613.14 ms / 752 tokens 14.09.644.206 I slot print_timing: id 2 | task 15831 | graphs reused = 14553 14.09.644.207 I slot print_timing: id 2 | task 15831 | graph reallocs = 0 / 0 (same size) / (changed size) 14.09.644.244 I slot release: id 2 | task 15831 | stop processing: n_tokens = 751, truncated = 0 14.09.644.381 I slot print_timing: id 3 | task 15832 | prompt eval time = 5159.31 ms / 687 tokens ( 7.51 ms per token, 133.16 tokens per second) 14.09.644.383 I slot print_timing: id 3 | task 15832 | eval time = 453.92 ms / 2 tokens ( 453.92 ms per token, 2.20 tokens per second) 14.09.644.383 I slot print_timing: id 3 | task 15832 | total time = 5613.23 ms / 689 tokens 14.09.644.384 I slot print_timing: id 3 | task 15832 | graphs reused = 14553 14.09.644.384 I slot print_timing: id 3 | task 15832 | graph reallocs = 0 / 0 (same size) / (changed size) 14.09.644.410 I slot release: id 3 | task 15832 | stop processing: n_tokens = 688, truncated = 0 14.09.644.416 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 683, t_last = 353632084397 14.09.653.872 I slot launch_slot_: id 1 | task 15841 | processing task, is_child = 0 14.09.653.944 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.762 MiB) 14.09.657.829 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 289.225 MiB) 14.09.662.428 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 751, t_last = 353632538424 14.09.662.552 I slot launch_slot_: id 2 | task 15842 | processing task, is_child = 0 14.09.662.609 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 688, t_last = 353632538590 14.09.662.704 I slot launch_slot_: id 3 | task 15843 | processing task, is_child = 0 14.09.662.710 I slot print_timing: id 0 | task 15836 | prompt processing, n_tokens = 706, progress = 0.99, t = 4.56 s / 154.78 tokens per second 14.11.221.242 I slot print_timing: id 0 | task 15836 | prompt eval time = 5448.99 ms / 710 tokens ( 7.67 ms per token, 130.30 tokens per second) 14.11.221.245 I slot print_timing: id 0 | task 15836 | eval time = 689.50 ms / 2 tokens ( 689.50 ms per token, 1.45 tokens per second) 14.11.221.245 I slot print_timing: id 0 | task 15836 | total time = 6138.50 ms / 712 tokens 14.11.221.246 I slot print_timing: id 0 | task 15836 | graphs reused = 14553 14.11.221.246 I slot print_timing: id 0 | task 15836 | graph reallocs = 0 / 0 (same size) / (changed size) 14.11.221.288 I slot release: id 0 | task 15836 | stop processing: n_tokens = 711, truncated = 0 14.11.405.951 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 711, t_last = 353634115468 14.11.525.447 I slot launch_slot_: id 0 | task 15847 | processing task, is_child = 0 14.14.232.085 I slot print_timing: id 1 | task 15841 | prompt processing, n_tokens = 719, progress = 0.87, t = 4.46 s / 161.27 tokens per second 14.14.233.845 I slot print_timing: id 2 | task 15842 | prompt processing, n_tokens = 719, progress = 0.88, t = 4.46 s / 161.27 tokens per second 14.14.235.151 I slot print_timing: id 3 | task 15843 | prompt processing, n_tokens = 719, progress = 0.86, t = 4.46 s / 161.28 tokens per second 14.15.289.874 I slot print_timing: id 0 | task 15847 | prompt processing, n_tokens = 294, progress = 0.36, t = 3.76 s / 78.10 tokens per second 14.15.289.890 I slot print_timing: id 1 | task 15841 | prompt processing, n_tokens = 827, progress = 1.00, t = 5.63 s / 147.00 tokens per second 14.15.411.434 I slot print_timing: id 2 | task 15842 | prompt processing, n_tokens = 810, progress = 1.00, t = 5.63 s / 143.98 tokens per second 14.15.412.929 I slot print_timing: id 3 | task 15843 | prompt processing, n_tokens = 832, progress = 1.00, t = 5.63 s / 147.89 tokens per second 14.15.548.468 I slot print_timing: id 0 | task 15847 | prompt processing, n_tokens = 302, progress = 0.37, t = 4.02 s / 75.08 tokens per second 14.16.363.954 I slot print_timing: id 1 | task 15841 | prompt eval time = 5884.29 ms / 831 tokens ( 7.08 ms per token, 141.22 tokens per second) 14.16.363.959 I slot print_timing: id 1 | task 15841 | eval time = 815.72 ms / 2 tokens ( 815.72 ms per token, 1.23 tokens per second) 14.16.363.960 I slot print_timing: id 1 | task 15841 | total time = 6700.01 ms / 833 tokens 14.16.363.960 I slot print_timing: id 1 | task 15841 | graphs reused = 14553 14.16.363.961 I slot print_timing: id 1 | task 15841 | graph reallocs = 0 / 0 (same size) / (changed size) 14.16.363.998 I slot release: id 1 | task 15841 | stop processing: n_tokens = 832, truncated = 0 14.16.364.123 I slot print_timing: id 2 | task 15842 | prompt eval time = 5884.29 ms / 814 tokens ( 7.23 ms per token, 138.33 tokens per second) 14.16.364.125 I slot print_timing: id 2 | task 15842 | eval time = 815.79 ms / 2 tokens ( 815.79 ms per token, 1.23 tokens per second) 14.16.364.125 I slot print_timing: id 2 | task 15842 | total time = 6700.08 ms / 816 tokens 14.16.364.125 I slot print_timing: id 2 | task 15842 | graphs reused = 14553 14.16.364.126 I slot print_timing: id 2 | task 15842 | graph reallocs = 0 / 0 (same size) / (changed size) 14.16.364.152 I slot release: id 2 | task 15842 | stop processing: n_tokens = 815, truncated = 0 14.16.364.307 I slot print_timing: id 3 | task 15843 | prompt eval time = 5884.33 ms / 836 tokens ( 7.04 ms per token, 142.07 tokens per second) 14.16.364.311 I slot print_timing: id 3 | task 15843 | eval time = 815.85 ms / 2 tokens ( 815.85 ms per token, 1.23 tokens per second) 14.16.364.316 I slot print_timing: id 3 | task 15843 | total time = 6700.17 ms / 838 tokens 14.16.364.316 I slot print_timing: id 3 | task 15843 | graphs reused = 14553 14.16.364.316 I slot print_timing: id 3 | task 15843 | graph reallocs = 0 / 0 (same size) / (changed size) 14.16.364.339 I slot release: id 3 | task 15843 | stop processing: n_tokens = 837, truncated = 0 14.16.364.346 I slot print_timing: id 0 | task 15847 | prompt processing, n_tokens = 719, progress = 0.88, t = 4.84 s / 148.60 tokens per second 14.16.371.718 I slot print_timing: id 0 | task 15847 | prompt processing, n_tokens = 814, progress = 1.00, t = 4.85 s / 167.96 tokens per second 14.16.747.662 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 832, t_last = 353639258178 14.16.747.742 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 277.005 MiB) 14.16.754.700 I slot launch_slot_: id 1 | task 15854 | processing task, is_child = 0 14.16.762.861 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 323.192 MiB) 14.16.769.463 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 815, t_last = 353639258332 14.16.769.578 I slot launch_slot_: id 2 | task 15855 | processing task, is_child = 0 14.16.769.642 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.894 (> 0.100 thold), f_keep = 0.889 14.16.769.682 I slot launch_slot_: id 3 | task 15856 | processing task, is_child = 0 14.17.686.091 I slot print_timing: id 0 | task 15847 | prompt eval time = 5222.20 ms / 818 tokens ( 6.38 ms per token, 156.64 tokens per second) 14.17.686.096 I slot print_timing: id 0 | task 15847 | eval time = 938.43 ms / 2 tokens ( 938.43 ms per token, 1.07 tokens per second) 14.17.686.096 I slot print_timing: id 0 | task 15847 | total time = 6160.63 ms / 820 tokens 14.17.686.097 I slot print_timing: id 0 | task 15847 | graphs reused = 14553 14.17.686.097 I slot print_timing: id 0 | task 15847 | graph reallocs = 0 / 0 (same size) / (changed size) 14.17.686.136 I slot release: id 0 | task 15847 | stop processing: n_tokens = 819, truncated = 0 14.18.057.309 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 819, t_last = 353640580316 14.18.067.122 I slot launch_slot_: id 0 | task 15859 | processing task, is_child = 0 14.19.863.311 I slot print_timing: id 3 | task 15856 | prompt eval time = 1287.41 ms / 88 tokens ( 14.63 ms per token, 68.35 tokens per second) 14.19.863.314 I slot print_timing: id 3 | task 15856 | eval time = 1806.00 ms / 2 tokens ( 1806.00 ms per token, 0.55 tokens per second) 14.19.863.315 I slot print_timing: id 3 | task 15856 | total time = 3093.41 ms / 90 tokens 14.19.863.315 I slot print_timing: id 3 | task 15856 | graphs reused = 14553 14.19.863.315 I slot print_timing: id 3 | task 15856 | graph reallocs = 0 / 0 (same size) / (changed size) 14.19.863.354 I slot release: id 3 | task 15856 | stop processing: n_tokens = 833, truncated = 0 14.19.863.717 I slot print_timing: id 1 | task 15854 | prompt processing, n_tokens = 599, progress = 0.85, t = 3.09 s / 193.63 tokens per second 14.19.866.211 I slot print_timing: id 2 | task 15855 | prompt processing, n_tokens = 599, progress = 0.85, t = 3.09 s / 193.64 tokens per second 14.20.539.927 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 833, t_last = 353642757534 14.20.540.020 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 143.574 MiB) 14.20.841.846 I slot launch_slot_: id 3 | task 15862 | processing task, is_child = 0 14.20.841.868 I slot print_timing: id 1 | task 15854 | prompt processing, n_tokens = 702, progress = 0.99, t = 3.77 s / 186.20 tokens per second 14.20.844.500 I slot print_timing: id 2 | task 15855 | prompt processing, n_tokens = 700, progress = 0.99, t = 3.77 s / 185.67 tokens per second 14.21.568.681 I slot print_timing: id 0 | task 15859 | prompt processing, n_tokens = 355, progress = 0.41, t = 3.50 s / 101.39 tokens per second 14.22.783.925 I slot print_timing: id 1 | task 15854 | prompt eval time = 4798.84 ms / 706 tokens ( 6.80 ms per token, 147.12 tokens per second) 14.22.783.931 I slot print_timing: id 1 | task 15854 | eval time = 1215.39 ms / 2 tokens ( 1215.39 ms per token, 0.82 tokens per second) 14.22.783.932 I slot print_timing: id 1 | task 15854 | total time = 6014.23 ms / 708 tokens 14.22.783.932 I slot print_timing: id 1 | task 15854 | graphs reused = 14553 14.22.783.933 I slot print_timing: id 1 | task 15854 | graph reallocs = 0 / 0 (same size) / (changed size) 14.22.783.965 I slot release: id 1 | task 15854 | stop processing: n_tokens = 707, truncated = 0 14.22.784.105 I slot print_timing: id 2 | task 15855 | prompt eval time = 4798.88 ms / 704 tokens ( 6.82 ms per token, 146.70 tokens per second) 14.22.784.107 I slot print_timing: id 2 | task 15855 | eval time = 1215.43 ms / 2 tokens ( 1215.43 ms per token, 0.82 tokens per second) 14.22.784.107 I slot print_timing: id 2 | task 15855 | total time = 6014.31 ms / 706 tokens 14.22.784.107 I slot print_timing: id 2 | task 15855 | graphs reused = 14553 14.22.784.108 I slot print_timing: id 2 | task 15855 | graph reallocs = 0 / 0 (same size) / (changed size) 14.22.784.132 I slot release: id 2 | task 15855 | stop processing: n_tokens = 705, truncated = 0 14.22.784.141 I slot print_timing: id 0 | task 15859 | prompt processing, n_tokens = 733, progress = 0.84, t = 4.72 s / 155.41 tokens per second 14.23.211.096 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 707, t_last = 353645678145 14.23.211.174 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 161.106 MiB) 14.23.353.317 I slot launch_slot_: id 1 | task 15866 | processing task, is_child = 0 14.23.353.391 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 143.082 MiB) 14.23.362.214 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 705, t_last = 353645678312 14.23.362.331 I slot launch_slot_: id 2 | task 15867 | processing task, is_child = 0 14.23.362.337 I slot print_timing: id 0 | task 15859 | prompt processing, n_tokens = 867, progress = 1.00, t = 5.14 s / 168.55 tokens per second 14.24.756.493 I slot print_timing: id 3 | task 15862 | prompt processing, n_tokens = 733, progress = 0.86, t = 3.91 s / 187.49 tokens per second 14.25.906.660 I slot print_timing: id 0 | task 15859 | prompt eval time = 6688.62 ms / 871 tokens ( 7.68 ms per token, 130.22 tokens per second) 14.25.906.666 I slot print_timing: id 0 | task 15859 | eval time = 1150.91 ms / 2 tokens ( 1150.91 ms per token, 0.87 tokens per second) 14.25.906.666 I slot print_timing: id 0 | task 15859 | total time = 7839.53 ms / 873 tokens 14.25.906.667 I slot print_timing: id 0 | task 15859 | graphs reused = 14553 14.25.906.667 I slot print_timing: id 0 | task 15859 | graph reallocs = 0 / 0 (same size) / (changed size) 14.25.906.708 I slot release: id 0 | task 15859 | stop processing: n_tokens = 872, truncated = 0 14.25.906.730 I slot print_timing: id 3 | task 15862 | prompt processing, n_tokens = 844, progress = 1.00, t = 5.06 s / 166.78 tokens per second 14.26.279.899 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 872, t_last = 353648800888 14.26.279.992 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.157 MiB) 14.26.291.540 I slot launch_slot_: id 0 | task 15871 | processing task, is_child = 0 14.28.017.623 I slot print_timing: id 3 | task 15862 | prompt eval time = 5433.80 ms / 848 tokens ( 6.41 ms per token, 156.06 tokens per second) 14.28.017.629 I slot print_timing: id 3 | task 15862 | eval time = 1737.72 ms / 2 tokens ( 1737.72 ms per token, 0.58 tokens per second) 14.28.017.629 I slot print_timing: id 3 | task 15862 | total time = 7171.52 ms / 850 tokens 14.28.017.630 I slot print_timing: id 3 | task 15862 | graphs reused = 14553 14.28.017.630 I slot print_timing: id 3 | task 15862 | graph reallocs = 0 / 0 (same size) / (changed size) 14.28.017.669 I slot release: id 3 | task 15862 | stop processing: n_tokens = 849, truncated = 0 14.28.018.025 I slot print_timing: id 1 | task 15866 | prompt processing, n_tokens = 685, progress = 0.83, t = 4.65 s / 147.19 tokens per second 14.28.020.139 I slot print_timing: id 2 | task 15867 | prompt processing, n_tokens = 733, progress = 0.86, t = 4.65 s / 157.50 tokens per second 14.28.889.582 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 849, t_last = 353650911849 14.28.889.669 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 142.275 MiB) 14.28.998.024 I slot launch_slot_: id 3 | task 15874 | processing task, is_child = 0 14.28.998.044 I slot print_timing: id 1 | task 15866 | prompt processing, n_tokens = 818, progress = 1.00, t = 5.53 s / 148.03 tokens per second 14.28.999.622 I slot print_timing: id 2 | task 15867 | prompt processing, n_tokens = 852, progress = 1.00, t = 5.53 s / 154.18 tokens per second 14.29.473.630 I slot print_timing: id 0 | task 15871 | prompt processing, n_tokens = 274, progress = 0.35, t = 3.18 s / 86.12 tokens per second 14.30.691.105 I slot print_timing: id 1 | task 15866 | prompt eval time = 6109.92 ms / 822 tokens ( 7.43 ms per token, 134.54 tokens per second) 14.30.691.110 I slot print_timing: id 1 | task 15866 | eval time = 1217.62 ms / 2 tokens ( 1217.62 ms per token, 0.82 tokens per second) 14.30.691.110 I slot print_timing: id 1 | task 15866 | total time = 7327.54 ms / 824 tokens 14.30.691.111 I slot print_timing: id 1 | task 15866 | graphs reused = 14553 14.30.691.111 I slot print_timing: id 1 | task 15866 | graph reallocs = 0 / 0 (same size) / (changed size) 14.30.691.150 I slot release: id 1 | task 15866 | stop processing: n_tokens = 823, truncated = 0 14.30.691.298 I slot print_timing: id 2 | task 15867 | prompt eval time = 6109.96 ms / 856 tokens ( 7.14 ms per token, 140.10 tokens per second) 14.30.691.301 I slot print_timing: id 2 | task 15867 | eval time = 1217.68 ms / 2 tokens ( 1217.68 ms per token, 0.82 tokens per second) 14.30.691.301 I slot print_timing: id 2 | task 15867 | total time = 7327.64 ms / 858 tokens 14.30.691.301 I slot print_timing: id 2 | task 15867 | graphs reused = 14553 14.30.691.302 I slot print_timing: id 2 | task 15867 | graph reallocs = 0 / 0 (same size) / (changed size) 14.30.691.333 I slot release: id 2 | task 15867 | stop processing: n_tokens = 857, truncated = 0 14.30.691.343 I slot print_timing: id 0 | task 15871 | prompt processing, n_tokens = 685, progress = 0.87, t = 4.40 s / 155.70 tokens per second 14.31.072.483 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.893 (> 0.100 thold), f_keep = 0.863 14.31.072.567 I slot launch_slot_: id 1 | task 15878 | processing task, is_child = 0 14.31.072.652 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 146.009 MiB) 14.31.147.199 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 857, t_last = 353653585513 14.31.147.335 I slot launch_slot_: id 2 | task 15879 | processing task, is_child = 0 14.31.147.341 I slot print_timing: id 0 | task 15871 | prompt processing, n_tokens = 786, progress = 0.99, t = 4.78 s / 164.40 tokens per second 14.32.714.054 I slot print_timing: id 3 | task 15874 | prompt processing, n_tokens = 685, progress = 0.86, t = 3.71 s / 184.60 tokens per second 14.33.553.516 I slot print_timing: id 0 | task 15871 | prompt eval time = 6420.12 ms / 790 tokens ( 8.13 ms per token, 123.05 tokens per second) 14.33.553.520 I slot print_timing: id 0 | task 15871 | eval time = 841.85 ms / 2 tokens ( 841.85 ms per token, 1.19 tokens per second) 14.33.553.521 I slot print_timing: id 0 | task 15871 | total time = 7261.97 ms / 792 tokens 14.33.553.521 I slot print_timing: id 0 | task 15871 | graphs reused = 14553 14.33.553.522 I slot print_timing: id 0 | task 15871 | graph reallocs = 0 / 0 (same size) / (changed size) 14.33.553.565 I slot release: id 0 | task 15871 | stop processing: n_tokens = 791, truncated = 0 14.33.556.562 I slot print_timing: id 3 | task 15874 | prompt processing, n_tokens = 795, progress = 0.99, t = 4.55 s / 174.63 tokens per second 14.34.399.758 I slot print_timing: id 1 | task 15878 | prompt eval time = 2404.97 ms / 85 tokens ( 28.29 ms per token, 35.34 tokens per second) 14.34.399.760 I slot print_timing: id 1 | task 15878 | eval time = 846.05 ms / 2 tokens ( 846.05 ms per token, 1.18 tokens per second) 14.34.399.765 I slot print_timing: id 1 | task 15878 | total time = 3251.01 ms / 87 tokens 14.34.399.765 I slot print_timing: id 1 | task 15878 | graphs reused = 14553 14.34.399.766 I slot print_timing: id 1 | task 15878 | graph reallocs = 0 / 0 (same size) / (changed size) 14.34.399.804 I slot release: id 1 | task 15878 | stop processing: n_tokens = 796, truncated = 0 14.34.399.980 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 791, t_last = 353656447746 14.34.400.061 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 146.487 MiB) 14.34.408.125 I slot launch_slot_: id 0 | task 15883 | processing task, is_child = 0 14.34.408.197 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 177.378 MiB) 14.34.413.086 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 796, t_last = 353657293984 14.34.413.212 I slot launch_slot_: id 1 | task 15884 | processing task, is_child = 0 14.34.413.434 I slot print_timing: id 2 | task 15879 | prompt processing, n_tokens = 685, progress = 0.87, t = 3.25 s / 210.80 tokens per second 14.35.368.675 I slot print_timing: id 3 | task 15874 | prompt eval time = 5399.14 ms / 799 tokens ( 6.76 ms per token, 147.99 tokens per second) 14.35.368.678 I slot print_timing: id 3 | task 15874 | eval time = 968.70 ms / 2 tokens ( 968.70 ms per token, 1.03 tokens per second) 14.35.368.679 I slot print_timing: id 3 | task 15874 | total time = 6367.84 ms / 801 tokens 14.35.368.679 I slot print_timing: id 3 | task 15874 | graphs reused = 14553 14.35.368.680 I slot print_timing: id 3 | task 15874 | graph reallocs = 0 / 0 (same size) / (changed size) 14.35.368.734 I slot release: id 3 | task 15874 | stop processing: n_tokens = 800, truncated = 0 14.35.369.838 I slot print_timing: id 2 | task 15879 | prompt processing, n_tokens = 779, progress = 0.99, t = 4.22 s / 184.67 tokens per second 14.36.106.378 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 800, t_last = 353658262914 14.36.106.459 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 151.984 MiB) 14.36.106.462 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.487 MiB) 14.36.111.059 I slot launch_slot_: id 3 | task 15887 | processing task, is_child = 0 14.37.402.588 I slot print_timing: id 2 | task 15879 | prompt eval time = 4956.28 ms / 783 tokens ( 6.33 ms per token, 157.98 tokens per second) 14.37.402.590 I slot print_timing: id 2 | task 15879 | eval time = 1296.21 ms / 2 tokens ( 1296.21 ms per token, 0.77 tokens per second) 14.37.402.590 I slot print_timing: id 2 | task 15879 | total time = 6252.49 ms / 785 tokens 14.37.402.591 I slot print_timing: id 2 | task 15879 | graphs reused = 14553 14.37.402.591 I slot print_timing: id 2 | task 15879 | graph reallocs = 0 / 0 (same size) / (changed size) 14.37.402.632 I slot release: id 2 | task 15879 | stop processing: n_tokens = 784, truncated = 0 14.38.809.705 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 784, t_last = 353660296812 14.39.273.667 I slot launch_slot_: id 2 | task 15890 | processing task, is_child = 0 14.39.273.687 I slot print_timing: id 0 | task 15883 | prompt processing, n_tokens = 940, progress = 0.86, t = 4.40 s / 213.81 tokens per second 14.39.276.197 I slot print_timing: id 1 | task 15884 | prompt processing, n_tokens = 940, progress = 0.85, t = 4.40 s / 213.81 