/Users/minipro/quantdiff/llama.cpp/llama-b11770/llama-server -m /Users/minipro/quantdiff/models/campaign/d54834c785c7/LFM2.5-24B-A2B-UD-Q3_K_XL.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 0.00.043.248 W Setting 'enable_thinking' via --chat-template-kwargs is deprecated. Use --reasoning on / --reasoning off instead. 0.00.043.308 I srv llama_server: initializing ... 0.00.043.313 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.043.379 I srv init_listene: The UI is disabled 0.00.043.380 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.043.414 W srv llama_server: security: no API key is set and CORS allows all origins (see https://github.com/ggml-org/llama.cpp/pull/25655) 0.00.045.104 I srv load_model: loading model '/Users/minipro/quantdiff/models/campaign/d54834c785c7/LFM2.5-24B-A2B-UD-Q3_K_XL.gguf' 0.00.878.963 I cmn init: llama threadpool init, n_threads = 8 0.00.954.843 I srv load_model: initializing, n_slots = 4, n_ctx_slot = 4096, kv_unified = 'false' 0.00.957.824 W srv init: chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve) 0.00.957.836 I srv llama_server: model loaded 0.00.957.838 I srv llama_server: listening on http://127.0.0.1:8091 0.30.002.693 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.30.002.725 I slot launch_slot_: id 0 | task 0 | processing task, is_child = 0 0.30.002.726 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.30.002.738 I slot launch_slot_: id 1 | task 1 | processing task, is_child = 0 0.30.002.739 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.30.002.750 I slot launch_slot_: id 2 | task 2 | processing task, is_child = 0 0.30.002.750 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.30.002.765 I slot launch_slot_: id 3 | task 3 | processing task, is_child = 0 0.31.092.369 I slot print_timing: id 0 | task 0 | prompt eval time = 1048.54 ms / 123 tokens ( 8.52 ms per token, 117.31 tokens per second) 0.31.092.372 I slot print_timing: id 0 | task 0 | eval time = 41.05 ms / 2 tokens ( 41.05 ms per token, 24.36 tokens per second) 0.31.092.372 I slot print_timing: id 0 | task 0 | total time = 1089.59 ms / 125 tokens 0.31.092.373 I slot print_timing: id 0 | task 0 | graphs reused = 1 0.31.092.373 I slot print_timing: id 0 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.092.393 I slot release: id 0 | task 0 | stop processing: n_tokens = 124, truncated = 0 0.31.092.676 I slot print_timing: id 1 | task 1 | prompt eval time = 1048.91 ms / 131 tokens ( 8.01 ms per token, 124.89 tokens per second) 0.31.092.678 I slot print_timing: id 1 | task 1 | eval time = 40.99 ms / 2 tokens ( 40.99 ms per token, 24.40 tokens per second) 0.31.092.679 I slot print_timing: id 1 | task 1 | total time = 1089.90 ms / 133 tokens 0.31.092.679 I slot print_timing: id 1 | task 1 | graphs reused = 1 0.31.092.679 I slot print_timing: id 1 | task 1 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.092.693 I slot release: id 1 | task 1 | stop processing: n_tokens = 132, truncated = 0 0.31.092.966 I slot print_timing: id 2 | task 2 | prompt eval time = 1049.30 ms / 117 tokens ( 8.97 ms per token, 111.50 tokens per second) 0.31.092.967 I slot print_timing: id 2 | task 2 | eval time = 40.88 ms / 2 tokens ( 40.88 ms per token, 24.46 tokens per second) 0.31.092.968 I slot print_timing: id 2 | task 2 | total time = 1090.18 ms / 119 tokens 0.31.092.968 I slot print_timing: id 2 | task 2 | graphs reused = 1 0.31.092.968 I slot print_timing: id 2 | task 2 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.092.978 I slot release: id 2 | task 2 | stop processing: n_tokens = 118, truncated = 0 0.31.093.360 I slot print_timing: id 3 | task 3 | prompt eval time = 1049.76 ms / 112 tokens ( 9.37 ms per token, 106.69 tokens per second) 0.31.093.362 I slot print_timing: id 3 | task 3 | eval time = 40.81 ms / 2 tokens ( 40.81 ms per token, 24.50 tokens per second) 0.31.093.363 I slot print_timing: id 3 | task 3 | total time = 1090.57 ms / 114 tokens 0.31.093.363 I slot print_timing: id 3 | task 3 | graphs reused = 1 0.31.093.363 I slot print_timing: id 3 | task 3 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.093.375 I slot release: id 3 | task 3 | stop processing: n_tokens = 113, truncated = 0 0.31.098.116 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.186 (> 0.100 thold), f_keep = 0.242 0.31.098.375 I slot launch_slot_: id 0 | task 7 | processing task, is_child = 0 0.31.099.396 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.273 (> 0.100 thold), f_keep = 0.227 0.31.099.428 I slot launch_slot_: id 1 | task 8 | processing task, is_child = 0 0.31.099.459 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.180 (> 0.100 thold), f_keep = 0.246 0.31.099.485 I slot launch_slot_: id 2 | task 9 | processing task, is_child = 0 0.31.099.502 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.146 (> 0.100 thold), f_keep = 0.257 0.31.099.528 I slot launch_slot_: id 3 | task 10 | processing task, is_child = 0 0.32.458.586 I slot print_timing: id 0 | task 7 | prompt eval time = 1318.86 ms / 161 tokens ( 8.19 ms per token, 122.08 tokens per second) 0.32.458.588 I slot print_timing: id 0 | task 7 | eval time = 40.19 ms / 2 tokens ( 40.19 ms per token, 24.88 tokens per second) 0.32.458.589 I slot print_timing: id 0 | task 7 | total time = 1359.05 ms / 163 tokens 0.32.458.589 I slot print_timing: id 0 | task 7 | graphs reused = 1 0.32.458.590 I slot print_timing: id 0 | task 7 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.458.624 I slot release: id 0 | task 7 | stop processing: n_tokens = 162, truncated = 0 0.32.458.888 I slot print_timing: id 1 | task 8 | prompt eval time = 1319.21 ms / 110 tokens ( 11.99 ms per token, 83.38 tokens per second) 0.32.458.890 I slot print_timing: id 1 | task 8 | eval time = 40.13 ms / 2 tokens ( 40.13 ms per token, 24.92 tokens per second) 0.32.458.890 I slot print_timing: id 1 | task 8 | total time = 1359.34 ms / 112 tokens 0.32.458.890 I slot print_