tokens per second 14.41.212.176 I slot print_timing: id 0 | task 15883 | prompt processing, n_tokens = 1088, progress = 1.00, t = 6.80 s / 160.02 tokens per second 14.41.539.354 I slot print_timing: id 1 | task 15884 | prompt processing, n_tokens = 1096, progress = 1.00, t = 6.80 s / 161.20 tokens per second 14.41.543.552 I slot print_timing: id 3 | task 15887 | prompt processing, n_tokens = 640, progress = 0.55, t = 5.10 s / 125.46 tokens per second 14.43.404.146 I slot print_timing: id 2 | task 15890 | prompt processing, n_tokens = 895, progress = 0.37, t = 4.13 s / 216.91 tokens per second 14.43.404.174 I slot print_timing: id 3 | task 15887 | prompt processing, n_tokens = 940, progress = 0.81, t = 7.29 s / 128.89 tokens per second 14.45.808.600 I slot print_timing: id 0 | task 15883 | prompt eval time = 8990.78 ms / 1092 tokens ( 8.23 ms per token, 121.46 tokens per second) 14.45.808.602 I slot print_timing: id 0 | task 15883 | eval time = 2404.60 ms / 2 tokens ( 2404.60 ms per token, 0.42 tokens per second) 14.45.808.603 I slot print_timing: id 0 | task 15883 | total time = 11395.37 ms / 1094 tokens 14.45.808.604 I slot print_timing: id 0 | task 15883 | graphs reused = 14553 14.45.808.604 I slot print_timing: id 0 | task 15883 | graph reallocs = 0 / 0 (same size) / (changed size) 14.45.808.657 I slot release: id 0 | task 15883 | stop processing: n_tokens = 1093, truncated = 0 14.45.808.780 I slot print_timing: id 1 | task 15884 | prompt eval time = 8990.80 ms / 1100 tokens ( 8.17 ms per token, 122.35 tokens per second) 14.45.808.783 I slot print_timing: id 1 | task 15884 | eval time = 2404.65 ms / 2 tokens ( 2404.65 ms per token, 0.42 tokens per second) 14.45.808.783 I slot print_timing: id 1 | task 15884 | total time = 11395.44 ms / 1102 tokens 14.45.808.784 I slot print_timing: id 1 | task 15884 | graphs reused = 14553 14.45.808.784 I slot print_timing: id 1 | task 15884 | graph reallocs = 0 / 0 (same size) / (changed size) 14.45.808.815 I slot release: id 1 | task 15884 | stop processing: n_tokens = 1101, truncated = 0 14.45.808.827 I slot print_timing: id 2 | task 15890 | prompt processing, n_tokens = 1903, progress = 0.79, t = 6.53 s / 291.39 tokens per second 14.45.810.802 I slot print_timing: id 3 | task 15887 | prompt processing, n_tokens = 1152, progress = 1.00, t = 9.70 s / 118.79 tokens per second 14.46.464.186 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1093, t_last = 353668702837 14.46.464.278 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 152.942 MiB) 14.46.464.286 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.878 MiB) 14.46.469.745 I slot launch_slot_: id 0 | task 15895 | processing task, is_child = 0 14.46.469.830 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 191.837 MiB) 14.46.474.257 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1101, t_last = 353668702995 14.46.474.390 I slot launch_slot_: id 1 | task 15896 | processing task, is_child = 0 14.46.474.673 I slot print_timing: id 2 | task 15890 | prompt processing, n_tokens = 2137, progress = 0.88, t = 7.19 s / 297.37 tokens per second 14.48.468.566 I slot print_timing: id 3 | task 15887 | prompt eval time = 10353.09 ms / 1156 tokens ( 8.96 ms per token, 111.66 tokens per second) 14.48.468.569 I slot print_timing: id 3 | task 15887 | eval time = 2004.38 ms / 2 tokens ( 2004.38 ms per token, 0.50 tokens per second) 14.48.468.569 I slot print_timing: id 3 | task 15887 | total time = 12357.47 ms / 1158 tokens 14.48.468.570 I slot print_timing: id 3 | task 15887 | graphs reused = 14553 14.48.468.570 I slot print_timing: id 3 | task 15887 | graph reallocs = 0 / 0 (same size) / (changed size) 14.48.468.630 I slot release: id 3 | task 15887 | stop processing: n_tokens = 1157, truncated = 0 14.48.471.969 I slot print_timing: id 2 | task 15890 | prompt processing, n_tokens = 2415, progress = 1.00, t = 9.19 s / 262.77 tokens per second 14.50.358.969 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1157, t_last = 353671362810 14.50.359.061 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 169.229 MiB) 14.50.369.632 I slot launch_slot_: id 3 | task 15899 | processing task, is_child = 0 14.50.369.651 I slot print_timing: id 0 | task 15895 | prompt processing, n_tokens = 895, progress = 0.38, t = 3.88 s / 230.41 tokens per second 14.50.369.673 I slot print_timing: id 1 | task 15896 | prompt processing, n_tokens = 895, progress = 0.35, t = 3.88 s / 230.42 tokens per second 14.54.255.049 I slot print_timing: id 2 | task 15890 | prompt eval time = 11081.22 ms / 2419 tokens ( 4.58 ms per token, 218.30 tokens per second) 14.54.255.052 I slot print_timing: id 2 | task 15890 | eval time = 3896.08 ms / 2 tokens ( 3896.08 ms per token, 0.26 tokens per second) 14.54.255.053 I slot print_timing: id 2 | task 15890 | total time = 14977.29 ms / 2421 tokens 14.54.255.053 I slot print_timing: id 2 | task 15890 | graphs reused = 14553 14.54.255.054 I slot print_timing: id 2 | task 15890 | graph reallocs = 0 / 0 (same size) / (changed size) 14.54.255.156 I slot release: id 2 | task 15890 | stop processing: n_tokens = 2420, truncated = 0 14.54.255.176 I slot print_timing: id 0 | task 15895 | prompt processing, n_tokens = 1817, progress = 0.78, t = 7.78 s / 233.53 tokens per second 14.54.257.006 I slot print_timing: id 1 | task 15896 | prompt processing, n_tokens = 2020, progress = 0.79, t = 7.78 s / 259.63 tokens per second 14.55.230.212 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 2420, t_last = 353677149337 14.55.230.377 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 154.993 MiB) 14.55.918.608 I slot launch_slot_: id 2 | task 15902 | processing task, is_child = 0 14.55.918.624 I slot print_timing: id 0 | task 15895 | prompt processing, n_tokens = 2137, progress = 0.92, t = 8.76 s / 244.07 tokens per second 14.55.919.964 I slot print_timing: id 1 | task 15896 | prompt processing, n_tokens = 2055, progress = 0.80, t = 8.76 s / 234.71 tokens per second 14.57.549.974 I slot print_timing: id 0 | task 15895 | prompt processing, n_tokens = 2329, progress = 1.00, t = 11.08 s / 210.28 tokens per second 14.58.239.595 I slot print_timing: id 1 | task 15896 | prompt processing, n_tokens = 2137, progress = 0.83, t = 11.08 s / 192.95 tokens per second 14.58.242.955 I slot print_timing: id 3 | task 15899 | prompt processing, n_tokens = 895, progress = 0.36, t = 3.29 s / 271.79 tokens per second 15.01.960.008 I slot print_timing: id 1 | task 15896 | prompt processing, n_tokens = 2567, progress = 1.00, t = 15.49 s / 165.77 tokens per second 15.01.962.273 I slot print_timing: id 2 | task 15902 | prompt processing, n_tokens = 473, progress = 0.29, t = 6.04 s / 78.33 tokens per second 15.01.962.295 I slot print_timing: id 3 | task 15899 | prompt processing, n_tokens = 1958, progress = 0.79, t = 7.70 s / 254.19 tokens per second 15.03.630.941 I slot print_timing: id 0 | task 15895 | prompt eval time = 15485.60 ms / 2333 tokens ( 6.64 ms per token, 150.66 tokens per second) 15.03.630.943 I slot print_timing: id 0 | task 15895 | eval time = 1670.94 ms / 2 tokens ( 1670.94 ms per token, 0.60 tokens per second) 15.03.630.945 I slot print_timing: id 0 | task 15895 | total time = 17156.53 ms / 2335 tokens 15.03.630.945 I slot print_timing: id 0 | task 15895 | graphs reused = 14553 15.03.630.946 I slot print_timing: id 0 | task 15895 | graph reallocs = 0 / 0 (same size) / (changed size) 15.03.631.040 I slot release: id 0 | task 15895 | stop processing: n_tokens = 2334, truncated = 0 15.03.631.206 I slot print_timing: id 2 | task 15902 | prompt processing, n_tokens = 1106, progress = 0.68, t = 7.71 s / 143.46 tokens per second 15.03.632.942 I slot print_timing: id 3 | task 15899 | prompt processing, n_tokens = 2137, progress = 0.86, t = 9.37 s / 227.98 tokens per second 15.04.919.797 I slot print_timing: id 1 | task 15896 | prompt eval time = 17156.65 ms / 2571 tokens ( 6.67 ms per token, 149.85 tokens per second) 15.04.919.802 I slot print_timing: id 1 | task 15896 | eval time = 1288.59 ms / 2 tokens ( 1288.59 ms per token, 0.78 tokens per second) 15.04.919.803 I slot print_timing: id 1 | task 15896 | total time = 18445.25 ms / 2573 tokens 15.04.919.803 I slot print_timing: id 1 | task 15896 | graphs reused = 14553 15.04.919.804 I slot print_timing: id 1 | task 15896 | graph reallocs = 0 / 0 (same size) / (changed size) 15.04.919.908 I slot release: id 1 | task 15896 | stop processing: n_tokens = 2572, truncated = 0 15.04.919.916 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 2334, t_last = 353686525221 15.04.920.052 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 156.525 MiB) 15.04.920.056 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 152.914 MiB) 15.04.934.684 I slot launch_slot_: id 0 | task 15907 | processing task, is_child = 0 15.04.934.822 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 139.622 MiB) 15.04.947.038 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 2572, t_last = 353687814089 15.04.947.226 I slot launch_slot_: id 1 | task 15908 | processing task, is_child = 0 15.04.948.684 I slot print_timing: id 2 | task 15902 | prompt processing, n_tokens = 1317, progress = 0.81, t = 9.00 s / 146.36 tokens per second 15.04.949.903 I slot print_timing: id 3 | task 15899 | prompt processing, n_tokens = 2470, progress = 1.00, t = 10.66 s / 231.65 tokens per second 15.06.476.481 I slot print_timing: id 2 | task 15902 | prompt processing, n_tokens = 1618, progress = 1.00, t = 10.55 s / 153.31 tokens per second 15.07.613.984 I slot print_timing: id 3 | task 15899 | prompt eval time = 12218.32 ms / 2474 tokens ( 4.94 ms per token, 202.48 tokens per second) 15.07.613.988 I slot print_timing: id 3 | task 15899 | eval time = 1138.65 ms / 2 tokens ( 1138.65 ms per token, 0.88 tokens per second) 15.07.613.988 I slot print_timing: id 3 | task 15899 | total time = 13356.96 ms / 2476 tokens 15.07.613.989 I slot print_timing: id 3 | task 15899 | graphs reused = 14553 15.07.613.989 I slot print_timing: id 3 | task 15899 | graph reallocs = 0 / 0 (same size) / (changed size) 15.07.614.090 I slot release: id 3 | task 15899 | stop processing: n_tokens = 2475, truncated = 0 15.10.536.067 I slot print_timing: id 2 | task 15902 | prompt eval time = 11692.67 ms / 1622 tokens ( 7.21 ms per token, 138.72 tokens per second) 15.10.536.070 I slot print_timing: id 2 | task 15902 | eval time = 2922.17 ms / 2 tokens ( 2922.17 ms per token, 0.34 tokens per second) 15.10.536.070 I slot print_timing: id 2 | task 15902 | total time = 14614.84 ms / 1624 tokens 15.10.536.071 I slot print_timing: id 2 | task 15902 | graphs reused = 14553 15.10.536.071 I slot print_timing: id 2 | task 15902 | graph reallocs = 0 / 0 (same size) / (changed size) 15.10.536.146 I slot release: id 2 | task 15902 | stop processing: n_tokens = 1623, truncated = 0 15.10.536.155 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.798 (> 0.100 thold), f_keep = 0.832 15.10.536.245 I slot launch_slot_: id 2 | task 15912 | processing task, is_child = 0 15.10.536.391 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 137.421 MiB) 15.10.536.397 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 172.304 MiB) 15.10.551.102 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 2475, t_last = 353690508272 15.10.551.302 I slot launch_slot_: id 3 | task 15913 | processing task, is_child = 0 15.10.551.312 I slot print_timing: id 0 | task 15907 | prompt processing, n_tokens = 1170, progress = 0.69, t = 5.59 s / 209.35 tokens per second 15.10.552.428 I slot print_timing: id 1 | task 15908 | prompt processing, n_tokens = 1317, progress = 0.70, t = 5.59 s / 235.66 tokens per second 15.12.046.847 I slot print_timing: id 0 | task 15907 | prompt processing, n_tokens = 1317, progress = 0.78, t = 7.10 s / 185.50 tokens per second 15.12.497.052 I slot print_timing: id 1 | task 15908 | prompt processing, n_tokens = 1354, progress = 0.72, t = 7.10 s / 190.72 tokens per second 15.15.133.834 I slot print_timing: id 0 | task 15907 | prompt processing, n_tokens = 1682, progress = 1.00, t = 10.19 s / 165.12 tokens per second 15.15.135.680 I slot print_timing: id 1 | task 15908 | prompt processing, n_tokens = 1866, progress = 1.00, t = 10.19 s / 183.19 tokens per second 15.15.138.383 I slot print_timing: id 3 | task 15913 | prompt processing, n_tokens = 473, progress = 0.27, t = 4.58 s / 103.30 tokens per second 15.16.739.451 I slot print_timing: id 2 | task 15912 | prompt eval time = 4580.21 ms / 342 tokens ( 13.39 ms per token, 74.67 tokens per second) 15.16.739.453 I slot print_timing: id 2 | task 15912 | eval time = 1605.63 ms / 2 tokens ( 1605.63 ms per token, 0.62 tokens per second) 15.16.739.454 I slot print_timing: id 2 | task 15912 | total time = 6185.84 ms / 344 tokens 15.16.739.454 I slot print_timing: id 2 | task 15912 | graphs reused = 14553 15.16.739.455 I slot print_timing: id 2 | task 15912 | graph reallocs = 0 / 0 (same size) / (changed size) 15.16.739.538 I slot release: id 2 | task 15912 | stop processing: n_tokens = 1693, truncated = 0 15.16.739.552 I slot print_timing: id 3 | task 15913 | prompt processing, n_tokens = 1259, progress = 0.71, t = 6.18 s / 203.58 tokens per second 15.17.051.839 I slot print_timing: id 0 | task 15907 | prompt eval time = 11791.95 ms / 1686 tokens ( 6.99 ms per token, 142.98 tokens per second) 15.17.051.844 I slot print_timing: id 0 | task 15907 | eval time = 312.65 ms / 2 tokens ( 312.65 ms per token, 3.20 tokens per second) 15.17.051.845 I slot print_timing: id 0 | task 15907 | total time = 12104.60 ms / 1688 tokens 15.17.051.845 I slot print_timing: id 0 | task 15907 | graphs reused = 14553 15.17.051.846 I slot print_timing: id 0 | task 15907 | graph reallocs = 0 / 0 (same size) / (changed size) 15.17.051.914 I slot release: id 0 | task 15907 | stop processing: n_tokens = 1687, truncated = 0 15.17.052.018 I slot print_timing: id 1 | task 15908 | prompt eval time = 11791.84 ms / 1870 tokens ( 6.31 ms per token, 158.58 tokens per second) 15.17.052.020 I slot print_timing: id 1 | task 15908 | eval time = 312.70 ms / 2 tokens ( 312.70 ms per token, 3.20 tokens per second) 15.17.052.021 I slot print_timing: id 1 | task 15908 | total time = 12104.53 ms / 1872 tokens 15.17.052.021 I slot print_timing: id 1 | task 15908 | graphs reused = 14553 15.17.052.022 I slot print_timing: id 1 | task 15908 | graph reallocs = 0 / 0 (same size) / (changed size) 15.17.052.073 I slot release: id 1 | task 15908 | stop processing: n_tokens = 1871, truncated = 0 15.17.052.080 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.832 (> 0.100 thold), f_keep = 0.800 15.17.052.174 I slot launch_slot_: id 0 | task 15918 | processing task, is_child = 0 15.17.052.304 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 174.205 MiB) 15.17.062.047 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 150.932 MiB) 15.17.067.842 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1693, t_last = 353699633719 15.17.068.006 I slot launch_slot_: id 2 | task 15919 | processing task, is_child = 0 15.17.068.117 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1871, t_last = 353699946253 15.17.068.261 I slot launch_slot_: id 1 | task 15920 | processing task, is_child = 0 15.17.069.919 I slot print_timing: id 3 | task 15913 | prompt processing, n_tokens = 1317, progress = 0.74, t = 6.50 s / 202.71 tokens per second 15.19.088.427 I slot print_timing: id 3 | task 15913 | prompt processing, n_tokens = 1771, progress = 1.00, t = 7.82 s / 226.52 tokens per second 15.20.926.129 I slot print_timing: id 0 | task 15918 | prompt eval time = 2292.46 ms / 273 tokens ( 8.40 ms per token, 119.09 tokens per second) 15.20.926.134 I slot print_timing: id 0 | task 15918 | eval time = 1565.39 ms / 2 tokens ( 1565.39 ms per token, 0.64 tokens per second) 15.20.926.138 I slot print_timing: id 0 | task 15918 | total time = 3857.85 ms / 275 tokens 15.20.926.138 I slot print_timing: id 0 | task 15918 | graphs reused = 14553 15.20.926.139 I slot print_timing: id 0 | task 15918 | graph reallocs = 0 / 0 (same size) / (changed size) 15.20.926.207 I slot release: id 0 | task 15918 | stop processing: n_tokens = 1624, truncated = 0 15.20.926.354 I slot print_timing: id 3 | task 15913 | prompt eval time = 8805.98 ms / 1775 tokens ( 4.96 ms per token, 201.57 tokens per second) 15.20.926.357 I slot print_timing: id 3 | task 15913 | eval time = 1565.51 ms / 2 tokens ( 1565.51 ms per token, 0.64 tokens per second) 15.20.926.357 I slot print_timing: id 3 | task 15913 | total time = 10371.48 ms / 1777 tokens 15.20.926.358 I slot print_timing: id 3 | task 15913 | graphs reused = 14553 15.20.926.358 I slot print_timing: id 3 | task 15913 | graph reallocs = 0 / 0 (same size) / (changed size) 15.20.926.406 I slot release: id 3 | task 15913 | stop processing: n_tokens = 1776, truncated = 0 15.20.926.416 I slot print_timing: id 1 | task 15920 | prompt processing, n_tokens = 538, progress = 0.84, t = 3.86 s / 139.51 tokens per second 15.20.928.715 I slot print_timing: id 2 | task 15919 | prompt processing, n_tokens = 538, progress = 0.81, t = 3.86 s / 139.51 tokens per second 15.21.406.449 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1624, t_last = 353703820387 15.21.406.575 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 161.557 MiB) 15.21.406.579 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.663 MiB) 15.21.534.840 I slot launch_slot_: id 0 | task 15925 | processing task, is_child = 0 15.21.534.950 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 160.600 MiB) 15.21.540.472 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1776, t_last = 353703820586 15.21.540.620 I slot launch_slot_: id 3 | task 15926 | processing task, is_child = 0 15.21.540.810 I slot print_timing: id 1 | task 15920 | prompt processing, n_tokens = 634, progress = 0.99, t = 4.34 s / 146.19 tokens per second 15.21.542.040 I slot print_timing: id 2 | task 15919 | prompt processing, n_tokens = 658, progress = 0.99, t = 4.34 s / 151.73 tokens per second 15.22.703.920 I slot print_timing: id 1 | task 15920 | prompt eval time = 5298.41 ms / 638 tokens ( 8.30 ms per token, 120.41 tokens per second) 15.22.703.922 I slot print_timing: id 1 | task 15920 | eval time = 336.00 ms / 2 tokens ( 336.00 ms per token, 2.98 tokens per second) 15.22.703.922 I slot print_timing: id 1 | task 15920 | total time = 5634.41 ms / 640 tokens 15.22.703.923 I slot print_timing: id 1 | task 15920 | graphs reused = 14553 15.22.703.923 I slot print_timing: id 1 | task 15920 | graph reallocs = 0 / 0 (same size) / (changed size) 15.22.703.963 I slot release: id 1 | task 15920 | stop processing: n_tokens = 639, truncated = 0 15.22.704.054 I slot print_timing: id 2 | task 15919 | prompt eval time = 5298.30 ms / 662 tokens ( 8.00 ms per token, 124.95 tokens per second) 15.22.704.057 I slot print_timing: id 2 | task 15919 | eval time = 336.01 ms / 2 tokens ( 336.01 ms per token, 2.98 tokens per second) 15.22.704.057 I slot print_timing: id 2 | task 15919 | total time = 5634.32 ms / 664 tokens 15.22.704.057 I slot print_timing: id 2 | task 15919 | graphs reused = 14553 15.22.704.058 I slot print_timing: id 2 | task 15919 | graph reallocs = 0 / 0 (same size) / (changed size) 15.22.704.077 I slot release: id 2 | task 15919 | stop processing: n_tokens = 663, truncated = 0 15.23.456.019 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.862 (> 0.100 thold), f_keep = 0.881 15.23.456.099 I slot launch_slot_: id 1 | task 15930 | processing task, is_child = 0 15.23.456.191 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 195.005 MiB) 15.24.157.469 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 663, t_last = 353705598257 15.24.157.613 I slot launch_slot_: id 2 | task 15931 | processing task, is_child = 0 15.25.061.596 I slot print_timing: id 0 | task 15925 | prompt processing, n_tokens = 635, progress = 0.99, t = 3.52 s / 180.35 tokens per second 15.25.215.885 I slot print_timing: id 3 | task 15926 | prompt processing, n_tokens = 669, progress = 0.99, t = 3.52 s / 190.14 tokens per second 15.26.386.281 I slot print_timing: id 0 | task 15925 | prompt eval time = 4095.05 ms / 639 tokens ( 6.41 ms per token, 156.04 tokens per second) 15.26.386.284 I slot print_timing: id 0 | task 15925 | eval time = 750.60 ms / 2 tokens ( 750.60 ms per token, 1.33 tokens per second) 15.26.386.285 I slot print_timing: id 0 | task 15925 | total time = 4845.65 ms / 641 tokens 15.26.386.285 I slot print_timing: id 0 | task 15925 | graphs reused = 14553 15.26.386.285 I slot print_timing: id 0 | task 15925 | graph reallocs = 0 / 0 (same size) / (changed size) 15.26.386.326 I slot release: id 0 | task 15925 | stop processing: n_tokens = 640, truncated = 0 15.26.386.427 I slot print_timing: id 1 | task 15930 | prompt eval time = 1475.77 ms / 90 tokens ( 16.40 ms per token, 60.99 tokens per second) 15.26.386.429 I slot print_timing: id 1 | task 15930 | eval time = 750.65 ms / 2 tokens ( 750.65 ms per token, 1.33 tokens per second) 15.26.386.429 I slot print_timing: id 1 | task 15930 | total time = 2226.42 ms / 92 tokens 15.26.386.429 I slot print_timing: id 1 | task 15930 | graphs reused = 14553 15.26.386.430 I slot print_timing: id 1 | task 15930 | graph reallocs = 0 / 0 (same size) / (changed size) 15.26.386.461 I slot release: id 1 | task 15930 | stop processing: n_tokens = 654, truncated = 0 15.26.386.559 I slot print_timing: id 3 | task 15926 | prompt eval time = 4092.69 ms / 673 tokens ( 6.08 ms per token, 164.44 tokens per second) 15.26.386.561 I slot print_timing: id 3 | task 15926 | eval time = 750.66 ms / 2 tokens ( 750.66 ms per token, 1.33 tokens per second) 15.26.386.561 I slot print_timing: id 3 | task 15926 | total time = 4843.35 ms / 675 tokens 15.26.386.561 I slot print_timing: id 3 | task 15926 | graphs reused = 14553 15.26.386.562 I slot print_timing: id 3 | task 15926 | graph reallocs = 0 / 0 (same size) / (changed size) 15.26.386.582 I slot release: id 3 | task 15926 | stop processing: n_tokens = 674, truncated = 0 15.26.871.149 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 640, t_last = 353709280506 15.26.871.226 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 152.818 MiB) 15.26.875.448 I slot launch_slot_: id 0 | task 15937 | processing task, is_child = 0 15.26.875.516 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 195.415 MiB) 15.26.884.048 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 654, t_last = 353709280641 15.26.884.168 I slot launch_slot_: id 1 | task 15938 | processing task, is_child = 0 15.26.884.226 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 674, t_last = 353709280762 15.26.884.322 I slot launch_slot_: id 3 | task 15939 | processing task, is_child = 0 15.27.860.002 I slot print_timing: id 2 | task 15931 | prompt eval time = 2709.90 ms / 703 tokens ( 3.85 ms per token, 259.42 tokens per second) 15.27.860.008 I slot print_timing: id 2 | task 15931 | eval time = 988.85 ms / 2 tokens ( 988.85 ms per token, 1.01 tokens per second) 15.27.860.008 I slot print_timing: id 2 | task 15931 | total time = 3698.75 ms / 705 tokens 15.27.860.009 I slot print_timing: id 2 | task 15931 | graphs reused = 14553 15.27.860.009 I slot print_timing: id 2 | task 15931 | graph reallocs = 0 / 0 (same size) / (changed size) 15.27.860.050 I slot release: id 2 | task 15931 | stop processing: n_tokens = 704, truncated = 0 15.28.179.197 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 704, t_last = 353710754230 15.28.179.274 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.118 MiB) 15.28.637.454 I slot launch_slot_: id 2 | task 15942 | processing task, is_child = 0 15.30.584.507 I slot print_timing: id 0 | task 15937 | prompt processing, n_tokens = 593, progress = 0.85, t = 3.70 s / 160.26 tokens per second 15.30.619.508 I slot print_timing: id 1 | task 15938 | prompt processing, n_tokens = 593, progress = 0.84, t = 3.70 s / 160.27 tokens per second 15.30.622.437 I slot print_timing: id 3 | task 15939 | prompt processing, n_tokens = 441, progress = 0.46, t = 3.70 s / 119.19 tokens per second 15.31.527.040 I slot print_timing: id 0 | task 15937 | prompt processing, n_tokens = 697, progress = 0.99, t = 4.64 s / 150.13 tokens per second 15.32.113.848 I slot print_timing: id 1 | task 15938 | prompt processing, n_tokens = 701, progress = 0.99, t = 4.64 s / 150.99 tokens per second 15.32.119.100 I slot print_timing: id 3 | task 15939 | prompt processing, n_tokens = 818, progress = 0.85, t = 4.64 s / 176.20 tokens per second 15.33.383.214 I slot print_timing: id 2 | task 15942 | prompt processing, n_tokens = 640, progress = 0.85, t = 4.74 s / 134.93 tokens per second 15.33.384.964 I slot print_timing: id 3 | task 15939 | prompt processing, n_tokens = 953, progress = 1.00, t = 6.50 s / 146.65 tokens per second 15.33.844.492 I slot print_timing: id 0 | task 15937 | prompt eval time = 6498.77 ms / 701 tokens ( 9.27 ms per token, 107.87 tokens per second) 15.33.844.497 I slot print_timing: id 0 | task 15937 | eval time = 461.39 ms / 2 tokens ( 461.39 ms per token, 2.17 tokens per second) 15.33.844.498 I slot print_timing: id 0 | task 15937 | total time = 6960.16 ms / 703 tokens 15.33.844.498 I slot print_timing: id 0 | task 15937 | graphs reused = 14553 15.33.844.499 I slot print_timing: id 0 | task 15937 | graph reallocs = 0 / 0 (same size) / (changed size) 15.33.844.540 I slot release: id 0 | task 15937 | stop processing: n_tokens = 702, truncated = 0 15.33.844.636 I slot print_timing: id 1 | task 15938 | prompt eval time = 6498.78 ms / 705 tokens ( 9.22 ms per token, 108.48 tokens per second) 15.33.844.638 I slot print_timing: id 1 | task 15938 | eval time = 461.43 ms / 2 tokens ( 461.43 ms per token, 2.17 tokens per second) 15.33.844.639 I slot print_timing: id 1 | task 15938 | total time = 6960.21 ms / 707 tokens 15.33.844.639 I slot print_timing: id 1 | task 15938 | graphs reused = 14553 15.33.844.639 I slot print_timing: id 1 | task 15938 | graph reallocs = 0 / 0 (same size) / (changed size) 15.33.844.664 I slot release: id 1 | task 15938 | stop processing: n_tokens = 706, truncated = 0 15.33.844.792 I slot print_timing: id 2 | task 15942 | prompt processing, n_tokens = 747, progress = 0.99, t = 5.20 s / 143.52 tokens per second 15.33.906.492 I slot print_timing: id 3 | task 15939 | prompt eval time = 6960.26 ms / 957 tokens ( 7.27 ms per token, 137.49 tokens per second) 15.33.906.495 I slot print_timing: id 3 | task 15939 | eval time = 61.70 ms / 2 tokens ( 61.70 ms per token, 16.21 tokens per second) 15.33.906.495 I slot print_timing: id 3 | task 15939 | total time = 7021.95 ms / 959 tokens 15.33.906.496 I slot print_timing: id 3 | task 15939 | graphs reused = 14553 15.33.906.496 I slot print_timing: id 3 | task 15939 | graph reallocs = 0 / 0 (same size) / (changed size) 15.33.906.534 I slot release: id 3 | task 15939 | stop processing: n_tokens = 958, truncated = 0 15.33.906.541 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 702, t_last = 353716738720 15.33.906.613 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 187.579 MiB) 15.33.911.240 I slot launch_slot_: id 0 | task 15948 | processing task, is_child = 0 15.33.911.312 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 159.150 MiB) 15.33.916.405 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 157.318 MiB) 15.33.921.106 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 706, t_last = 353716738844 15.33.921.224 I slot launch_slot_: id 1 | task 15949 | processing task, is_child = 0 15.33.921.295 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 958, t_last = 353716800714 15.33.921.405 I slot launch_slot_: id 3 | task 15950 | processing task, is_child = 0 15.34.836.828 I slot print_timing: id 2 | task 15942 | prompt eval time = 5266.77 ms / 751 tokens ( 7.01 ms per token, 142.59 tokens per second) 15.34.836.830 I slot print_timing: id 2 | task 15942 | eval time = 930.42 ms / 2 tokens ( 930.42 ms per token, 1.07 tokens per second) 15.34.836.831 I slot print_timing: id 2 | task 15942 | total time = 6197.19 ms / 753 tokens 15.34.836.831 I slot print_timing: id 2 | task 15942 | graphs reused = 14553 15.34.836.832 I slot print_timing: id 2 | task 15942 | graph reallocs = 0 / 0 (same size) / (changed size) 15.34.836.869 I slot release: id 2 | task 15942 | stop processing: n_tokens = 752, truncated = 0 15.35.554.172 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.867 (> 0.100 thold), f_keep = 0.884 15.35.554.279 I slot launch_slot_: id 2 | task 15953 | processing task, is_child = 0 15.36.924.768 I slot print_timing: id 0 | task 15948 | prompt processing, n_tokens = 640, progress = 0.86, t = 3.00 s / 213.10 tokens per second 15.37.256.247 I slot print_timing: id 1 | task 15949 | prompt processing, n_tokens = 287, progress = 0.36, t = 3.00 s / 95.56 tokens per second 15.37.260.041 I slot print_timing: id 3 | task 15950 | prompt processing, n_tokens = 293, progress = 0.36, t = 3.00 s / 97.56 tokens per second 15.39.080.766 I slot print_timing: id 0 | task 15948 | prompt processing, n_tokens = 741, progress = 0.99, t = 5.16 s / 143.63 tokens per second 15.39.082.498 I slot print_timing: id 1 | task 15949 | prompt processing, n_tokens = 640, progress = 0.80, t = 5.16 s / 124.05 tokens per second 15.39.084.543 I slot print_timing: id 3 | task 15950 | prompt processing, n_tokens = 640, progress = 0.79, t = 5.16 s / 124.05 tokens per second 15.40.098.216 I slot print_timing: id 2 | task 15953 | prompt eval time = 3100.30 ms / 102 tokens ( 30.40 ms per token, 32.90 tokens per second) 15.40.098.223 I slot print_timing: id 2 | task 15953 | eval time = 1017.46 ms / 2 tokens ( 1017.46 ms per token, 0.98 tokens per second) 15.40.098.223 I slot print_timing: id 2 | task 15953 | total time = 4117.76 ms / 104 tokens 15.40.098.224 I slot print_timing: id 2 | task 15953 | graphs reused = 14553 15.40.098.224 I slot print_timing: id 2 | task 15953 | graph reallocs = 0 / 0 (same size) / (changed size) 15.40.098.266 I slot release: id 2 | task 15953 | stop processing: n_tokens = 768, truncated = 0 15.40.098.283 I slot print_timing: id 1 | task 15949 | prompt processing, n_tokens = 799, progress = 1.00, t = 6.17 s / 129.54 tokens per second 15.40.099.823 I slot print_timing: id 3 | task 15950 | prompt processing, n_tokens = 805, progress = 1.00, t = 6.17 s / 130.51 tokens per second 15.40.206.593 I slot print_timing: id 0 | task 15948 | prompt eval time = 6176.67 ms / 745 tokens ( 8.29 ms per token, 120.62 tokens per second) 15.40.206.596 I slot print_timing: id 0 | task 15948 | eval time = 108.51 ms / 2 tokens ( 108.51 ms per token, 9.22 tokens per second) 15.40.206.597 I slot print_timing: id 0 | task 15948 | total time = 6285.18 ms / 747 tokens 15.40.206.598 I slot print_timing: id 0 | task 15948 | graphs reused = 14553 15.40.206.598 I slot print_timing: id 0 | task 15948 | graph reallocs = 0 / 0 (same size) / (changed size) 15.40.206.638 I slot release: id 0 | task 15948 | stop processing: n_tokens = 746, truncated = 0 15.40.207.024 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 768, t_last = 353722992446 15.40.207.110 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 153.202 MiB) 15.40.215.794 I slot launch_slot_: id 2 | task 15958 | processing task, is_child = 0 15.40.215.867 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 156.169 MiB) 15.40.220.823 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 746, t_last = 353723100818 15.40.220.947 I slot launch_slot_: id 0 | task 15959 | processing task, is_child = 0 15.40.943.531 I slot print_timing: id 1 | task 15949 | prompt eval time = 6285.23 ms / 803 tokens ( 7.83 ms per token, 127.76 tokens per second) 15.40.943.537 I slot print_timing: id 1 | task 15949 | eval time = 736.77 ms / 2 tokens ( 736.77 ms per token, 1.36 tokens per second) 15.40.943.537 I slot print_timing: id 1 | task 15949 | total time = 7022.01 ms / 805 tokens 15.40.943.538 I slot print_timing: id 1 | task 15949 | graphs reused = 14553 15.40.943.538 I slot print_timing: id 1 | task 15949 | graph reallocs = 0 / 0 (same size) / (changed size) 15.40.943.585 I slot release: id 1 | task 15949 | stop processing: n_tokens = 804, truncated = 0 15.40.943.679 I slot print_timing: id 3 | task 15950 | prompt eval time = 6285.41 ms / 809 tokens ( 7.77 ms per token, 128.71 tokens per second) 15.40.943.680 I slot print_timing: id 3 | task 15950 | eval time = 736.66 ms / 2 tokens ( 736.66 ms per token, 1.36 tokens per second) 15.40.943.681 I slot print_timing: id 3 | task 15950 | total time = 7022.07 ms / 811 tokens 15.40.943.681 I slot print_timing: id 3 | task 15950 | graphs reused = 14553 15.40.943.681 I slot print_timing: id 3 | task 15950 | graph reallocs = 0 / 0 (same size) / (changed size) 15.40.943.710 I slot release: id 3 | task 15950 | stop processing: n_tokens = 810, truncated = 0 15.41.301.743 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 804, t_last = 353723837765 15.41.301.825 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 184.081 MiB) 15.41.436.001 I slot launch_slot_: id 1 | task 15962 | processing task, is_child = 0 15.41.436.080 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 218.062 MiB) 15.41.440.313 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 810, t_last = 353723837890 15.41.440.444 I slot launch_slot_: id 3 | task 15963 | processing task, is_child = 0 15.44.484.455 I slot print_timing: id 0 | task 15959 | prompt processing, n_tokens = 711, progress = 0.99, t = 4.26 s / 166.76 tokens per second 15.44.594.281 I slot print_timing: id 1 | task 15962 | prompt processing, n_tokens = 150, progress = 0.23, t = 3.04 s / 49.29 tokens per second 15.44.595.029 I slot print_timing: id 2 | task 15958 | prompt processing, n_tokens = 596, progress = 0.99, t = 4.26 s / 139.80 tokens per second 15.44.597.528 I slot print_timing: id 3 | task 15963 | prompt processing, n_tokens = 207, progress = 0.28, t = 3.04 s / 68.02 tokens per second 15.45.496.597 I slot print_timing: id 1 | task 15962 | prompt processing, n_tokens = 545, progress = 0.82, t = 4.06 s / 134.39 tokens per second 15.45.497.895 I slot print_timing: id 3 | task 15963 | prompt processing, n_tokens = 224, progress = 0.30, t = 4.06 s / 55.24 tokens per second 15.46.666.380 I slot print_timing: id 0 | task 15959 | prompt eval time = 5275.53 ms / 715 tokens ( 7.38 ms per token, 135.53 tokens per second) 15.46.666.382 I slot print_timing: id 0 | task 15959 | eval time = 1169.89 ms / 2 tokens ( 1169.89 ms per token, 0.85 tokens per second) 15.46.666.383 I slot print_timing: id 0 | task 15959 | total time = 6445.42 ms / 717 tokens 15.46.666.383 I slot print_timing: id 0 | task 15959 | graphs reused = 14553 15.46.666.384 I slot print_timing: id 0 | task 15959 | graph reallocs = 0 / 0 (same size) / (changed size) 15.46.666.425 I slot release: id 0 | task 15959 | stop processing: n_tokens = 716, truncated = 0 15.46.666.527 I slot print_timing: id 2 | task 15958 | prompt eval time = 5275.52 ms / 600 tokens ( 8.79 ms per token, 113.73 tokens per second) 15.46.666.533 I slot print_timing: id 2 | task 15958 | eval time = 1169.94 ms / 2 tokens ( 1169.94 ms per token, 0.85 tokens per second) 15.46.666.533 I slot print_timing: id 2 | task 15958 | total time = 6445.46 ms / 602 tokens 15.46.666.533 I slot print_timing: id 2 | task 15958 | graphs reused = 14553 15.46.666.534 I slot print_timing: id 2 | task 15958 | graph reallocs = 0 / 0 (same size) / (changed size) 15.46.666.558 I slot release: id 2 | task 15958 | stop processing: n_tokens = 601, truncated = 0 15.46.666.566 I slot print_timing: id 1 | task 15962 | prompt processing, n_tokens = 662, progress = 0.99, t = 5.23 s / 126.69 tokens per second 15.46.668.422 I slot print_timing: id 3 | task 15963 | prompt processing, n_tokens = 612, progress = 0.83, t = 5.22 s / 117.13 tokens per second 15.47.114.604 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 716, t_last = 353729560605 15.47.114.684 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 184.245 MiB) 15.47.121.396 I slot launch_slot_: id 0 | task 15969 | processing task, is_child = 0 15.47.125.192 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 601, t_last = 353729560738 15.47.125.301 I slot launch_slot_: id 2 | task 15970 | processing task, is_child = 0 15.47.125.486 I slot print_timing: id 3 | task 15963 | prompt processing, n_tokens = 736, progress = 0.99, t = 5.67 s / 129.73 tokens per second 15.47.847.618 I slot print_timing: id 1 | task 15962 | prompt eval time = 5673.64 ms / 666 tokens ( 8.52 ms per token, 117.38 tokens per second) 15.47.847.624 I slot print_timing: id 1 | task 15962 | eval time = 733.01 ms / 2 tokens ( 733.01 ms per token, 1.36 tokens per second) 15.47.847.624 I slot print_timing: id 1 | task 15962 | total time = 6406.66 ms / 668 tokens 15.47.847.625 I slot print_timing: id 1 | task 15962 | graphs reused = 14553 15.47.847.625 I slot print_timing: id 1 | task 15962 | graph reallocs = 0 / 0 (same size) / (changed size) 15.47.847.657 I slot release: id 1 | task 15962 | stop processing: n_tokens = 667, truncated = 0 15.48.132.093 I slot print_timing: id 3 | task 15963 | prompt eval time = 6406.42 ms / 740 tokens ( 8.66 ms per token, 115.51 tokens per second) 15.48.132.096 I slot print_timing: id 3 | task 15963 | eval time = 284.32 ms / 2 tokens ( 284.32 ms per token, 3.52 tokens per second) 15.48.132.097 I slot print_timing: id 3 | task 15963 | total time = 6690.73 ms / 742 tokens 15.48.132.097 I slot print_timing: id 3 | task 15963 | graphs reused = 14553 15.48.132.098 I slot print_timing: id 3 | task 15963 | graph reallocs = 0 / 0 (same size) / (changed size) 15.48.132.136 I slot release: id 3 | task 15963 | stop processing: n_tokens = 741, truncated = 0 15.48.132.141 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 667, t_last = 353730741837 15.48.132.211 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 181.974 MiB) 15.48.137.289 I slot launch_slot_: id 1 | task 15973 | processing task, is_child = 0 15.48.137.353 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 144.299 MiB) 15.48.141.011 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 741, t_last = 353731026316 15.48.141.143 I slot launch_slot_: id 3 | task 15974 | processing task, is_child = 0 15.50.915.465 I slot print_timing: id 0 | task 15969 | prompt processing, n_tokens = 617, progress = 0.99, t = 3.79 s / 162.79 tokens per second 15.51.169.449 I slot print_timing: id 2 | task 15970 | prompt processing, n_tokens = 642, progress = 0.99, t = 3.79 s / 169.39 tokens per second 15.52.725.721 I slot print_timing: id 1 | task 15973 | prompt processing, n_tokens = 522, progress = 0.81, t = 4.58 s / 113.87 tokens per second 15.52.727.321 I slot print_timing: id 3 | task 15974 | prompt processing, n_tokens = 522, progress = 0.84, t = 4.58 s / 113.88 tokens per second 15.53.512.498 I slot print_timing: id 0 | task 15969 | prompt eval time = 5600.28 ms / 621 tokens ( 9.02 ms per token, 110.89 tokens per second) 15.53.512.504 I slot print_timing: id 0 | task 15969 | eval time = 786.90 ms / 2 tokens ( 786.90 ms per token, 1.27 tokens per second) 15.53.512.505 I slot print_timing: id 0 | task 15969 | total time = 6387.19 ms / 623 tokens 15.53.512.506 I slot print_timing: id 0 | task 15969 | graphs reused = 14553 15.53.512.506 I slot print_timing: id 0 | task 15969 | graph reallocs = 0 / 0 (same size) / (changed size) 15.53.512.541 I slot release: id 0 | task 15969 | stop processing: n_tokens = 622, truncated = 0 15.53.512.643 I slot print_timing: id 2 | task 15970 | prompt eval time = 5600.30 ms / 646 tokens ( 8.67 ms per token, 115.35 tokens per second) 15.53.512.648 I slot print_timing: id 2 | task 15970 | eval time = 786.93 ms / 2 tokens ( 786.93 ms per token, 1.27 tokens per second) 15.53.512.649 I slot print_timing: id 2 | task 15970 | total time = 6387.23 ms / 648 tokens 15.53.512.649 I slot print_timing: id 2 | task 15970 | graphs reused = 14553 15.53.512.649 I slot print_timing: id 2 | task 15970 | graph reallocs = 0 / 0 (same size) / (changed size) 15.53.512.675 I slot release: id 2 | task 15970 | stop processing: n_tokens = 647, truncated = 0 15.53.512.684 I slot print_timing: id 1 | task 15973 | prompt processing, n_tokens = 642, progress = 0.99, t = 5.37 s / 119.53 tokens per second 15.53.514.665 I slot print_timing: id 3 | task 15974 | prompt processing, n_tokens = 618, progress = 0.99, t = 5.37 s / 115.07 tokens per second 15.53.595.720 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.887 (> 0.100 thold), f_keep = 0.879 15.53.595.798 I slot launch_slot_: id 0 | task 15980 | processing task, is_child = 0 15.53.595.876 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 146.022 MiB) 15.53.600.750 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 647, t_last = 353736406855 15.53.600.863 I slot launch_slot_: id 2 | task 15981 | processing task, is_child = 0 15.54.266.911 I slot print_timing: id 1 | task 15973 | prompt eval time = 5454.19 ms / 646 tokens ( 8.44 ms per token, 118.44 tokens per second) 15.54.266.913 I slot print_timing: id 1 | task 15973 | eval time = 671.29 ms / 2 tokens ( 671.29 ms per token, 1.49 tokens per second) 15.54.266.913 I slot print_timing: id 1 | task 15973 | total time = 6125.47 ms / 648 tokens 15.54.266.917 I slot print_timing: id 1 | task 15973 | graphs reused = 14553 15.54.266.918 I slot print_timing: id 1 | task 15973 | graph reallocs = 0 / 0 (same size) / (changed size) 15.54.266.953 I slot release: id 1 | task 15973 | stop processing: n_tokens = 647, truncated = 0 15.54.267.047 I slot print_timing: id 3 | task 15974 | prompt eval time = 5453.86 ms / 622 tokens ( 8.77 ms per token, 114.05 tokens per second) 15.54.267.049 I slot print_timing: id 3 | task 15974 | eval time = 671.33 ms / 2 tokens ( 671.33 ms per token, 1.49 tokens per second) 15.54.267.050 I slot print_timing: id 3 | task 15974 | total time = 6125.19 ms / 624 tokens 15.54.267.050 I slot print_timing: id 3 | task 15974 | graphs reused = 14553 15.54.267.050 I slot print_timing: id 3 | task 15974 | graph reallocs = 0 / 0 (same size) / (changed size) 15.54.267.069 I slot release: id 3 | task 15974 | stop processing: n_tokens = 623, truncated = 0 15.54.417.101 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.889 (> 0.100 thold), f_keep = 0.845 15.54.417.161 I slot launch_slot_: id 1 | task 15984 | processing task, is_child = 0 15.54.417.227 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 155.882 MiB) 15.54.422.760 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.887 (> 0.100 thold), f_keep = 0.878 15.54.422.813 I slot launch_slot_: id 3 | task 15985 | processing task, is_child = 0 15.55.633.200 I slot print_timing: id 0 | task 15980 | prompt eval time = 816.22 ms / 70 tokens ( 11.66 ms per token, 85.76 tokens per second) 15.55.633.206 I slot print_timing: id 0 | task 15980 | eval time = 1216.10 ms / 2 tokens ( 1216.10 ms per token, 0.82 tokens per second) 15.55.633.206 I slot print_timing: id 0 | task 15980 | total time = 2032.33 ms / 72 tokens 15.55.633.207 I slot print_timing: id 0 | task 15980 | graphs reused = 14553 15.55.633.207 I slot print_timing: id 0 | task 15980 | graph reallocs = 0 / 0 (same size) / (changed size) 15.55.633.244 I slot release: id 0 | task 15980 | stop processing: n_tokens = 618, truncated = 0 15.56.050.785 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.877 (> 0.100 thold), f_keep = 0.888 15.56.050.891 I slot launch_slot_: id 0 | task 15988 | processing task, is_child = 0 15.56.442.342 I slot print_timing: id 1 | task 15984 | prompt eval time = 1627.86 ms / 68 tokens ( 23.94 ms per token, 41.77 tokens per second) 15.56.442.347 I slot print_timing: id 1 | task 15984 | eval time = 391.66 ms / 2 tokens ( 391.66 ms per token, 2.55 tokens per second) 15.56.442.348 I slot print_timing: id 1 | task 15984 | total time = 2019.52 ms / 70 tokens 15.56.442.348 I slot print_timing: id 1 | task 15984 | graphs reused = 14553 15.56.442.349 I slot print_timing: id 1 | task 15984 | graph reallocs = 0 / 0 (same size) / (changed size) 15.56.442.382 I slot release: id 1 | task 15984 | stop processing: n_tokens = 616, truncated = 0 15.56.442.582 I slot print_timing: id 3 | task 15985 | prompt eval time = 1626.22 ms / 70 tokens ( 23.23 ms per token, 43.04 tokens per second) 15.56.442.587 I slot print_timing: id 3 | task 15985 | eval time = 391.80 ms / 2 tokens ( 391.80 ms per token, 2.55 tokens per second) 15.56.442.588 I slot print_timing: id 3 | task 15985 | total time = 2018.02 ms / 72 tokens 15.56.442.588 I slot print_timing: id 3 | task 15985 | graphs reused = 14553 15.56.442.588 I slot print_timing: id 3 | task 15985 | graph reallocs = 0 / 0 (same size) / (changed size) 15.56.442.611 I slot release: id 3 | task 15985 | stop processing: n_tokens = 618, truncated = 0 15.56.503.172 I slot print_timing: id 2 | task 15981 | prompt eval time = 2840.50 ms / 624 tokens ( 4.55 ms per token, 219.68 tokens per second) 15.56.503.177 I slot print_timing: id 2 | task 15981 | eval time = 60.68 ms / 2 tokens ( 60.68 ms per token, 16.48 tokens per second) 15.56.503.177 I slot print_timing: id 2 | task 15981 | total time = 2901.18 ms / 626 tokens 15.56.503.178 I slot print_timing: id 2 | task 15981 | graphs reused = 14553 15.56.503.178 I slot print_timing: id 2 | task 15981 | graph reallocs = 0 / 0 (same size) / (changed size) 15.56.503.206 I slot release: id 2 | task 15981 | stop processing: n_tokens = 625, truncated = 0 15.56.503.212 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.877 (> 0.100 thold), f_keep = 0.890 15.56.503.281 I slot launch_slot_: id 1 | task 15991 | processing task, is_child = 0 15.56.503.355 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 152.819 MiB) 15.56.507.008 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 181.480 MiB) 15.56.511.438 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.834 (> 0.100 thold), f_keep = 0.875 15.56.511.514 I slot launch_slot_: id 2 | task 15992 | processing task, is_child = 0 15.56.511.574 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.885 (> 0.100 thold), f_keep = 0.885 15.56.511.613 I slot launch_slot_: id 3 | task 15993 | processing task, is_child = 0 15.57.329.078 I slot print_timing: id 0 | task 15988 | prompt eval time = 452.14 ms / 77 tokens ( 5.87 ms per token, 170.30 tokens per second) 15.57.329.081 I slot print_timing: id 0 | task 15988 | eval time = 826.03 ms / 2 tokens ( 826.03 ms per token, 1.21 tokens per second) 15.57.329.082 I slot print_timing: id 0 | task 15988 | total time = 1278.18 ms / 79 tokens 15.57.329.082 I slot print_timing: id 0 | task 15988 | graphs reused = 14553 15.57.329.083 I slot print_timing: id 0 | task 15988 | graph reallocs = 0 / 0 (same size) / (changed size) 15.57.329.127 I slot release: id 0 | task 15988 | stop processing: n_tokens = 627, truncated = 0 15.57.417.821 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 627, t_last = 353740223308 15.57.417.893 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 151.547 MiB) 15.57.426.896 I slot launch_slot_: id 0 | task 15996 | processing task, is_child = 0 15.57.913.455 I slot print_timing: id 1 | task 15991 | prompt eval time = 905.98 ms / 77 tokens ( 11.77 ms per token, 84.99 tokens per second) 15.57.913.459 I slot print_timing: id 1 | task 15991 | eval time = 495.85 ms / 2 tokens ( 495.85 ms per token, 2.02 tokens per second) 15.57.913.460 I slot print_timing: id 1 | task 15991 | total time = 1401.83 ms / 79 tokens 15.57.913.460 I slot print_timing: id 1 | task 15991 | graphs reused = 14553 15.57.913.461 I slot print_timing: id 1 | task 15991 | graph reallocs = 0 / 0 (same size) / (changed size) 15.57.913.499 I slot release: id 1 | task 15991 | stop processing: n_tokens = 626, truncated = 0 15.57.913.593 I slot print_timing: id 2 | task 15992 | prompt eval time = 904.90 ms / 109 tokens ( 8.30 ms per token, 120.46 tokens per second) 15.57.913.595 I slot print_timing: id 2 | task 15992 | eval time = 495.89 ms / 2 tokens ( 495.89 ms per token, 2.02 tokens per second) 15.57.913.596 I slot print_timing: id 2 | task 15992 | total time = 1400.79 ms / 111 tokens 15.57.913.596 I slot print_timing: id 2 | task 15992 | graphs reused = 14553 15.57.913.596 I slot print_timing: id 2 | task 15992 | graph reallocs = 0 / 0 (same size) / (changed size) 15.57.913.617 I slot release: id 2 | task 15992 | stop processing: n_tokens = 657, truncated = 0 15.57.913.771 I slot print_timing: id 3 | task 15993 | prompt eval time = 903.86 ms / 71 tokens ( 12.73 ms per token, 78.55 tokens per second) 15.57.913.779 I slot print_timing: id 3 | task 15993 | eval time = 495.95 ms / 2 tokens ( 495.95 ms per token, 2.02 tokens per second) 15.57.913.780 I slot print_timing: id 3 | task 15993 | total time = 1399.82 ms / 73 tokens 15.57.913.780 I slot print_timing: id 3 | task 15993 | graphs reused = 14553 15.57.913.780 I slot print_timing: id 3 | task 15993 | graph reallocs = 0 / 0 (same size) / (changed size) 15.57.913.802 I slot release: id 3 | task 15993 | stop processing: n_tokens = 619, truncated = 0 15.57.922.547 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 626, t_last = 353740807679 15.57.922.623 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 145.516 MiB) 15.58.243.164 I slot launch_slot_: id 1 | task 15999 | processing task, is_child = 0 15.58.243.242 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 147.718 MiB) 15.58.243.248 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 160.873 MiB) 15.58.249.163 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 159.246 MiB) 15.58.254.172 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 657, t_last = 353740807797 15.58.254.294 I slot launch_slot_: id 2 | task 16000 | processing task, is_child = 0 15.58.254.365 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 619, t_last = 353740807982 15.58.254.458 I slot launch_slot_: id 3 | task 16001 | processing task, is_child = 0 16.00.976.415 I slot print_timing: id 0 | task 15996 | prompt processing, n_tokens = 677, progress = 0.85, t = 3.55 s / 190.73 tokens per second 16.02.192.596 I slot print_timing: id 0 | task 15996 | prompt processing, n_tokens = 792, progress = 0.99, t = 4.77 s / 166.19 tokens per second 16.02.604.437 I slot print_timing: id 1 | task 15999 | prompt processing, n_tokens = 482, progress = 0.48, t = 3.94 s / 122.39 tokens per second 16.02.606.771 I slot print_timing: id 2 | task 16000 | prompt processing, n_tokens = 269, progress = 0.34, t = 3.94 s / 68.31 tokens per second 16.02.607.859 I slot print_timing: id 3 | task 16001 | prompt processing, n_tokens = 472, progress = 0.48, t = 3.94 s / 119.86 tokens per second 16.04.848.965 I slot print_timing: id 1 | task 15999 | prompt processing, n_tokens = 824, progress = 0.83, t = 6.59 s / 124.96 tokens per second 16.04.850.663 I slot print_timing: id 2 | task 16000 | prompt processing, n_tokens = 677, progress = 0.86, t = 6.59 s / 102.67 tokens per second 16.04.853.091 I slot print_timing: id 3 | task 16001 | prompt processing, n_tokens = 824, progress = 0.83, t = 6.59 s / 124.96 tokens per second 16.06.085.292 I slot print_timing: id 0 | task 15996 | prompt eval time = 7422.05 ms / 796 tokens ( 9.32 ms per token, 107.25 tokens per second) 16.06.085.303 I slot print_timing: id 0 | task 15996 | eval time = 1236.34 ms / 2 tokens ( 1236.34 ms per token, 0.81 tokens per second) 16.06.085.305 I slot print_timing: id 0 | task 15996 | total time = 8658.38 ms / 798 tokens 16.06.085.306 I slot print_timing: id 0 | task 15996 | graphs reused = 14553 16.06.085.306 I slot print_timing: id 0 | task 15996 | graph reallocs = 0 / 0 (same size) / (changed size) 16.06.085.345 I slot release: id 0 | task 15996 | stop processing: n_tokens = 797, truncated = 0 16.06.085.357 I slot print_timing: id 1 | task 15999 | prompt processing, n_tokens = 994, progress = 1.00, t = 7.83 s / 126.94 tokens per second 16.06.087.379 I slot print_timing: id 2 | task 16000 | prompt processing, n_tokens = 781, progress = 0.99, t = 7.83 s / 99.74 tokens per second 16.06.089.504 I slot print_timing: id 3 | task 16001 | prompt processing, n_tokens = 984, progress = 1.00, t = 7.83 s / 125.66 tokens per second 16.06.171.805 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 797, t_last = 353748979525 16.06.171.884 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 161.352 MiB) 16.06.176.841 I slot launch_slot_: id 0 | task 16008 | processing task, is_child = 0 16.06.670.875 I slot print_timing: id 1 | task 15999 | prompt eval time = 7917.11 ms / 998 tokens ( 7.93 ms per token, 126.06 tokens per second) 16.06.670.877 I slot print_timing: id 1 | task 15999 | eval time = 499.29 ms / 2 tokens ( 499.29 ms per token, 2.00 tokens per second) 16.06.670.878 I slot print_timing: id 1 | task 15999 | total time = 8416.40 ms / 1000 tokens 16.06.670.878 I slot print_timing: id 1 | task 15999 | graphs reused = 14553 16.06.670.878 I slot print_timing: id 1 | task 15999 | graph reallocs = 0 / 0 (same size) / (changed size) 16.06.670.937 I slot release: id 1 | task 15999 | stop processing: n_tokens = 999, truncated = 0 16.06.671.079 I slot print_timing: id 2 | task 16000 | prompt eval time = 7917.13 ms / 785 tokens ( 10.09 ms per token, 99.15 tokens per second) 16.06.671.082 I slot print_timing: id 2 | task 16000 | eval time = 499.38 ms / 2 tokens ( 499.38 ms per token, 2.00 tokens per second) 16.06.671.082 I slot print_timing: id 2 | task 16000 | total time = 8416.51 ms / 787 tokens 16.06.671.082 I slot print_timing: id 2 | task 16000 | graphs reused = 14553 16.06.671.083 I slot print_timing: id 2 | task 16000 | graph reallocs = 0 / 0 (same size) / (changed size) 16.06.671.121 I slot release: id 2 | task 16000 | stop processing: n_tokens = 786, truncated = 0 16.06.671.260 I slot print_timing: id 3 | task 16001 | prompt eval time = 7917.15 ms / 988 tokens ( 8.01 ms per token, 124.79 tokens per second) 16.06.671.262 I slot print_timing: id 3 | task 16001 | eval time = 499.46 ms / 2 tokens ( 499.46 ms per token, 2.00 tokens per second) 16.06.671.262 I slot print_timing: id 3 | task 16001 | total time = 8416.61 ms / 990 tokens 16.06.671.262 I slot print_timing: id 3 | task 16001 | graphs reused = 14553 16.06.671.263 I slot print_timing: id 3 | task 16001 | graph reallocs = 0 / 0 (same size) / (changed size) 16.06.671.289 I slot release: id 3 | task 16001 | stop processing: n_tokens = 989, truncated = 0 16.07.135.586 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.892 16.07.135.679 I slot launch_slot_: id 1 | task 16012 | processing task, is_child = 0 16.07.135.767 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 159.629 MiB) 16.07.558.818 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.317 MiB) 16.07.564.557 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.900 16.07.564.652 I slot launch_slot_: id 3 | task 16013 | processing task, is_child = 0 16.07.564.725 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 786, t_last = 353749565301 16.07.566.413 I slot launch_slot_: id 2 | task 16014 | processing task, is_child = 0 16.10.001.821 I slot print_timing: id 0 | task 16008 | prompt processing, n_tokens = 987, progress = 1.00, t = 3.82 s / 258.06 tokens per second 16.10.128.692 I slot print_timing: id 1 | task 16012 | prompt eval time = 2434.03 ms / 86 tokens ( 28.30 ms per token, 35.33 tokens per second) 16.10.128.699 I slot print_timing: id 1 | task 16012 | eval time = 127.03 ms / 2 tokens ( 127.03 ms per token, 7.87 tokens per second) 16.10.128.700 I slot print_timing: id 1 | task 16012 | total time = 2561.06 ms / 88 tokens 16.10.128.701 I slot print_timing: id 1 | task 16012 | graphs reused = 14553 16.10.128.701 I slot print_timing: id 1 | task 16012 | graph reallocs = 0 / 0 (same size) / (changed size) 16.10.128.756 I slot release: id 1 | task 16012 | stop processing: n_tokens = 978, truncated = 0 16.10.129.030 I slot print_timing: id 3 | task 16013 | prompt eval time = 2430.55 ms / 96 tokens ( 25.32 ms per token, 39.50 tokens per second) 16.10.129.033 I slot print_timing: id 3 | task 16013 | eval time = 127.22 ms / 2 tokens ( 127.22 ms per token, 7.86 tokens per second) 16.10.129.035 I slot print_timing: id 3 | task 16013 | total time = 2557.76 ms / 98 tokens 16.10.129.036 I slot print_timing: id 3 | task 16013 | graphs reused = 14553 16.10.129.036 I slot print_timing: id 3 | task 16013 | graph reallocs = 0 / 0 (same size) / (changed size) 16.10.129.072 I slot release: id 3 | task 16013 | stop processing: n_tokens = 987, truncated = 0 16.10.175.557 I slot print_timing: id 0 | task 16008 | prompt eval time = 3951.66 ms / 991 tokens ( 3.99 ms per token, 250.78 tokens per second) 16.10.175.566 I slot print_timing: id 0 | task 16008 | eval time = 47.04 ms / 2 tokens ( 47.04 ms per token, 21.26 tokens per second) 16.10.175.567 I slot print_timing: id 0 | task 16008 | total time = 3998.70 ms / 993 tokens 16.10.175.568 I slot print_timing: id 0 | task 16008 | graphs reused = 14553 16.10.175.569 I slot print_timing: id 0 | task 16008 | graph reallocs = 0 / 0 (same size) / (changed size) 16.10.175.637 I slot release: id 0 | task 16008 | stop processing: n_tokens = 992, truncated = 0 16.10.175.861 I slot print_timing: id 2 | task 16014 | prompt eval time = 2560.10 ms / 162 tokens ( 15.80 ms per token, 63.28 tokens per second) 16.10.175.867 I slot print_timing: id 2 | task 16014 | eval time = 46.95 ms / 2 tokens ( 46.95 ms per token, 21.30 tokens per second) 16.10.175.869 I slot print_timing: id 2 | task 16014 | total time = 2607.05 ms / 164 tokens 16.10.175.869 I slot print_timing: id 2 | task 16014 | graphs reused = 14553 16.10.175.870 I slot print_timing: id 2 | task 16014 | graph reallocs = 0 / 0 (same size) / (changed size) 16.10.175.922 I slot release: id 2 | task 16014 | stop processing: n_tokens = 986, truncated = 0 16.10.175.933 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.901 (> 0.100 thold), f_keep = 0.898 16.10.176.108 I slot launch_slot_: id 0 | task 16019 | processing task, is_child = 0 16.10.185.916 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 147.403 MiB) 16.10.193.220 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 147.212 MiB) 16.10.200.026 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.911 16.10.200.121 I slot launch_slot_: id 1 | task 16020 | processing task, is_child = 0 16.10.200.347 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.896 (> 0.100 thold), f_keep = 0.904 16.10.200.410 I slot launch_slot_: id 2 | task 16021 | processing task, is_child = 0 16.10.200.521 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.903 16.10.200.585 I slot launch_slot_: id 3 | task 16022 | processing task, is_child = 0 16.11.280.890 I slot print_timing: id 0 | task 16019 | prompt eval time = 1037.95 ms / 98 tokens ( 10.59 ms per token, 94.42 tokens per second) 16.11.280.892 I slot print_timing: id 0 | task 16019 | eval time = 42.34 ms / 2 tokens ( 42.34 ms per token, 23.62 tokens per second) 16.11.280.893 I slot print_timing: id 0 | task 16019 | total time = 1080.29 ms / 100 tokens 16.11.280.893 I slot print_timing: id 0 | task 16019 | graphs reused = 14553 16.11.280.894 I slot print_timing: id 0 | task 16019 | graph reallocs = 0 / 0 (same size) / (changed size) 16.11.280.932 I slot release: id 0 | task 16019 | stop processing: n_tokens = 990, truncated = 0 16.11.281.021 I slot print_timing: id 1 | task 16020 | prompt eval time = 1036.52 ms / 88 tokens ( 11.78 ms per token, 84.90 tokens per second) 16.11.281.023 I slot print_timing: id 1 | task 16020 | eval time = 42.36 ms / 2 tokens ( 42.36 ms per token, 23.61 tokens per second) 16.11.281.023 I slot print_timing: id 1 | task 16020 | total time = 1078.88 ms / 90 tokens 16.11.281.023 I slot print_timing: id 1 | task 16020 | graphs reused = 14553 16.11.281.024 I slot print_timing: id 1 | task 16020 | graph reallocs = 0 / 0 (same size) / (changed size) 16.11.281.056 I slot release: id 1 | task 16020 | stop processing: n_tokens = 980, truncated = 0 16.11.281.138 I slot print_timing: id 2 | task 16021 | prompt eval time = 1035.15 ms / 103 tokens ( 10.05 ms per token, 99.50 tokens per second) 16.11.281.140 I slot print_timing: id 2 | task 16021 | eval time = 42.36 ms / 2 tokens ( 42.36 ms per token, 23.61 tokens per second) 16.11.281.140 I slot print_timing: id 2 | task 16021 | total time = 1077.51 ms / 105 tokens 16.11.281.140 I slot print_timing: id 2 | task 16021 | graphs reused = 14553 16.11.281.141 I slot print_timing: id 2 | task 16021 | graph reallocs = 0 / 0 (same size) / (changed size) 16.11.281.170 I slot release: id 2 | task 16021 | stop processing: n_tokens = 995, truncated = 0 16.11.281.256 I slot print_timing: id 3 | task 16022 | prompt eval time = 1033.80 ms / 99 tokens ( 10.44 ms per token, 95.76 tokens per second) 16.11.281.260 I slot print_timing: id 3 | task 16022 | eval time = 42.38 ms / 2 tokens ( 42.38 ms per token, 23.60 tokens per second) 16.11.281.261 I slot print_timing: id 3 | task 16022 | total time = 1076.18 ms / 101 tokens 16.11.281.261 I slot print_timing: id 3 | task 16022 | graphs reused = 14553 16.11.281.261 I slot print_timing: id 3 | task 16022 | graph reallocs = 0 / 0 (same size) / (changed size) 16.11.281.281 I slot release: id 3 | task 16022 | stop processing: n_tokens = 991, truncated = 0 16.11.290.430 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.904 (> 0.100 thold), f_keep = 0.900 16.11.290.478 I slot launch_slot_: id 0 | task 16026 | processing task, is_child = 0 16.11.290.557 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 161.762 MiB) 16.11.290.562 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 159.561 MiB) 16.11.299.608 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 160.326 MiB) 16.11.306.033 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 153.803 MiB) 16.11.306.039 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 191.203 MiB) 16.11.312.454 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.909 16.11.312.516 I slot launch_slot_: id 1 | task 16027 | processing task, is_child = 0 16.11.312.653 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.895 16.11.312.691 I slot launch_slot_: id 2 | task 16028 | processing task, is_child = 0 16.11.312.765 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.899 16.11.312.804 I slot launch_slot_: id 3 | task 16029 | processing task, is_child = 0 16.12.258.086 I slot print_timing: id 0 | task 16026 | prompt eval time = 902.99 ms / 95 tokens ( 9.51 ms per token, 105.21 tokens per second) 16.12.258.089 I slot print_timing: id 0 | task 16026 | eval time = 42.29 ms / 2 tokens ( 42.29 ms per token, 23.65 tokens per second) 16.12.258.089 I slot print_timing: id 0 | task 16026 | total time = 945.27 ms / 97 tokens 16.12.258.090 I slot print_timing: id 0 | task 16026 | graphs reused = 14553 16.12.258.090 I slot print_timing: id 0 | task 16026 | graph reallocs = 0 / 0 (same size) / (changed size) 16.12.258.133 I slot release: id 0 | task 16026 | stop processing: n_tokens = 987, truncated = 0 16.12.258.219 I slot print_timing: id 1 | task 16027 | prompt eval time = 901.87 ms / 91 tokens ( 9.91 ms per token, 100.90 tokens per second) 16.12.258.221 I slot print_timing: id 1 | task 16027 | eval time = 42.33 ms / 2 tokens ( 42.33 ms per token, 23.63 tokens per second) 16.12.258.221 I slot print_timing: id 1 | task 16027 | total time = 944.20 ms / 93 tokens 16.12.258.222 I slot print_timing: id 1 | task 16027 | graphs reused = 14553 16.12.258.222 I slot print_timing: id 1 | task 16027 | graph reallocs = 0 / 0 (same size) / (changed size) 16.12.258.253 I slot release: id 1 | task 16027 | stop processing: n_tokens = 983, truncated = 0 16.12.258.337 I slot print_timing: id 2 | task 16028 | prompt eval time = 900.82 ms / 92 tokens ( 9.79 ms per token, 102.13 tokens per second) 16.12.258.342 I slot print_timing: id 2 | task 16028 | eval time = 42.34 ms / 2 tokens ( 42.34 ms per token, 23.62 tokens per second) 16.12.258.342 I slot print_timing: id 2 | task 16028 | total time = 943.16 ms / 94 tokens 16.12.258.342 I slot print_timing: id 2 | task 16028 | graphs reused = 14553 16.12.258.343 I slot print_timing: id 2 | task 16028 | graph reallocs = 0 / 0 (same size) / (changed size) 16.12.258.372 I slot release: id 2 | task 16028 | stop processing: n_tokens = 984, truncated = 0 16.12.258.467 I slot print_timing: id 3 | task 16029 | prompt eval time = 899.76 ms / 96 tokens ( 9.37 ms per token, 106.70 tokens per second) 16.12.258.469 I slot print_timing: id 3 | task 16029 | eval time = 42.37 ms / 2 tokens ( 42.37 ms per token, 23.60 tokens per second) 16.12.258.469 I slot print_timing: id 3 | task 16029 | total time = 942.13 ms / 98 tokens 16.12.258.469 I slot print_timing: id 3 | task 16029 | graphs reused = 14553 16.12.258.470 I slot print_timing: id 3 | task 16029 | graph reallocs = 0 / 0 (same size) / (changed size) 16.12.258.491 I slot release: id 3 | task 16029 | stop processing: n_tokens = 988, truncated = 0 16.12.268.676 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.903 16.12.268.731 I slot launch_slot_: id 0 | task 16033 | processing task, is_child = 0 16.12.268.816 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 154.665 MiB) 16.12.274.541 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 153.133 MiB) 16.12.274.550 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 181.687 MiB) 16.12.281.670 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 181.906 MiB) 16.12.288.131 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 983, t_last = 353755152433 16.12.288.289 I slot launch_slot_: id 1 | task 16034 | processing task, is_child = 0 16.12.288.427 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 984, t_last = 353755152552 16.12.288.539 I slot launch_slot_: id 2 | task 16035 | processing task, is_child = 0 16.12.288.608 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 988, t_last = 353755152671 16.12.288.719 I slot launch_slot_: id 3 | task 16036 | processing task, is_child = 0 16.15.032.602 I slot print_timing: id 0 | task 16033 | prompt eval time = 2071.62 ms / 94 tokens ( 22.04 ms per token, 45.38 tokens per second) 16.15.032.604 I slot print_timing: id 0 | task 16033 | eval time = 672.25 ms / 2 tokens ( 672.25 ms per token, 1.49 tokens per second) 16.15.032.605 I slot print_timing: id 0 | task 16033 | total time = 2743.87 ms / 96 tokens 16.15.032.605 I slot print_timing: id 0 | task 16033 | graphs reused = 14553 16.15.032.606 I slot print_timing: id 0 | task 16033 | graph reallocs = 0 / 0 (same size) / (changed size) 16.15.032.650 I slot release: id 0 | task 16033 | stop processing: n_tokens = 986, truncated = 0 16.17.038.513 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 986, t_last = 353757926830 16.17.038.610 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 183.438 MiB) 16.17.111.555 I slot launch_slot_: id 0 | task 16041 | processing task, is_child = 0 16.17.111.706 I slot print_timing: id 1 | task 16034 | prompt processing, n_tokens = 764, progress = 0.79, t = 4.75 s / 160.90 tokens per second 16.17.112.990 I slot print_timing: id 2 | task 16035 | prompt processing, n_tokens = 764, progress = 0.86, t = 4.75 s / 160.90 tokens per second 16.17.114.106 I slot print_timing: id 3 | task 16036 | prompt processing, n_tokens = 764, progress = 0.84, t = 4.75 s / 160.91 tokens per second 16.18.554.807 I slot print_timing: id 1 | task 16034 | prompt processing, n_tokens = 964, progress = 1.00, t = 6.19 s / 155.66 tokens per second 16.18.556.347 I slot print_timing: id 2 | task 16035 | prompt processing, n_tokens = 889, progress = 1.00, t = 6.19 s / 143.56 tokens per second 16.18.557.859 I slot print_timing: id 3 | task 16036 | prompt processing, n_tokens = 901, progress = 1.00, t = 6.19 s / 145.50 tokens per second 16.19.436.413 I slot print_timing: id 1 | task 16034 | prompt eval time = 6782.14 ms / 968 tokens ( 7.01 ms per token, 142.73 tokens per second) 16.19.436.415 I slot print_timing: id 1 | task 16034 | eval time = 364.11 ms / 2 tokens ( 364.11 ms per token, 2.75 tokens per second) 16.19.436.415 I slot print_timing: id 1 | task 16034 | total time = 7146.25 ms / 970 tokens 16.19.436.416 I slot print_timing: id 1 | task 16034 | graphs reused = 14553 16.19.436.416 I slot print_timing: id 1 | task 16034 | graph reallocs = 0 / 0 (same size) / (changed size) 16.19.436.463 I slot release: id 1 | task 16034 | stop processing: n_tokens = 969, truncated = 0 16.19.436.577 I slot print_timing: id 2 | task 16035 | prompt eval time = 6782.19 ms / 893 tokens ( 7.59 ms per token, 131.67 tokens per second) 16.19.436.584 I slot print_timing: id 2 | task 16035 | eval time = 364.08 ms / 2 tokens ( 364.08 ms per token, 2.75 tokens per second) 16.19.436.584 I slot print_timing: id 2 | task 16035 | total time = 7146.27 ms / 895 tokens 16.19.436.585 I slot print_timing: id 2 | task 16035 | graphs reused = 14553 16.19.436.585 I slot print_timing: id 2 | task 16035 | graph reallocs = 0 / 0 (same size) / (changed size) 16.19.436.614 I slot release: id 2 | task 16035 | stop processing: n_tokens = 894, truncated = 0 16.19.436.764 I slot print_timing: id 3 | task 16036 | prompt eval time = 6782.30 ms / 905 tokens ( 7.49 ms per token, 133.44 tokens per second) 16.19.436.766 I slot print_timing: id 3 | task 16036 | eval time = 364.05 ms / 2 tokens ( 364.05 ms per token, 2.75 tokens per second) 16.19.436.766 I slot print_timing: id 3 | task 16036 | total time = 7146.35 ms / 907 tokens 16.19.436.767 I slot print_timing: id 3 | task 16036 | graphs reused = 14553 16.19.436.767 I slot print_timing: id 3 | task 16036 | graph reallocs = 0 / 0 (same size) / (changed size) 16.19.436.796 I slot release: id 3 | task 16036 | stop processing: n_tokens = 906, truncated = 0 16.20.133.976 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 969, t_last = 353762330643 16.20.134.058 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 232.003 MiB) 16.20.616.297 I slot launch_slot_: id 1 | task 16047 | processing task, is_child = 0 16.20.616.391 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 229.651 MiB) 16.20.632.843 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.880 (> 0.100 thold), f_keep = 0.883 16.20.632.914 I slot launch_slot_: id 2 | task 16048 | processing task, is_child = 0 16.20.632.983 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.864 (> 0.100 thold), f_keep = 0.871 16.20.633.029 I slot launch_slot_: id 3 | task 16049 | processing task, is_child = 0 16.20.633.035 I slot print_timing: id 0 | task 16041 | prompt processing, n_tokens = 937, progress = 1.00, t = 3.02 s / 310.02 tokens per second 16.21.723.487 I slot print_timing: id 0 | task 16041 | prompt eval time = 4421.55 ms / 941 tokens ( 4.70 ms per token, 212.82 tokens per second) 16.21.723.489 I slot print_timing: id 0 | task 16041 | eval time = 190.36 ms / 2 tokens ( 190.36 ms per token, 5.25 tokens per second) 16.21.723.490 I slot print_timing: id 0 | task 16041 | total time = 4611.91 ms / 943 tokens 16.21.723.490 I slot print_timing: id 0 | task 16041 | graphs reused = 14553 16.21.723.491 I slot print_timing: id 0 | task 16041 | graph reallocs = 0 / 0 (same size) / (changed size) 16.21.723.535 I slot release: id 0 | task 16041 | stop processing: n_tokens = 942, truncated = 0 16.22.491.335 I slot print_timing: id 2 | task 16048 | prompt eval time = 1089.16 ms / 108 tokens ( 10.08 ms per token, 99.16 tokens per second) 16.22.491.339 I slot print_timing: id 2 | task 16048 | eval time = 767.65 ms / 2 tokens ( 767.65 ms per token, 1.30 tokens per second) 16.22.491.339 I slot print_timing: id 2 | task 16048 | total time = 1856.81 ms / 110 tokens 16.22.491.340 I slot print_timing: id 2 | task 16048 | graphs reused = 14553 16.22.491.340 I slot print_timing: id 2 | task 16048 | graph reallocs = 0 / 0 (same size) / (changed size) 16.22.491.385 I slot release: id 2 | task 16048 | stop processing: n_tokens = 898, truncated = 0 16.22.491.535 I slot print_timing: id 3 | task 16049 | prompt eval time = 1088.16 ms / 124 tokens ( 8.78 ms per token, 113.95 tokens per second) 16.22.491.538 I slot print_timing: id 3 | task 16049 | eval time = 767.75 ms / 2 tokens ( 767.75 ms per token, 1.30 tokens per second) 16.22.491.538 I slot print_timing: id 3 | task 16049 | total time = 1855.90 ms / 126 tokens 16.22.491.538 I slot print_timing: id 3 | task 16049 | graphs reused = 14553 16.22.491.539 I slot print_timing: id 3 | task 16049 | graph reallocs = 0 / 0 (same size) / (changed size) 16.22.491.573 I slot release: id 3 | task 16049 | stop processing: n_tokens = 914, truncated = 0 16.22.491.578 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 942, t_last = 353764617715 16.22.491.661 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 236.161 MiB) 16.22.501.540 I slot launch_slot_: id 0 | task 16053 | processing task, is_child = 0 16.22.501.620 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 233.508 MiB) 16.22.507.436 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 204.063 MiB) 16.22.512.538 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 898, t_last = 353765385565 16.22.512.668 I slot launch_slot_: id 2 | task 16054 | processing task, is_child = 0 16.22.512.758 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 914, t_last = 353765385753 16.22.512.861 I slot launch_slot_: id 3 | task 16055 | processing task, is_child = 0 16.26.009.906 I slot print_timing: id 1 | task 16047 | prompt eval time = 3170.90 ms / 652 tokens ( 4.86 ms per token, 205.62 tokens per second) 16.26.009.911 I slot print_timing: id 1 | task 16047 | eval time = 2204.61 ms / 2 tokens ( 2204.61 ms per token, 0.45 tokens per second) 16.26.009.912 I slot print_timing: id 1 | task 16047 | total time = 5375.52 ms / 654 tokens 16.26.009.912 I slot print_timing: id 1 | task 16047 | graphs reused = 14553 16.26.009.913 I slot print_timing: id 1 | task 16047 | graph reallocs = 0 / 0 (same size) / (changed size) 16.26.009.946 I slot release: id 1 | task 16047 | stop processing: n_tokens = 653, truncated = 0 16.26.009.958 I slot print_timing: id 0 | task 16053 | prompt processing, n_tokens = 536, progress = 0.77, t = 3.50 s / 153.28 tokens per second 16.26.011.227 I slot print_timing: id 2 | task 16054 | prompt processing, n_tokens = 536, progress = 0.85, t = 3.50 s / 153.34 tokens per second 16.26.012.613 I slot print_timing: id 3 | task 16055 | prompt processing, n_tokens = 536, progress = 0.83, t = 3.50 s / 153.34 tokens per second 16.26.920.493 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.871 (> 0.100 thold), f_keep = 0.859 16.26.920.587 I slot launch_slot_: id 1 | task 16060 | processing task, is_child = 0 16.26.920.594 I slot print_timing: id 0 | task 16053 | prompt processing, n_tokens = 692, progress = 0.99, t = 4.41 s / 157.00 tokens per second 16.27.011.297 I slot print_timing: id 2 | task 16054 | prompt processing, n_tokens = 623, progress = 0.99, t = 4.41 s / 141.39 tokens per second 16.27.013.797 I slot print_timing: id 3 | task 16055 | prompt processing, n_tokens = 639, progress = 0.99, t = 4.41 s / 145.02 tokens per second 16.27.523.690 I slot print_timing: id 0 | task 16053 | prompt eval time = 4912.94 ms / 696 tokens ( 7.06 ms per token, 141.67 tokens per second) 16.27.523.696 I slot print_timing: id 0 | task 16053 | eval time = 97.87 ms / 2 tokens ( 97.87 ms per token, 10.22 tokens per second) 16.27.523.696 I slot print_timing: id 0 | task 16053 | total time = 5010.81 ms / 698 tokens 16.27.523.697 I slot print_timing: id 0 | task 16053 | graphs reused = 14553 16.27.523.697 I slot print_timing: id 0 | task 16053 | graph reallocs = 0 / 0 (same size) / (changed size) 16.27.523.732 I slot release: id 0 | task 16053 | stop processing: n_tokens = 697, truncated = 0 16.27.523.978 I slot print_timing: id 2 | task 16054 | prompt eval time = 4911.71 ms / 627 tokens ( 7.83 ms per token, 127.65 tokens per second) 16.27.523.984 I slot print_timing: id 2 | task 16054 | eval time = 98.07 ms / 2 tokens ( 98.07 ms per token, 10.20 tokens per second) 16.27.523.984 I slot print_timing: id 2 | task 16054 | total time = 5009.78 ms / 629 tokens 16.27.523.985 I slot print_timing: id 2 | task 16054 | graphs reused = 14553 16.27.523.985 I slot print_timing: id 2 | task 16054 | graph reallocs = 0 / 0 (same size) / (changed size) 16.27.524.010 I slot release: id 2 | task 16054 | stop processing: n_tokens = 628, truncated = 0 16.27.524.120 I slot print_timing: id 3 | task 16055 | prompt eval time = 4911.72 ms / 643 tokens ( 7.64 ms per token, 130.91 tokens per second) 16.27.524.124 I slot print_timing: id 3 | task 16055 | eval time = 98.08 ms / 2 tokens ( 98.08 ms per token, 10.20 tokens per second) 16.27.524.124 I slot print_timing: id 3 | task 16055 | total time = 5009.80 ms / 645 tokens 16.27.524.125 I slot print_timing: id 3 | task 16055 | graphs reused = 14553 16.27.524.125 I slot print_timing: id 3 | task 16055 | graph reallocs = 0 / 0 (same size) / (changed size) 16.27.524.143 I slot release: id 3 | task 16055 | stop processing: n_tokens = 644, truncated = 0 16.27.545.795 I slot print_timing: id 1 | task 16060 | prompt eval time = 514.67 ms / 83 tokens ( 6.20 ms per token, 161.27 tokens per second) 16.27.545.797 I slot print_timing: id 1 | task 16060 | eval time = 21.90 ms / 2 tokens ( 21.90 ms per token, 45.67 tokens per second) 16.27.545.798 I slot print_timing: id 1 | task 16060 | total time = 536.57 ms / 85 tokens 16.27.545.798 I slot print_timing: id 1 | task 16060 | graphs reused = 14553 16.27.545.799 I slot print_timing: id 1 | task 16060 | graph reallocs = 0 / 0 (same size) / (changed size) 16.27.545.836 I slot release: id 1 | task 16060 | stop processing: n_tokens = 645, truncated = 0 16.27.545.844 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.889 (> 0.100 thold), f_keep = 0.805 16.27.545.904 I slot launch_slot_: id 0 | task 16064 | processing task, is_child = 0 16.27.545.989 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 234.269 MiB) 16.27.555.130 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 232.382 MiB) 16.27.558.779 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.858 (> 0.100 thold), f_keep = 0.870 16.27.558.843 I slot launch_slot_: id 1 | task 16065 | processing task, is_child = 0 16.27.558.990 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.882 (> 0.100 thold), f_keep = 0.874 16.27.559.039 I slot launch_slot_: id 3 | task 16066 | processing task, is_child = 0 16.27.559.112 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.870 (> 0.100 thold), f_keep = 0.893 16.27.559.158 I slot launch_slot_: id 2 | task 16067 | processing task, is_child = 0 16.28.573.065 I slot print_timing: id 0 | task 16064 | prompt eval time = 971.62 ms / 70 tokens ( 13.88 ms per token, 72.04 tokens per second) 16.28.573.068 I slot print_timing: id 0 | task 16064 | eval time = 42.27 ms / 2 tokens ( 42.27 ms per token, 23.66 tokens per second) 16.28.573.069 I slot print_timing: id 0 | task 16064 | total time = 1013.89 ms / 72 tokens 16.28.573.069 I slot print_timing: id 0 | task 16064 | graphs reused = 14553 16.28.573.069 I slot print_timing: id 0 | task 16064 | graph reallocs = 0 / 0 (same size) / (changed size) 16.28.573.103 I slot release: id 0 | task 16064 | stop processing: n_tokens = 632, truncated = 0 16.28.573.189 I slot print_timing: id 1 | task 16065 | prompt eval time = 970.51 ms / 93 tokens ( 10.44 ms per token, 95.83 tokens per second) 16.28.573.192 I slot print_timing: id 1 | task 16065 | eval time = 42.28 ms / 2 tokens ( 42.28 ms per token, 23.65 tokens per second) 16.28.573.192 I slot print_timing: id 1 | task 16065 | total time = 1012.79 ms / 95 tokens 16.28.573.192 I slot print_timing: id 1 | task 16065 | graphs reused = 14553 16.28.573.193 I slot print_timing: id 1 | task 16065 | graph reallocs = 0 / 0 (same size) / (changed size) 16.28.573.213 I slot release: id 1 | task 16065 | stop processing: n_tokens = 655, truncated = 0 16.28.573.311 I slot print_timing: id 2 | task 16067 | prompt eval time = 969.41 ms / 84 tokens ( 11.54 ms per token, 86.65 tokens per second) 16.28.573.313 I slot print_timing: id 2 | task 16067 | eval time = 42.27 ms / 2 tokens ( 42.27 ms per token, 23.66 tokens per second) 16.28.573.313 I slot print_timing: id 2 | task 16067 | total time = 1011.68 ms / 86 tokens 16.28.573.314 I slot print_timing: id 2 | task 16067 | graphs reused = 14553 16.28.573.314 I slot print_timing: id 2 | task 16067 | graph reallocs = 0 / 0 (same size) / (changed size) 16.28.573.331 I slot release: id 2 | task 16067 | stop processing: n_tokens = 646, truncated = 0 16.28.573.420 I slot print_timing: id 3 | task 16066 | prompt eval time = 968.25 ms / 75 tokens ( 12.91 ms per token, 77.46 tokens per second) 16.28.573.423 I slot print_timing: id 3 | task 16066 | eval time = 42.27 ms / 2 tokens ( 42.27 ms per token, 23.66 tokens per second) 16.28.573.423 I slot print_timing: id 3 | task 16066 | total time = 1010.51 ms / 77 tokens 16.28.573.423 I slot print_timing: id 3 | task 16066 | graphs reused = 14553 16.28.573.424 I slot print_timing: id 3 | task 16066 | graph reallocs = 0 / 0 (same size) / (changed size) 16.28.573.444 I slot release: id 3 | task 16066 | stop processing: n_tokens = 639, truncated = 0 16.28.582.938 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 632, t_last = 353771467283 16.28.583.014 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 201.465 MiB) 16.28.588.084 I slot launch_slot_: id 0 | task 16071 | processing task, is_child = 0 16.28.588.145 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 141.140 MiB) 16.28.592.510 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 138.938 MiB) 16.28.597.025 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 174.328 MiB) 16.28.601.421 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 655, t_last = 353771467393 16.28.601.554 I slot launch_slot_: id 1 | task 16072 | processing task, is_child = 0 16.28.601.676 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 646, t_last = 353771467511 16.28.601.795 I slot launch_slot_: id 2 | task 16073 | processing task, is_child = 0 16.28.601.853 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 639, t_last = 353771467624 16.28.601.953 I slot launch_slot_: id 3 | task 16074 | processing task, is_child = 0 16.34.043.282 I slot print_timing: id 0 | task 16071 | prompt processing, n_tokens = 706, progress = 0.83, t = 5.44 s / 129.75 tokens per second 16.34.163.997 I slot print_timing: id 1 | task 16072 | prompt processing, n_tokens = 706, progress = 0.85, t = 5.44 s / 129.75 tokens per second 16.34.166.493 I slot print_timing: id 2 | task 16073 | prompt processing, n_tokens = 706, progress = 0.82, t = 5.44 s / 129.75 tokens per second 16.34.169.055 I slot print_timing: id 3 | task 16074 | prompt processing, n_tokens = 706, progress = 0.77, t = 5.44 s / 129.75 tokens per second 16.35.436.139 I slot print_timing: id 0 | task 16071 | prompt processing, n_tokens = 845, progress = 1.00, t = 6.83 s / 123.64 tokens per second 16.35.704.802 I slot print_timing: id 1 | task 16072 | prompt processing, n_tokens = 823, progress = 1.00, t = 6.83 s / 120.43 tokens per second 16.35.707.139 I slot print_timing: id 2 | task 16073 | prompt processing, n_tokens = 852, progress = 1.00, t = 6.83 s / 124.67 tokens per second 16.35.708.486 I slot print_timing: id 3 | task 16074 | prompt processing, n_tokens = 908, progress = 1.00, t = 6.83 s / 132.87 tokens per second 16.35.850.525 I slot print_timing: id 0 | task 16071 | prompt eval time = 7206.09 ms / 849 tokens ( 8.49 ms per token, 117.82 tokens per second) 16.35.850.527 I slot print_timing: id 0 | task 16071 | eval time = 42.48 ms / 2 tokens ( 42.48 ms per token, 23.54 tokens per second) 16.35.850.527 I slot print_timing: id 0 | task 16071 | total time = 7248.56 ms / 851 tokens 16.35.850.528 I slot print_timing: id 0 | task 16071 | graphs reused = 14554 16.35.850.528 I slot print_timing: id 0 | task 16071 | graph reallocs = 0 / 0 (same size) / (changed size) 16.35.850.570 I slot release: id 0 | task 16071 | stop processing: n_tokens = 850, truncated = 0 16.35.850.658 I slot print_timing: id 1 | task 16072 | prompt eval time = 7206.10 ms / 827 tokens ( 8.71 ms per token, 114.76 tokens per second) 16.35.850.664 I slot print_timing: id 1 | task 16072 | eval time = 42.51 ms / 2 tokens ( 42.51 ms per token, 23.52 tokens per second) 16.35.850.664 I slot print_timing: id 1 | task 16072 | total time = 7248.61 ms / 829 tokens 16.35.850.665 I slot print_timing: id 1 | task 16072 | graphs reused = 14554 16.35.850.665 I slot print_timing: id 1 | task 16072 | graph reallocs = 0 / 0 (same size) / (changed size) 16.35.850.692 I slot release: id 1 | task 16072 | stop processing: n_tokens = 828, truncated = 0 16.35.850.774 I slot print_timing: id 2 | task 16073 | prompt eval time = 7206.12 ms / 856 tokens ( 8.42 ms per token, 118.79 tokens per second) 16.35.850.776 I slot print_timing: id 2 | task 16073 | eval time = 42.51 ms / 2 tokens ( 42.51 ms per token, 23.52 tokens per second) 16.35.850.776 I slot print_timing: id 2 | task 16073 | total time = 7248.63 ms / 858 tokens 16.35.850.777 I slot print_timing: id 2 | task 16073 | graphs reused = 14554 16.35.850.777 I slot print_timing: id 2 | task 16073 | graph reallocs = 0 / 0 (same size) / (changed size) 16.35.850.801 I slot release: id 2 | task 16073 | stop processing: n_tokens = 857, truncated = 0 16.35.850.897 I slot print_timing: id 3 | task 16074 | prompt eval time = 7206.15 ms / 912 tokens ( 7.90 ms per token, 126.56 tokens per second) 16.35.850.899 I slot print_timing: id 3 | task 16074 | eval time = 42.51 ms / 2 tokens ( 42.51 ms per token, 23.52 tokens per second) 16.35.850.901 I slot print_timing: id 3 | task 16074 | total time = 7248.66 ms / 914 tokens 16.35.850.901 I slot print_timing: id 3 | task 16074 | graphs reused = 14554 16.35.850.901 I slot print_timing: id 3 | task 16074 | graph reallocs = 0 / 0 (same size) / (changed size) 16.35.850.928 I slot release: id 3 | task 16074 | stop processing: n_tokens = 913, truncated = 0 16.35.862.584 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 850, t_last = 353778744750 16.35.862.669 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 142.193 MiB) 16.35.866.702 I slot launch_slot_: id 0 | task 16082 | processing task, is_child = 0 16.35.866.770 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 144.108 MiB) 16.35.870.884 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 146.446 MiB) 16.35.875.050 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 146.829 MiB) 16.35.883.093 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 828, t_last = 353778744872 16.35.883.229 I slot launch_slot_: id 1 | task 16083 | processing task, is_child = 0 16.35.883.357 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 857, t_last = 353778744981 16.35.883.461 I slot launch_slot_: id 2 | task 16084 | processing task, is_child = 0 16.35.883.528 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 913, t_last = 353778745108 16.35.883.639 I slot launch_slot_: id 3 | task 16085 | processing task, is_child = 0 16.42.824.011 I slot print_timing: id 0 | task 16082 | prompt processing, n_tokens = 454, progress = 0.47, t = 6.94 s / 65.41 tokens per second 16.42.897.915 I slot print_timing: id 1 | task 16083 | prompt processing, n_tokens = 463, progress = 0.47, t = 6.94 s / 66.71 tokens per second 16.42.899.934 I slot print_timing: id 2 | task 16084 | prompt processing, n_tokens = 1419, progress = 0.73, t = 6.94 s / 204.46 tokens per second 16.42.901.931 I slot print_timing: id 3 | task 16085 | prompt processing, n_tokens = 1431, progress = 0.73, t = 6.94 s / 206.20 tokens per second 16.45.293.920 I slot print_timing: id 0 | task 16082 | prompt processing, n_tokens = 832, progress = 0.86, t = 9.41 s / 88.41 tokens per second 16.45.354.890 I slot print_timing: id 1 | task 16083 | prompt processing, n_tokens = 832, progress = 0.85, t = 9.41 s / 88.42 tokens per second 16.45.357.506 I slot print_timing: id 2 | task 16084 | prompt processing, n_tokens = 1634, progress = 0.84, t = 9.41 s / 173.64 tokens per second 16.45.360.032 I slot print_timing: id 3 | task 16085 | prompt processing, n_tokens = 1634, progress = 0.84, t = 9.41 s / 173.65 tokens per second 16.47.265.021 I slot print_timing: id 0 | task 16082 | prompt processing, n_tokens = 966, progress = 1.00, t = 11.38 s / 84.88 tokens per second 16.47.339.914 I slot print_timing: id 1 | task 16083 | prompt processing, n_tokens = 975, progress = 1.00, t = 11.38 s / 85.67 tokens per second 16.47.342.413 I slot print_timing: id 2 | task 16084 | prompt processing, n_tokens = 1931, progress = 1.00, t = 11.38 s / 169.67 tokens per second 16.47.344.703 I slot print_timing: id 3 | task 16085 | prompt processing, n_tokens = 1943, progress = 1.00, t = 11.38 s / 170.72 tokens per second 16.47.489.440 I slot print_timing: id 0 | task 16082 | prompt eval time = 11562.74 ms / 970 tokens ( 11.92 ms per token, 83.89 tokens per second) 16.47.489.441 I slot print_timing: id 0 | task 16082 | eval time = 43.05 ms / 2 tokens ( 43.05 ms per token, 23.23 tokens per second) 16.47.489.442 I slot print_timing: id 0 | task 16082 | total time = 11605.79 ms / 972 tokens 16.47.489.442 I slot print_timing: id 0 | task 16082 | graphs reused = 14554 16.47.489.443 I slot print_timing: id 0 | task 16082 | graph reallocs = 0 / 0 (same size) / (changed size) 16.47.489.490 I slot release: id 0 | task 16082 | stop processing: n_tokens = 971, truncated = 0 16.47.489.579 I slot print_timing: id 1 | task 16083 | prompt eval time = 11562.73 ms / 979 tokens ( 11.81 ms per token, 84.67 tokens per second) 16.47.489.581 I slot print_timing: id 1 | task 16083 | eval time = 43.07 ms / 2 tokens ( 43.07 ms per token, 23.22 tokens per second) 16.47.489.582 I slot print_timing: id 1 | task 16083 | total time = 11605.80 ms / 981 tokens 16.47.489.582 I slot print_timing: id 1 | task 16083 | graphs reused = 14554 16.47.489.582 I slot print_timing: id 1 | task 16083 | graph reallocs = 0 / 0 (same size) / (changed size) 16.47.489.616 I slot release: id 1 | task 16083 | stop processing: n_tokens = 980, truncated = 0 16.47.489.708 I slot print_timing: id 2 | task 16084 | prompt eval time = 11562.75 ms / 1935 tokens ( 5.98 ms per token, 167.35 tokens per second) 16.47.489.710 I slot print_timing: id 2 | task 16084 | eval time = 43.07 ms / 2 tokens ( 43.07 ms per token, 23.22 tokens per second) 16.47.489.710 I slot print_timing: id 2 | task 16084 | total time = 11605.82 ms / 1937 tokens 16.47.489.710 I slot print_timing: id 2 | task 16084 | graphs reused = 14554 16.47.489.711 I slot print_timing: id 2 | task 16084 | graph reallocs = 0 / 0 (same size) / (changed size) 16.47.489.781 I slot release: id 2 | task 16084 | stop processing: n_tokens = 1936, truncated = 0 16.47.489.878 I slot print_timing: id 3 | task 16085 | prompt eval time = 11562.75 ms / 1947 tokens ( 5.94 ms per token, 168.39 tokens per second) 16.47.489.879 I slot print_timing: id 3 | task 16085 | eval time = 43.12 ms / 2 tokens ( 43.12 ms per token, 23.19 tokens per second) 16.47.489.880 I slot print_timing: id 3 | task 16085 | total time = 11605.87 ms / 1949 tokens 16.47.489.880 I slot print_timing: id 3 | task 16085 | graphs reused = 14554 16.47.489.880 I slot print_timing: id 3 | task 16085 | graph reallocs = 0 / 0 (same size) / (changed size) 16.47.489.924 I slot release: id 3 | task 16085 | stop processing: n_tokens = 1948, truncated = 0 16.47.503.066 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 16.47.503.119 I slot launch_slot_: id 2 | task 16093 | processing task, is_child = 0 16.47.503.195 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 171.704 MiB) 16.47.507.798 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 185.720 MiB) 16.47.512.810 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 149.632 MiB) 16.47.512.817 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 155.185 MiB) 16.47.518.505 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.868 (> 0.100 thold), f_keep = 0.852 16.47.518.577 I slot launch_slot_: id 3 | task 16094 | processing task, is_child = 0 16.47.518.716 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 971, t_last = 353790383670 16.47.521.155 I slot launch_slot_: id 0 | task 16095 | processing task, is_child = 0 16.47.521.237 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 980, t_last = 353790383796 16.47.521.342 I slot launch_slot_: id 1 | task 16096 | processing task, is_child = 0 16.50.796.640 I slot print_timing: id 0 | task 16095 | prompt processing, n_tokens = 322, progress = 1.00, t = 3.27 s / 98.32 tokens per second 16.50.799.034 I slot print_timing: id 1 | task 16096 | prompt processing, n_tokens = 598, progress = 0.30, t = 3.27 s / 182.71 tokens per second 16.52.523.510 I slot print_timing: id 2 | task 16093 | prompt eval time = 3272.88 ms / 231 tokens ( 14.17 ms per token, 70.58 tokens per second) 16.52.523.526 I slot print_timing: id 2 | task 16093 | eval time = 1726.99 ms / 2 tokens ( 1726.99 ms per token, 0.58 tokens per second) 16.52.523.528 I slot print_timing: id 2 | task 16093 | total time = 4999.87 ms / 233 tokens 16.52.523.531 I slot print_timing: id 2 | task 16093 | graphs reused = 14554 16.52.523.533 I slot print_timing: id 2 | task 16093 | graph reallocs = 0 / 0 (same size) / (changed size) 16.52.523.934 I slot release: id 2 | task 16093 | stop processing: n_tokens = 1892, truncated = 0 16.52.524.489 I slot print_timing: id 3 | task 16094 | prompt eval time = 3271.63 ms / 253 tokens ( 12.93 ms per token, 77.33 tokens per second) 16.52.524.494 I slot print_timing: id 3 | task 16094 | eval time = 1727.85 ms / 2 tokens ( 1727.85 ms per token, 0.58 tokens per second) 16.52.524.494 I slot print_timing: id 3 | task 16094 | total time = 4999.48 ms / 255 tokens 16.52.524.496 I slot print_timing: id 3 | task 16094 | graphs reused = 14554 16.52.524.497 I slot print_timing: id 3 | task 16094 | graph reallocs = 0 / 0 (same size) / (changed size) 16.52.524.688 I slot release: id 3 | task 16094 | stop processing: n_tokens = 1914, truncated = 0 16.52.524.745 I slot print_timing: id 1 | task 16096 | prompt processing, n_tokens = 1469, progress = 0.74, t = 5.00 s / 293.90 tokens per second 16.53.052.980 I slot print_timing: id 0 | task 16095 | prompt eval time = 5001.37 ms / 326 tokens ( 15.34 ms per token, 65.18 tokens per second) 16.53.053.002 I slot print_timing: id 0 | task 16095 | eval time = 530.24 ms / 2 tokens ( 530.24 ms per token, 1.89 tokens per second) 16.53.053.005 I slot print_timing: id 0 | task 16095 | total time = 5531.61 ms / 328 tokens 16.53.053.007 I slot print_timing: id 0 | task 16095 | graphs reused = 14554 16.53.053.013 I slot print_timing: id 0 | task 16095 | graph reallocs = 0 / 0 (same size) / (changed size) 16.53.053.373 I slot release: id 0 | task 16095 | stop processing: n_tokens = 1960, truncated = 0 16.53.053.450 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.866 (> 0.100 thold), f_keep = 0.846 16.53.053.991 I slot launch_slot_: id 0 | task 16101 | processing task, is_child = 0 16.53.075.846 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 155.759 MiB) 16.53.075.858 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 145.256 MiB) 16.53.088.826 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.832 (> 0.100 thold), f_keep = 0.877 16.53.088.965 I slot launch_slot_: id 2 | task 16102 | processing task, is_child = 0 16.53.089.136 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.801 (> 0.100 thold), f_keep = 0.867 16.53.089.200 I slot launch_slot_: id 3 | task 16103 | processing task, is_child = 0 16.53.090.818 I slot print_timing: id 1 | task 16096 | prompt processing, n_tokens = 1634, progress = 0.82, t = 5.53 s / 295.53 tokens per second 16.55.988.980 I slot print_timing: id 1 | task 16096 | prompt processing, n_tokens = 1981, progress = 1.00, t = 8.13 s / 243.69 tokens per second 16.56.145.957 I slot print_timing: id 0 | task 16101 | prompt eval time = 3012.85 ms / 257 tokens ( 11.72 ms per token, 85.30 tokens per second) 16.56.145.962 I slot print_timing: id 0 | task 16101 | eval time = 43.89 ms / 2 tokens ( 43.89 ms per token, 22.78 tokens per second) 16.56.145.963 I slot print_timing: id 0 | task 16101 | total time = 3056.75 ms / 259 tokens 16.56.145.963 I slot print_timing: id 0 | task 16101 | graphs reused = 14554 16.56.145.964 I slot print_timing: id 0 | task 16101 | graph reallocs = 0 / 0 (same size) / (changed size) 16.56.146.038 I slot release: id 0 | task 16101 | stop processing: n_tokens = 1917, truncated = 0 16.56.146.143 I slot print_timing: id 1 | task 16096 | prompt eval time = 8578.70 ms / 1985 tokens ( 4.32 ms per token, 231.39 tokens per second) 16.56.146.145 I slot print_timing: id 1 | task 16096 | eval time = 43.98 ms / 2 tokens ( 43.98 ms per token, 22.74 tokens per second) 16.56.146.146 I slot print_timing: id 1 | task 16096 | total time = 8622.69 ms / 1987 tokens 16.56.146.146 I slot print_timing: id 1 | task 16096 | graphs reused = 14554 16.56.146.146 I slot print_timing: id 1 | task 16096 | graph reallocs = 0 / 0 (same size) / (changed size) 16.56.146.202 I slot release: id 1 | task 16096 | stop processing: n_tokens = 1986, truncated = 0 16.56.146.295 I slot print_timing: id 2 | task 16102 | prompt eval time = 3010.06 ms / 336 tokens ( 8.96 ms per token, 111.63 tokens per second) 16.56.146.297 I slot print_timing: id 2 | task 16102 | eval time = 44.03 ms / 2 tokens ( 44.03 ms per token, 22.71 tokens per second) 16.56.146.298 I slot print_timing: id 2 | task 16102 | total time = 3054.09 ms / 338 tokens 16.56.146.298 I slot print_timing: id 2 | task 16102 | graphs reused = 14554 16.56.146.298 I slot print_timing: id 2 | task 16102 | graph reallocs = 0 / 0 (same size) / (changed size) 16.56.146.349 I slot release: id 2 | task 16102 | stop processing: n_tokens = 1997, truncated = 0 16.56.146.441 I slot print_timing: id 3 | task 16103 | prompt eval time = 3008.35 ms / 412 tokens ( 7.30 ms per token, 136.95 tokens per second) 16.56.146.443 I slot print_timing: id 3 | task 16103 | eval time = 44.05 ms / 2 tokens ( 44.05 ms per token, 22.70 tokens per second) 16.56.146.444 I slot print_timing: id 3 | task 16103 | total time = 3052.40 ms / 414 tokens 16.56.146.444 I slot print_timing: id 3 | task 16103 | graphs reused = 14554 16.56.146.444 I slot print_timing: id 3 | task 16103 | graph reallocs = 0 / 0 (same size) / (changed size) 16.56.146.489 I slot release: id 3 | task 16103 | stop processing: n_tokens = 2073, truncated = 0 16.56.159.713 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.864 (> 0.100 thold), f_keep = 0.836 16.56.159.760 I slot launch_slot_: id 1 | task 16107 | processing task, is_child = 0 16.56.159.872 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 134.590 MiB) 16.56.159.877 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 140.429 MiB) 16.56.169.081 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 147.650 MiB) 16.56.180.860 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 138.515 MiB) 16.56.180.865 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 135.739 MiB) 16.56.193.159 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.831 16.56.193.224 I slot launch_slot_: id 2 | task 16108 | processing task, is_child = 0 16.56.193.438 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.892 (> 0.100 thold), f_keep = 0.801 16.56.193.484 I slot launch_slot_: id 3 | task 16109 | processing task, is_child = 0 16.56.193.583 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.890 (> 0.100 thold), f_keep = 0.865 16.56.193.622 I slot launch_slot_: id 0 | task 16110 | processing task, is_child = 0 16.58.532.869 I slot print_timing: id 0 | task 16110 | prompt eval time = 2295.75 ms / 206 tokens ( 11.14 ms per token, 89.73 tokens per second) 16.58.532.874 I slot print_timing: id 0 | task 16110 | eval time = 43.49 ms / 2 tokens ( 43.49 ms per token, 22.99 tokens per second) 16.58.532.874 I slot print_timing: id 0 | task 16110 | total time = 2339.24 ms / 208 tokens 16.58.532.875 I slot print_timing: id 0 | task 16110 | graphs reused = 14554 16.58.532.875 I slot print_timing: id 0 | task 16110 | graph reallocs = 0 / 0 (same size) / (changed size) 16.58.532.951 I slot release: id 0 | task 16110 | stop processing: n_tokens = 1866, truncated = 0 16.58.533.043 I slot print_timing: id 1 | task 16107 | prompt eval time = 2294.71 ms / 261 tokens ( 8.79 ms per token, 113.74 tokens per second) 16.58.533.045 I slot print_timing: id 1 | task 16107 | eval time = 43.51 ms / 2 tokens ( 43.51 ms per token, 22.98 tokens per second) 16.58.533.047 I slot print_timing: id 1 | task 16107 | total time = 2338.22 ms / 263 tokens 16.58.533.047 I slot print_timing: id 1 | task 16107 | graphs reused = 14554 16.58.533.047 I slot print_timing: id 1 | task 16107 | graph reallocs = 0 / 0 (same size) / (changed size) 16.58.533.094 I slot release: id 1 | task 16107 | stop processing: n_tokens = 1922, truncated = 0 16.58.533.185 I slot print_timing: id 2 | task 16108 | prompt eval time = 2293.48 ms / 169 tokens ( 13.57 ms per token, 73.69 tokens per second) 16.58.533.187 I slot print_timing: id 2 | task 16108 | eval time = 43.53 ms / 2 tokens ( 43.53 ms per token, 22.97 tokens per second) 16.58.533.187 I slot print_timing: id 2 | task 16108 | total time = 2337.02 ms / 171 tokens 16.58.533.188 I slot print_timing: id 2 | task 16108 | graphs reused = 14554 16.58.533.188 I slot print_timing: id 2 | task 16108 | graph reallocs = 0 / 0 (same size) / (changed size) 16.58.533.231 I slot release: id 2 | task 16108 | stop processing: n_tokens = 1830, truncated = 0 16.58.533.318 I slot print_timing: id 3 | task 16109 | prompt eval time = 2292.31 ms / 201 tokens ( 11.40 ms per token, 87.68 tokens per second) 16.58.533.319 I slot print_timing: id 3 | task 16109 | eval time = 43.54 ms / 2 tokens ( 43.54 ms per token, 22.97 tokens per second) 16.58.533.320 I slot print_timing: id 3 | task 16109 | total time = 2335.85 ms / 203 tokens 16.58.533.320 I slot print_timing: id 3 | task 16109 | graphs reused = 14554 16.58.533.320 I slot print_timing: id 3 | task 16109 | graph reallocs = 0 / 0 (same size) / (changed size) 16.58.533.361 I slot release: id 3 | task 16109 | stop processing: n_tokens = 1862, truncated = 0 16.58.547.728 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.889 16.58.547.829 I slot launch_slot_: id 0 | task 16114 | processing task, is_child = 0 16.58.547.978 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 135.930 MiB) 16.58.547.983 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 170.677 MiB) 16.58.555.077 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 205.930 MiB) 16.58.562.959 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 207.612 MiB) 16.58.562.966 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 171.880 MiB) 16.58.575.317 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.864 (> 0.100 thold), f_keep = 0.863 16.58.575.389 I slot launch_slot_: id 1 | task 16115 | processing task, is_child = 0 16.58.575.598 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.849 (> 0.100 thold), f_keep = 0.907 16.58.575.655 I slot launch_slot_: id 2 | task 16116 | processing task, is_child = 0 16.58.575.761 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.843 (> 0.100 thold), f_keep = 0.892 16.58.575.800 I slot launch_slot_: id 3 | task 16117 | processing task, is_child = 0 17.01.141.563 I slot print_timing: id 0 | task 16114 | prompt eval time = 2522.19 ms / 169 tokens ( 14.92 ms per token, 67.01 tokens per second) 17.01.141.565 I slot print_timing: id 0 | task 16114 | eval time = 43.56 ms / 2 tokens ( 43.56 ms per token, 22.96 tokens per second) 17.01.141.566 I slot print_timing: id 0 | task 16114 | total time = 2565.75 ms / 171 tokens 17.01.141.566 I slot print_timing: id 0 | task 16114 | graphs reused = 14554 17.01.141.566 I slot print_timing: id 0 | task 16114 | graph reallocs = 0 / 0 (same size) / (changed size) 17.01.141.646 I slot release: id 0 | task 16114 | stop processing: n_tokens = 1829, truncated = 0 17.01.141.736 I slot print_timing: id 1 | task 16115 | prompt eval time = 2521.03 ms / 262 tokens ( 9.62 ms per token, 103.93 tokens per second) 17.01.141.738 I slot print_timing: id 1 | task 16115 | eval time = 43.60 ms / 2 tokens ( 43.60 ms per token, 22.94 tokens per second) 17.01.141.739 I slot print_timing: id 1 | task 16115 | total time = 2564.63 ms / 264 tokens 17.01.141.739 I slot print_timing: id 1 | task 16115 | graphs reused = 14554 17.01.141.740 I slot print_timing: id 1 | task 16115 | graph reallocs = 0 / 0 (same size) / (changed size) 17.01.141.791 I slot release: id 1 | task 16115 | stop processing: n_tokens = 1922, truncated = 0 17.01.141.881 I slot print_timing: id 2 | task 16116 | prompt eval time = 2519.80 ms / 295 tokens ( 8.54 ms per token, 117.07 tokens per second) 17.01.141.884 I slot print_timing: id 2 | task 16116 | eval time = 43.62 ms / 2 tokens ( 43.62 ms per token, 22.93 tokens per second) 17.01.141.884 I slot print_timing: id 2 | task 16116 | total time = 2563.42 ms / 297 tokens 17.01.141.884 I slot print_timing: id 2 | task 16116 | graphs reused = 14554 17.01.141.885 I slot print_timing: id 2 | task 16116 | graph reallocs = 0 / 0 (same size) / (changed size) 17.01.141.933 I slot release: id 2 | task 16116 | stop processing: n_tokens = 1956, truncated = 0 17.01.142.031 I slot print_timing: id 3 | task 16117 | prompt eval time = 2518.60 ms / 308 tokens ( 8.18 ms per token, 122.29 tokens per second) 17.01.142.033 I slot print_timing: id 3 | task 16117 | eval time = 43.64 ms / 2 tokens ( 43.64 ms per token, 22.91 tokens per second) 17.01.142.033 I slot print_timing: id 3 | task 16117 | total time = 2562.24 ms / 310 tokens 17.01.142.033 I slot print_timing: id 3 | task 16117 | graphs reused = 14554 17.01.142.034 I slot print_timing: id 3 | task 16117 | graph reallocs = 0 / 0 (same size) / (changed size) 17.01.142.075 I slot release: id 3 | task 16117 | stop processing: n_tokens = 1969, truncated = 0 17.01.155.792 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.849 17.01.155.865 I slot launch_slot_: id 2 | task 16121 | processing task, is_child = 0 17.01.155.978 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 170.704 MiB) 17.01.168.334 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 157.249 MiB) 17.01.168.339 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 156.196 MiB) 17.01.180.328 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 211.428 MiB) 17.01.187.195 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.876 (> 0.100 thold), f_keep = 0.907 17.01.187.286 I slot launch_slot_: id 0 | task 16122 | processing task, is_child = 0 17.01.187.506 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.823 (> 0.100 thold), f_keep = 0.863 17.01.187.549 I slot launch_slot_: id 1 | task 16123 | processing task, is_child = 0 17.01.187.657 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.820 (> 0.100 thold), f_keep = 0.843 17.01.187.702 I slot launch_slot_: id 3 | task 16124 | processing task, is_child = 0 17.04.129.122 I slot print_timing: id 0 | task 16122 | prompt eval time = 2898.12 ms / 234 tokens ( 12.39 ms per token, 80.74 tokens per second) 17.04.129.124 I slot print_timing: id 0 | task 16122 | eval time = 43.28 ms / 2 tokens ( 43.28 ms per token, 23.10 tokens per second) 17.04.129.126 I slot print_timing: id 0 | task 16122 | total time = 2941.40 ms / 236 tokens 17.04.129.126 I slot print_timing: id 0 | task 16122 | graphs reused = 14554 17.04.129.126 I slot print_timing: id 0 | task 16122 | graph reallocs = 0 / 0 (same size) / (changed size) 17.04.129.206 I slot release: id 0 | task 16122 | stop processing: n_tokens = 1894, truncated = 0 17.04.129.304 I slot print_timing: id 1 | task 16123 | prompt eval time = 2897.02 ms / 358 tokens ( 8.09 ms per token, 123.58 tokens per second) 17.04.129.306 I slot print_timing: id 1 | task 16123 | eval time = 43.37 ms / 2 tokens ( 43.37 ms per token, 23.06 tokens per second) 17.04.129.307 I slot print_timing: id 1 | task 16123 | total time = 2940.39 ms / 360 tokens 17.04.129.307 I slot print_timing: id 1 | task 16123 | graphs reused = 14554 17.04.129.307 I slot print_timing: id 1 | task 16123 | graph reallocs = 0 / 0 (same size) / (changed size) 17.04.129.357 I slot release: id 1 | task 16123 | stop processing: n_tokens = 2018, truncated = 0 17.04.129.444 I slot print_timing: id 2 | task 16121 | prompt eval time = 2895.73 ms / 168 tokens ( 17.24 ms per token, 58.02 tokens per second) 17.04.129.446 I slot print_timing: id 2 | task 16121 | eval time = 43.41 ms / 2 tokens ( 43.41 ms per token, 23.04 tokens per second) 17.04.129.446 I slot print_timing: id 2 | task 16121 | total time = 2939.14 ms / 170 tokens 17.04.129.446 I slot print_timing: id 2 | task 16121 | graphs reused = 14554 17.04.129.447 I slot print_timing: id 2 | task 16121 | graph reallocs = 0 / 0 (same size) / (changed size) 17.04.129.485 I slot release: id 2 | task 16121 | stop processing: n_tokens = 1829, truncated = 0 17.04.129.570 I slot print_timing: id 3 | task 16124 | prompt eval time = 2894.19 ms / 365 tokens ( 7.93 ms per token, 126.11 tokens per second) 17.04.129.572 I slot print_timing: id 3 | task 16124 | eval time = 43.44 ms / 2 tokens ( 43.44 ms per token, 23.02 tokens per second) 17.04.129.572 I slot print_timing: id 3 | task 16124 | total time = 2937.63 ms / 367 tokens 17.04.129.573 I slot print_timing: id 3 | task 16124 | graphs reused = 14554 17.04.129.573 I slot print_timing: id 3 | task 16124 | graph reallocs = 0 / 0 (same size) / (changed size) 17.04.129.621 I slot release: id 3 | task 16124 | stop processing: n_tokens = 2026, truncated = 0 17.04.143.121 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.895 (> 0.100 thold), f_keep = 0.876 17.04.143.164 I slot launch_slot_: id 0 | task 16128 | processing task, is_child = 0 17.04.143.294 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 210.895 MiB) 17.04.149.862 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 210.991 MiB) 17.04.149.870 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 211.483 MiB) 17.04.156.962 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 246.216 MiB) 17.04.168.806 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.822 17.04.168.875 I slot launch_slot_: id 1 | task 16129 | processing task, is_child = 0 17.04.169.091 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.908 17.04.169.130 I slot launch_slot_: id 2 | task 16130 | processing task, is_child = 0 17.04.169.239 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.819 17.04.169.278 I slot launch_slot_: id 3 | task 16131 | processing task, is_child = 0 17.06.116.305 I slot print_timing: id 0 | task 16128 | prompt eval time = 1903.64 ms / 194 tokens ( 9.81 ms per token, 101.91 tokens per second) 17.06.116.307 I slot print_timing: id 0 | task 16128 | eval time = 43.37 ms / 2 tokens ( 43.37 ms per token, 23.06 tokens per second) 17.06.116.308 I slot print_timing: id 0 | task 16128 | total time = 1947.02 ms / 196 tokens 17.06.116.308 I slot print_timing: id 0 | task 16128 | graphs reused = 14554 17.06.116.309 I slot print_timing: id 0 | task 16128 | graph reallocs = 0 / 0 (same size) / (changed size) 17.06.116.389 I slot release: id 0 | task 16128 | stop processing: n_tokens = 1854, truncated = 0 17.06.116.476 I slot print_timing: id 1 | task 16129 | prompt eval time = 1902.46 ms / 108 tokens ( 17.62 ms per token, 56.77 tokens per second) 17.06.116.478 I slot print_timing: id 1 | task 16129 | eval time = 43.42 ms / 2 tokens ( 43.42 ms per token, 23.03 tokens per second) 17.06.116.478 I slot print_timing: id 1 | task 16129 | total time = 1945.89 ms / 110 tokens 17.06.116.479 I slot print_timing: id 1 | task 16129 | graphs reused = 14554 17.06.116.479 I slot print_timing: id 1 | task 16129 | graph reallocs = 0 / 0 (same size) / (changed size) 17.06.116.531 I slot release: id 1 | task 16129 | stop processing: n_tokens = 1768, truncated = 0 17.06.116.620 I slot print_timing: id 2 | task 16130 | prompt eval time = 1901.34 ms / 191 tokens ( 9.95 ms per token, 100.46 tokens per second) 17.06.116.622 I slot print_timing: id 2 | task 16130 | eval time = 43.43 ms / 2 tokens ( 43.43 ms per token, 23.02 tokens per second) 17.06.116.622 I slot print_timing: id 2 | task 16130 | total time = 1944.77 ms / 193 tokens 17.06.116.622 I slot print_timing: id 2 | task 16130 | graphs reused = 14554 17.06.116.623 I slot print_timing: id 2 | task 16130 | graph reallocs = 0 / 0 (same size) / (changed size) 17.06.116.670 I slot release: id 2 | task 16130 | stop processing: n_tokens = 1852, truncated = 0 17.06.116.770 I slot print_timing: id 3 | task 16131 | prompt eval time = 1900.05 ms / 217 tokens ( 8.76 ms per token, 114.21 tokens per second) 17.06.116.773 I slot print_timing: id 3 | task 16131 | eval time = 43.46 ms / 2 tokens ( 43.46 ms per token, 23.01 tokens per second) 17.06.116.774 I slot print_timing: id 3 | task 16131 | total time = 1943.51 ms / 219 tokens 17.06.116.774 I slot print_timing: id 3 | task 16131 | graphs reused = 14554 17.06.116.774 I slot print_timing: id 3 | task 16131 | graph reallocs = 0 / 0 (same size) / (changed size) 17.06.116.817 I slot release: id 3 | task 16131 | stop processing: n_tokens = 1878, truncated = 0 17.06.129.040 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1854, t_last = 353809010569 17.06.129.154 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 246.175 MiB) 17.06.136.515 I slot launch_slot_: id 0 | task 16135 | processing task, is_child = 0 17.06.136.631 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 211.565 MiB) 17.06.143.025 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 245.916 MiB) 17.06.149.809 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 246.093 MiB) 17.06.156.118 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1768, t_last = 353809010711 17.06.156.305 I slot launch_slot_: id 1 | task 16136 | processing task, is_child = 0 17.06.156.518 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1852, t_last = 353809010850 17.06.156.672 I slot launch_slot_: id 2 | task 16137 | processing task, is_child = 0 17.06.156.779 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.916 (> 0.100 thold), f_keep = 0.883 17.06.156.816 I slot launch_slot_: id 3 | task 16138 | processing task, is_child = 0 17.09.294.819 I slot print_timing: id 0 | task 16135 | prompt processing, n_tokens = 515, progress = 0.39, t = 3.14 s / 164.12 tokens per second 17.09.294.837 I slot print_timing: id 1 | task 16136 | prompt processing, n_tokens = 515, progress = 0.37, t = 3.14 s / 164.13 tokens per second 17.09.294.848 I slot print_timing: id 2 | task 16137 | prompt processing, n_tokens = 515, progress = 0.34, t = 3.14 s / 164.16 tokens per second 17.11.594.964 I slot print_timing: id 3 | task 16138 | prompt eval time = 3136.66 ms / 152 tokens ( 20.64 ms per token, 48.46 tokens per second) 17.11.594.970 I slot print_timing: id 3 | task 16138 | eval time = 2300.15 ms / 2 tokens ( 2300.15 ms per token, 0.43 tokens per second) 17.11.594.970 I slot print_timing: id 3 | task 16138 | total time = 5436.81 ms / 154 tokens 17.11.594.971 I slot print_timing: id 3 | task 16138 | graphs reused = 14554 17.11.594.971 I slot print_timing: id 3 | task 16138 | graph reallocs = 0 / 0 (same size) / (changed size) 17.11.595.048 I slot release: id 3 | task 16138 | stop processing: n_tokens = 1812, truncated = 0 17.11.595.060 I slot print_timing: id 0 | task 16135 | prompt processing, n_tokens = 798, progress = 0.61, t = 5.44 s / 146.74 tokens per second 17.11.596.928 I slot print_timing: id 1 | task 16136 | prompt processing, n_tokens = 866, progress = 0.63, t = 5.44 s / 159.25 tokens per second 17.11.599.496 I slot print_timing: id 2 | task 16137 | prompt processing, n_tokens = 989, progress = 0.66, t = 5.44 s / 181.89 tokens per second 17.13.000.892 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1812, t_last = 353814489228 17.13.001.048 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 211.169 MiB) 17.13.291.754 I slot launch_slot_: id 3 | task 16143 | processing task, is_child = 0 17.13.291.769 I slot print_timing: id 0 | task 16135 | prompt processing, n_tokens = 1135, progress = 0.86, t = 6.84 s / 165.84 tokens per second 17.13.293.129 I slot print_timing: id 1 | task 16136 | prompt processing, n_tokens = 1135, progress = 0.82, t = 6.84 s / 165.84 tokens per second 17.13.294.425 I slot print_timing: id 2 | task 16137 | prompt processing, n_tokens = 1135, progress = 0.75, t = 6.84 s / 165.85 tokens per second 17.15.244.527 I slot print_timing: id 0 | task 16135 | prompt processing, n_tokens = 1310, progress = 1.00, t = 9.09 s / 144.15 tokens per second 17.15.653.189 I slot print_timing: id 1 | task 16136 | prompt processing, n_tokens = 1378, progress = 1.00, t = 9.09 s / 151.64 tokens per second 17.15.655.756 I slot print_timing: id 2 | task 16137 | prompt processing, n_tokens = 1501, progress = 1.00, t = 9.09 s / 165.18 tokens per second 17.16.271.185 I slot print_timing: id 0 | task 16135 | prompt eval time = 10011.25 ms / 1314 tokens ( 7.62 ms per token, 131.25 tokens per second) 17.16.271.188 I slot print_timing: id 0 | task 16135 | eval time = 103.11 ms / 2 tokens ( 103.11 ms per token, 9.70 tokens per second) 17.16.271.188 I slot print_timing: id 0 | task 16135 | total time = 10114.36 ms / 1316 tokens 17.16.271.189 I slot print_timing: id 0 | task 16135 | graphs reused = 14554 17.16.271.189 I slot print_timing: id 0 | task 16135 | graph reallocs = 0 / 0 (same size) / (changed size) 17.16.271.251 I slot release: id 0 | task 16135 | stop processing: n_tokens = 1315, truncated = 0 17.16.271.339 I slot print_timing: id 1 | task 16136 | prompt eval time = 10011.16 ms / 1382 tokens ( 7.24 ms per token, 138.05 tokens per second) 17.16.271.342 I slot print_timing: id 1 | task 16136 | eval time = 103.17 ms / 2 tokens ( 103.17 ms per token, 9.69 tokens per second) 17.16.271.342 I slot print_timing: id 1 | task 16136 | total time = 10114.33 ms / 1384 tokens 17.16.271.343 I slot print_timing: id 1 | task 16136 | graphs reused = 14554 17.16.271.343 I slot print_timing: id 1 | task 16136 | graph reallocs = 0 / 0 (same size) / (changed size) 17.16.271.380 I slot release: id 1 | task 16136 | stop processing: n_tokens = 1383, truncated = 0 17.16.271.470 I slot print_timing: id 2 | task 16137 | prompt eval time = 10010.78 ms / 1505 tokens ( 6.65 ms per token, 150.34 tokens per second) 17.16.271.472 I slot print_timing: id 2 | task 16137 | eval time = 103.16 ms / 2 tokens ( 103.16 ms per token, 9.69 tokens per second) 17.16.271.473 I slot print_timing: id 2 | task 16137 | total time = 10113.94 ms / 1507 tokens 17.16.271.473 I slot print_timing: id 2 | task 16137 | graphs reused = 14554 17.16.271.473 I slot print_timing: id 2 | task 16137 | graph reallocs = 0 / 0 (same size) / (changed size) 17.16.271.522 I slot release: id 2 | task 16137 | stop processing: n_tokens = 1506, truncated = 0 17.17.007.873 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1315, t_last = 353819165432 17.17.007.969 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 175.492 MiB) 17.17.432.558 I slot launch_slot_: id 0 | task 16149 | processing task, is_child = 0 17.17.432.664 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 168.312 MiB) 17.17.439.494 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 169.461 MiB) 17.17.439.501 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 172.907 MiB) 17.17.445.203 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1383, t_last = 353819165560 17.17.445.359 I slot launch_slot_: id 1 | task 16150 | processing task, is_child = 0 17.17.445.448 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1506, t_last = 353819165703 17.17.445.584 I slot launch_slot_: id 2 | task 16151 | processing task, is_child = 0 17.17.446.558 I slot print_timing: id 3 | task 16143 | prompt processing, n_tokens = 899, progress = 1.00, t = 3.71 s / 242.17 tokens per second 17.19.611.944 I slot print_timing: id 3 | task 16143 | prompt eval time = 5469.00 ms / 903 tokens ( 6.06 ms per token, 165.11 tokens per second) 17.19.611.949 I slot print_timing: id 3 | task 16143 | eval time = 847.28 ms / 2 tokens ( 847.28 ms per token, 1.18 tokens per second) 17.19.611.950 I slot print_timing: id 3 | task 16143 | total time = 6316.28 ms / 905 tokens 17.19.611.950 I slot print_timing: id 3 | task 16143 | graphs reused = 14554 17.19.611.951 I slot print_timing: id 3 | task 16143 | graph reallocs = 0 / 0 (same size) / (changed size) 17.19.611.994 I slot release: id 3 | task 16143 | stop processing: n_tokens = 904, truncated = 0 17.21.846.252 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.893 (> 0.100 thold), f_keep = 0.875 17.21.846.362 I slot launch_slot_: id 3 | task 16155 | processing task, is_child = 0 17.21.846.371 I slot print_timing: id 0 | task 16149 | prompt processing, n_tokens = 766, progress = 0.89, t = 4.40 s / 174.07 tokens per second 17.21.956.693 I slot print_timing: id 1 | task 16150 | prompt processing, n_tokens = 766, progress = 0.87, t = 4.40 s / 174.07 tokens per second 17.21.958.413 I slot print_timing: id 2 | task 16151 | prompt processing, n_tokens = 766, progress = 0.86, t = 4.40 s / 174.08 tokens per second 17.22.980.780 I slot print_timing: id 0 | task 16149 | prompt processing, n_tokens = 860, progress = 1.00, t = 5.54 s / 155.37 tokens per second 17.23.045.811 I slot print_timing: id 1 | task 16150 | prompt processing, n_tokens = 877, progress = 1.00, t = 5.54 s / 158.45 tokens per second 17.23.048.607 I slot print_timing: id 2 | task 16151 | prompt processing, n_tokens = 887, progress = 1.00, t = 5.53 s / 160.26 tokens per second 17.23.192.469 I slot print_timing: id 0 | task 16149 | prompt eval time = 5704.23 ms / 864 tokens ( 6.60 ms per token, 151.47 tokens per second) 17.23.192.475 I slot print_timing: id 0 | task 16149 | eval time = 42.64 ms / 2 tokens ( 42.64 ms per token, 23.45 tokens per second) 17.23.192.475 I slot print_timing: id 0 | task 16149 | total time = 5746.87 ms / 866 tokens 17.23.192.476 I slot print_timing: id 0 | task 16149 | graphs reused = 14555 17.23.192.476 I slot print_timing: id 0 | task 16149 | graph reallocs = 0 / 0 (same size) / (changed size) 17.23.192.516 I slot release: id 0 | task 16149 | stop processing: n_tokens = 865, truncated = 0 17.23.192.604 I slot print_timing: id 1 | task 16150 | prompt eval time = 5704.16 ms / 881 tokens ( 6.47 ms per token, 154.45 tokens per second) 17.23.192.607 I slot print_timing: id 1 | task 16150 | eval time = 42.67 ms / 2 tokens ( 42.67 ms per token, 23.43 tokens per second) 17.23.192.608 I slot print_timing: id 1 | task 16150 | total time = 5746.84 ms / 883 tokens 17.23.192.608 I slot print_timing: id 1 | task 16150 | graphs reused = 14555 17.23.192.608 I slot print_timing: id 1 | task 16150 | graph reallocs = 0 / 0 (same size) / (changed size) 17.23.192.633 I slot release: id 1 | task 16150 | stop processing: n_tokens = 882, truncated = 0 17.23.192.716 I slot print_timing: id 2 | task 16151 | prompt eval time = 5703.97 ms / 891 tokens ( 6.40 ms per token, 156.21 tokens per second) 17.23.192.718 I slot print_timing: id 2 | task 16151 | eval time = 42.67 ms / 2 tokens ( 42.67 ms per token, 23.44 tokens per second) 17.23.192.719 I slot print_timing: id 2 | task 16151 | total time = 5746.64 ms / 893 tokens 17.23.192.719 I slot print_timing: id 2 | task 16151 | graphs reused = 14555 17.23.192.719 I slot print_timing: id 2 | task 16151 | graph reallocs = 0 / 0 (same size) / (changed size) 17.23.192.744 I slot release: id 2 | task 16151 | stop processing: n_tokens = 892, truncated = 0 17.23.192.837 I slot print_timing: id 3 | task 16155 | prompt eval time = 1190.48 ms / 95 tokens ( 12.53 ms per token, 79.80 tokens per second) 17.23.192.838 I slot print_timing: id 3 | task 16155 | eval time = 42.66 ms / 2 tokens ( 42.66 ms per token, 23.44 tokens per second) 17.23.192.838 I slot print_timing: id 3 | task 16155 | total time = 1233.15 ms / 97 tokens 17.23.192.839 I slot print_timing: id 3 | task 16155 | graphs reused = 14555 17.23.192.839 I slot print_timing: id 3 | task 16155 | graph reallocs = 0 / 0 (same size) / (changed size) 17.23.192.860 I slot release: id 3 | task 16155 | stop processing: n_tokens = 887, truncated = 0 17.23.201.818 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 865, t_last = 353826086696 17.23.201.893 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 203.497 MiB) 17.23.207.396 I slot launch_slot_: id 0 | task 16159 | processing task, is_child = 0 17.23.213.263 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 204.755 MiB) 17.23.217.702 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 175.244 MiB) 17.23.223.604 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.899 (> 0.100 thold), f_keep = 0.897 17.23.223.673 I slot launch_slot_: id 1 | task 16160 | processing task, is_child = 0 17.23.223.806 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.887 17.23.223.845 I slot launch_slot_: id 2 | task 16161 | processing task, is_child = 0 17.23.223.909 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 887, t_last = 353826087040 17.23.224.013 I slot launch_slot_: id 3 | task 16162 | processing task, is_child = 0 17.27.218.980 I slot print_timing: id 1 | task 16160 | prompt eval time = 2321.28 ms / 89 tokens ( 26.08 ms per token, 38.34 tokens per second) 17.27.218.984 I slot print_timing: id 1 | task 16160 | eval time = 1673.55 ms / 2 tokens ( 1673.55 ms per token, 0.60 tokens per second) 17.27.218.985 I slot print_timing: id 1 | task 16160 | total time = 3994.83 ms / 91 tokens 17.27.218.985 I slot print_timing: id 1 | task 16160 | graphs reused = 14555 17.27.218.986 I slot print_timing: id 1 | task 16160 | graph reallocs = 0 / 0 (same size) / (changed size) 17.27.219.024 I slot release: id 1 | task 16160 | stop processing: n_tokens = 881, truncated = 0 17.27.219.162 I slot print_timing: id 2 | task 16161 | prompt eval time = 2320.28 ms / 83 tokens ( 27.96 ms per token, 35.77 tokens per second) 17.27.219.166 I slot print_timing: id 2 | task 16161 | eval time = 1673.58 ms / 2 tokens ( 1673.58 ms per token, 0.60 tokens per second) 17.27.219.166 I slot print_timing: id 2 | task 16161 | total time = 3993.86 ms / 85 tokens 17.27.219.166 I slot print_timing: id 2 | task 16161 | graphs reused = 14555 17.27.219.167 I slot print_timing: id 2 | task 16161 | graph reallocs = 0 / 0 (same size) / (changed size) 17.27.219.193 I slot release: id 2 | task 16161 | stop processing: n_tokens = 875, truncated = 0 17.27.219.201 I slot print_timing: id 0 | task 16159 | prompt processing, n_tokens = 615, progress = 0.86, t = 3.99 s / 153.95 tokens per second 17.27.221.111 I slot print_timing: id 3 | task 16162 | prompt processing, n_tokens = 987, progress = 0.66, t = 3.99 s / 247.22 tokens per second 17.27.581.557 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 881, t_last = 353830113204 17.27.581.653 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 137.995 MiB) 17.27.581.663 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 139.526 MiB) 17.28.199.874 I slot launch_slot_: id 1 | task 16167 | processing task, is_child = 0 17.28.199.974 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 177.897 MiB) 17.28.206.314 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 875, t_last = 353830113373 17.28.206.437 I slot launch_slot_: id 2 | task 16168 | processing task, is_child = 0 17.28.206.444 I slot print_timing: id 0 | task 16159 | prompt processing, n_tokens = 712, progress = 0.99, t = 4.36 s / 163.40 tokens per second 17.28.208.071 I slot print_timing: id 3 | task 16162 | prompt processing, n_tokens = 1265, progress = 0.84, t = 4.36 s / 290.46 tokens per second 17.30.046.263 I slot print_timing: id 3 | task 16162 | prompt processing, n_tokens = 1499, progress = 1.00, t = 6.82 s / 219.89 tokens per second 17.30.756.160 I slot print_timing: id 0 | task 16159 | prompt eval time = 6819.70 ms / 716 tokens ( 9.52 ms per token, 104.99 tokens per second) 17.30.756.166 I slot print_timing: id 0 | task 16159 | eval time = 712.43 ms / 2 tokens ( 712.43 ms per token, 1.40 tokens per second) 17.30.756.166 I slot print_timing: id 0 | task 16159 | total time = 7532.13 ms / 718 tokens 17.30.756.167 I slot print_timing: id 0 | task 16159 | graphs reused = 14555 17.30.756.167 I slot print_timing: id 0 | task 16159 | graph reallocs = 0 / 0 (same size) / (changed size) 17.30.756.209 I slot release: id 0 | task 16159 | stop processing: n_tokens = 717, truncated = 0 17.32.530.106 I slot print_timing: id 3 | task 16162 | prompt eval time = 7529.90 ms / 1503 tokens ( 5.01 ms per token, 199.60 tokens per second) 17.32.530.109 I slot print_timing: id 3 | task 16162 | eval time = 1773.78 ms / 2 tokens ( 1773.78 ms per token, 0.56 tokens per second) 17.32.530.110 I slot print_timing: id 3 | task 16162 | total time = 9303.68 ms / 1505 tokens 17.32.530.110 I slot print_timing: id 3 | task 16162 | graphs reused = 14555 17.32.530.110 I slot print_timing: id 3 | task 16162 | graph reallocs = 0 / 0 (same size) / (changed size) 17.32.530.176 I slot release: id 3 | task 16162 | stop processing: n_tokens = 1504, truncated = 0 17.32.530.184 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.857 (> 0.100 thold), f_keep = 0.858 17.32.530.272 I slot launch_slot_: id 3 | task 16172 | processing task, is_child = 0 17.32.530.358 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 175.518 MiB) 17.32.535.862 I slot print_timing: id 1 | task 16167 | prompt processing, n_tokens = 945, progress = 0.65, t = 4.32 s / 218.63 tokens per second 17.32.536.984 I slot print_timing: id 2 | task 16168 | prompt processing, n_tokens = 973, progress = 0.65, t = 4.32 s / 225.12 tokens per second 17.34.309.953 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 717, t_last = 353833650389 17.34.310.126 I slot launch_slot_: id 0 | task 16174 | processing task, is_child = 0 17.34.310.237 I slot print_timing: id 1 | task 16167 | prompt processing, n_tokens = 1265, progress = 0.87, t = 6.10 s / 207.30 tokens per second 17.34.454.742 I slot print_timing: id 2 | task 16168 | prompt processing, n_tokens = 1265, progress = 0.85, t = 6.10 s / 207.30 tokens per second 17.36.315.856 I slot print_timing: id 1 | task 16167 | prompt processing, n_tokens = 1457, progress = 1.00, t = 8.11 s / 179.71 tokens per second 17.36.318.558 I slot print_timing: id 2 | task 16168 | prompt processing, n_tokens = 1485, progress = 1.00, t = 8.11 s / 183.17 tokens per second 17.36.854.960 I slot print_timing: id 3 | task 16172 | prompt eval time = 3777.00 ms / 215 tokens ( 17.57 ms per token, 56.92 tokens per second) 17.36.854.966 I slot print_timing: id 3 | task 16172 | eval time = 539.86 ms / 2 tokens ( 539.86 ms per token, 1.85 tokens per second) 17.36.854.966 I slot print_timing: id 3 | task 16172 | total time = 4316.86 ms / 217 tokens 17.36.854.966 I slot print_timing: id 3 | task 16172 | graphs reused = 14555 17.36.854.967 I slot print_timing: id 3 | task 16172 | graph reallocs = 0 / 0 (same size) / (changed size) 17.36.855.029 I slot release: id 3 | task 16172 | stop processing: n_tokens = 1506, truncated = 0 17.38.087.828 I slot print_timing: id 1 | task 16167 | prompt eval time = 8647.07 ms / 1461 tokens ( 5.92 ms per token, 168.96 tokens per second) 17.38.087.831 I slot print_timing: id 1 | task 16167 | eval time = 1233.10 ms / 2 tokens ( 1233.10 ms per token, 0.81 tokens per second) 17.38.087.831 I slot print_timing: id 1 | task 16167 | total time = 9880.16 ms / 1463 tokens 17.38.087.832 I slot print_timing: id 1 | task 16167 | graphs reused = 14555 17.38.087.832 I slot print_timing: id 1 | task 16167 | graph reallocs = 0 / 0 (same size) / (changed size) 17.38.087.895 I slot release: id 1 | task 16167 | stop processing: n_tokens = 1462, truncated = 0 17.38.087.994 I slot print_timing: id 2 | task 16168 | prompt eval time = 8647.08 ms / 1489 tokens ( 5.81 ms per token, 172.20 tokens per second) 17.38.087.997 I slot print_timing: id 2 | task 16168 | eval time = 1233.12 ms / 2 tokens ( 1233.12 ms per token, 0.81 tokens per second) 17.38.087.997 I slot print_timing: id 2 | task 16168 | total time = 9880.20 ms / 1491 tokens 17.38.087.998 I slot print_timing: id 2 | task 16168 | graphs reused = 14555 17.38.087.998 I slot print_timing: id 2 | task 16168 | graph reallocs = 0 / 0 (same size) / (changed size) 17.38.088.046 I slot release: id 2 | task 16168 | stop processing: n_tokens = 1490, truncated = 0 17.38.088.052 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1506, t_last = 353839749209 17.38.088.154 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 173.562 MiB) 17.38.096.161 I slot launch_slot_: id 3 | task 16178 | processing task, is_child = 0 17.38.096.259 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 174.465 MiB) 17.38.096.263 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 160.750 MiB) 17.38.101.567 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 158.644 MiB) 17.38.106.681 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1462, t_last = 353840982075 17.38.106.859 I slot launch_slot_: id 1 | task 16179 | processing task, is_child = 0 17.38.106.951 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1490, t_last = 353840982226 17.38.107.084 I slot launch_slot_: id 2 | task 16180 | processing task, is_child = 0 17.38.107.091 I slot print_timing: id 0 | task 16174 | prompt processing, n_tokens = 1072, progress = 0.68, t = 3.78 s / 283.78 tokens per second 17.39.222.501 I slot print_timing: id 0 | task 16174 | prompt processing, n_tokens = 1265, progress = 0.80, t = 4.91 s / 257.51 tokens per second 17.40.659.725 I slot print_timing: id 0 | task 16174 | prompt processing, n_tokens = 1584, progress = 1.00, t = 6.35 s / 249.47 tokens per second 17.41.967.811 I slot print_timing: id 1 | task 16179 | prompt processing, n_tokens = 262, progress = 0.34, t = 3.86 s / 67.89 tokens per second 17.41.968.442 I slot print_timing: id 2 | task 16180 | prompt processing, n_tokens = 628, progress = 0.85, t = 3.86 s / 162.73 tokens per second 17.41.970.513 I slot print_timing: id 3 | task 16178 | prompt processing, n_tokens = 233, progress = 0.31, t = 3.86 s / 60.38 tokens per second 17.43.896.342 I slot print_timing: id 0 | task 16174 | prompt eval time = 7657.66 ms / 1588 tokens ( 4.82 ms per token, 207.37 tokens per second) 17.43.896.345 I slot print_timing: id 0 | task 16174 | eval time = 1928.54 ms / 2 tokens ( 1928.54 ms per token, 0.52 tokens per second) 17.43.896.345 I slot print_timing: id 0 | task 16174 | total time = 9586.20 ms / 1590 tokens 17.43.896.346 I slot print_timing: id 0 | task 16174 | graphs reused = 14555 17.43.896.346 I slot print_timing: id 0 | task 16174 | graph reallocs = 0 / 0 (same size) / (changed size) 17.43.896.416 I slot release: id 0 | task 16174 | stop processing: n_tokens = 1589, truncated = 0 17.43.896.428 I slot print_timing: id 1 | task 16179 | prompt processing, n_tokens = 648, progress = 0.83, t = 5.79 s / 111.96 tokens per second 17.43.898.014 I slot print_timing: id 2 | task 16180 | prompt processing, n_tokens = 739, progress = 0.99, t = 5.79 s / 127.68 tokens per second 17.43.900.697 I slot print_timing: id 3 | task 16178 | prompt processing, n_tokens = 648, progress = 0.87, t = 5.79 s / 111.97 tokens per second 17.44.724.943 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1589, t_last = 353846790596 17.44.725.051 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 161.420 MiB) 17.44.731.729 I slot launch_slot_: id 0 | task 16186 | processing task, is_child = 0 17.44.731.922 I slot print_timing: id 1 | task 16179 | prompt processing, n_tokens = 774, progress = 0.99, t = 6.62 s / 116.98 tokens per second 17.44.733.158 I slot print_timing: id 3 | task 16178 | prompt processing, n_tokens = 745, progress = 0.99, t = 6.62 s / 112.61 tokens per second 17.45.239.756 I slot print_timing: id 2 | task 16180 | prompt eval time = 6616.47 ms / 743 tokens ( 8.91 ms per token, 112.30 tokens per second) 17.45.239.762 I slot print_timing: id 2 | task 16180 | eval time = 514.82 ms / 2 tokens ( 514.82 ms per token, 1.94 tokens per second) 17.45.239.763 I slot print_timing: id 2 | task 16180 | total time = 7131.29 ms / 745 tokens 17.45.239.763 I slot print_timing: id 2 | task 16180 | graphs reused = 14555 17.45.239.763 I slot print_timing: id 2 | task 16180 | graph reallocs = 0 / 0 (same size) / (changed size) 17.45.239.797 I slot release: id 2 | task 16180 | stop processing: n_tokens = 744, truncated = 0 17.45.651.575 I slot print_timing: id 1 | task 16179 | prompt eval time = 7131.39 ms / 778 tokens ( 9.17 ms per token, 109.10 tokens per second) 17.45.651.579 I slot print_timing: id 1 | task 16179 | eval time = 411.90 ms / 2 tokens ( 411.90 ms per token, 2.43 tokens per second) 17.45.651.579 I slot print_timing: id 1 | task 16179 | total time = 7543.29 ms / 780 tokens 17.45.651.580 I slot print_timing: id 1 | task 16179 | graphs reused = 14555 17.45.651.580 I slot print_timing: id 1 | task 16179 | graph reallocs = 0 / 0 (same size) / (changed size) 17.45.651.630 I slot release: id 1 | task 16179 | stop processing: n_tokens = 779, truncated = 0 17.45.651.738 I slot print_timing: id 3 | task 16178 | prompt eval time = 7131.09 ms / 749 tokens ( 9.52 ms per token, 105.03 tokens per second) 17.45.651.740 I slot print_timing: id 3 | task 16178 | eval time = 411.83 ms / 2 tokens ( 411.83 ms per token, 2.43 tokens per second) 17.45.651.740 I slot print_timing: id 3 | task 16178 | total time = 7542.91 ms / 751 tokens 17.45.651.740 I slot print_timing: id 3 | task 16178 | graphs reused = 14555 17.45.651.741 I slot print_timing: id 3 | task 16178 | graph reallocs = 0 / 0 (same size) / (changed size) 17.45.651.769 I slot release: id 3 | task 16178 | stop processing: n_tokens = 750, truncated = 0 17.45.651.775 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.834 (> 0.100 thold), f_keep = 0.878 17.45.651.862 I slot launch_slot_: id 2 | task 16189 | processing task, is_child = 0 17.45.651.953 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 166.781 MiB) 17.45.657.448 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 174.042 MiB) 17.45.662.287 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 779, t_last = 353848545810 17.45.662.401 I slot launch_slot_: id 1 | task 16190 | processing task, is_child = 0 17.45.662.482 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 750, t_last = 353848545949 17.45.662.583 I slot launch_slot_: id 3 | task 16191 | processing task, is_child = 0 17.47.815.325 I slot print_timing: id 0 | task 16186 | prompt processing, n_tokens = 628, progress = 0.82, t = 3.08 s / 203.67 tokens per second 17.49.731.124 I slot print_timing: id 2 | task 16189 | prompt eval time = 2152.60 ms / 130 tokens ( 16.56 ms per token, 60.39 tokens per second) 17.49.731.127 I slot print_timing: id 2 | task 16189 | eval time = 1915.81 ms / 2 tokens ( 1915.81 ms per token, 0.52 tokens per second) 17.49.731.128 I slot print_timing: id 2 | task 16189 | total time = 4068.41 ms / 132 tokens 17.49.731.128 I slot print_timing: id 2 | task 16189 | graphs reused = 14555 17.49.731.129 I slot print_timing: id 2 | task 16189 | graph reallocs = 0 / 0 (same size) / (changed size) 17.49.731.169 I slot release: id 2 | task 16189 | stop processing: n_tokens = 784, truncated = 0 17.49.731.181 I slot print_timing: id 0 | task 16186 | prompt processing, n_tokens = 759, progress = 0.99, t = 5.00 s / 151.82 tokens per second 17.49.733.226 I slot print_timing: id 1 | task 16190 | prompt processing, n_tokens = 544, progress = 0.83, t = 4.07 s / 133.71 tokens per second 17.49.735.750 I slot print_timing: id 3 | task 16191 | prompt processing, n_tokens = 544, progress = 0.80, t = 4.07 s / 133.76 tokens per second 17.50.582.535 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 784, t_last = 353852625349 17.50.582.614 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 174.904 MiB) 17.50.589.142 I slot launch_slot_: id 2 | task 16196 | processing task, is_child = 0 17.50.589.154 I slot print_timing: id 1 | task 16190 | prompt processing, n_tokens = 648, progress = 0.99, t = 4.92 s / 131.71 tokens per second 17.50.590.475 I slot print_timing: id 3 | task 16191 | prompt processing, n_tokens = 675, progress = 0.99, t = 4.92 s / 137.24 tokens per second 17.51.012.282 I slot print_timing: id 0 | task 16186 | prompt eval time = 5850.79 ms / 763 tokens ( 7.67 ms per token, 130.41 tokens per second) 17.51.012.287 I slot print_timing: id 0 | task 16186 | eval time = 429.75 ms / 2 tokens ( 429.75 ms per token, 2.33 tokens per second) 17.51.012.288 I slot print_timing: id 0 | task 16186 | total time = 6280.54 ms / 765 tokens 17.51.012.288 I slot print_timing: id 0 | task 16186 | graphs reused = 14555 17.51.012.289 I slot print_timing: id 0 | task 16186 | graph reallocs = 0 / 0 (same size) / (changed size) 17.51.012.328 I slot release: id 0 | task 16186 | stop processing: n_tokens = 764, truncated = 0 17.51.129.236 I slot print_timing: id 1 | task 16190 | prompt eval time = 5349.84 ms / 652 tokens ( 8.21 ms per token, 121.87 tokens per second) 17.51.129.242 I slot print_timing: id 1 | task 16190 | eval time = 116.79 ms / 2 tokens ( 116.79 ms per token, 8.56 tokens per second) 17.51.129.244 I slot print_timing: id 1 | task 16190 | total time = 5466.63 ms / 654 tokens 17.51.129.244 I slot print_timing: id 1 | task 16190 | graphs reused = 14555 17.51.129.244 I slot print_timing: id 1 | task 16190 | graph reallocs = 0 / 0 (same size) / (changed size) 17.51.129.284 I slot release: id 1 | task 16190 | stop processing: n_tokens = 653, truncated = 0 17.51.129.439 I slot print_timing: id 3 | task 16191 | prompt eval time = 5348.61 ms / 679 tokens ( 7.88 ms per token, 126.95 tokens per second) 17.51.129.442 I slot print_timing: id 3 | task 16191 | eval time = 116.89 ms / 2 tokens ( 116.89 ms per token, 8.56 tokens per second) 17.51.129.442 I slot print_timing: id 3 | task 16191 | total time = 5465.49 ms / 681 tokens 17.51.129.442 I slot print_timing: id 3 | task 16191 | graphs reused = 14555 17.51.129.443 I slot print_timing: id 3 | task 16191 | graph reallocs = 0 / 0 (same size) / (changed size) 17.51.129.469 I slot release: id 3 | task 16191 | stop processing: n_tokens = 680, truncated = 0 17.51.129.473 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 764, t_last = 353853906508 17.51.129.556 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 250.994 MiB) 17.51.134.152 I slot launch_slot_: id 0 | task 16199 | processing task, is_child = 0 17.51.137.785 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 251.596 MiB) 17.51.141.327 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 653, t_last = 353854023464 17.51.141.471 I slot launch_slot_: id 1 | task 16200 | processing task, is_child = 0 17.54.515.397 I slot print_timing: id 0 | task 16199 | prompt processing, n_tokens = 495, progress = 0.79, t = 3.37 s / 146.72 tokens per second 17.54.516.555 I slot print_timing: id 1 | task 16200 | prompt processing, n_tokens = 495, progress = 0.84, t = 3.37 s / 146.73 tokens per second 17.55.220.937 I slot print_timing: id 2 | task 16196 | prompt eval time = 3925.01 ms / 603 tokens ( 6.51 ms per token, 153.63 tokens per second) 17.55.220.939 I slot print_timing: id 2 | task 16196 | eval time = 705.55 ms / 2 tokens ( 705.55 ms per token, 1.42 tokens per second) 17.55.220.939 I slot print_timing: id 2 | task 16196 | total time = 4630.55 ms / 605 tokens 17.55.220.940 I slot print_timing: id 2 | task 16196 | graphs reused = 14555 17.55.220.940 I slot print_timing: id 2 | task 16196 | graph reallocs = 0 / 0 (same size) / (changed size) 17.55.220.982 I slot release: id 2 | task 16196 | stop processing: n_tokens = 604, truncated = 0 17.55.220.993 I slot print_timing: id 0 | task 16199 | prompt processing, n_tokens = 621, progress = 0.99, t = 4.08 s / 152.23 tokens per second 17.55.222.668 I slot print_timing: id 1 | task 16200 | prompt processing, n_tokens = 587, progress = 0.99, t = 4.08 s / 143.90 tokens per second 17.55.316.468 I slot print_timing: id 0 | task 16199 | prompt eval time = 4141.81 ms / 625 tokens ( 6.63 ms per token, 150.90 tokens per second) 17.55.316.473 I slot print_timing: id 0 | task 16199 | eval time = 33.13 ms / 2 tokens ( 33.13 ms per token, 30.19 tokens per second) 17.55.316.473 I slot print_timing: id 0 | task 16199 | total time = 4174.94 ms / 627 tokens 17.55.316.474 I slot print_timing: id 0 | task 16199 | graphs reused = 14555 17.55.316.474 I slot print_timing: id 0 | task 16199 | graph reallocs = 0 / 0 (same size) / (changed size) 17.55.316.500 I slot release: id 0 | task 16199 | stop processing: n_tokens = 626, truncated = 0 17.55.316.583 I slot print_timing: id 1 | task 16200 | prompt eval time = 4141.78 ms / 591 tokens ( 7.01 ms per token, 142.69 tokens per second) 17.55.316.585 I slot print_timing: id 1 | task 16200 | eval time = 33.14 ms / 2 tokens ( 33.14 ms per token, 30.18 tokens per second) 17.55.316.585 I slot print_timing: id 1 | task 16200 | total time = 4174.92 ms / 593 tokens 17.55.316.585 I slot print_timing: id 1 | task 16200 | graphs reused = 14555 17.55.316.585 I slot print_timing: id 1 | task 16200 | graph reallocs = 0 / 0 (same size) / (changed size) 17.55.316.601 I slot release: id 1 | task 16200 | stop processing: n_tokens = 592, truncated = 0 17.57.657.802 I srv operator(): operator(): cleaning up before exit...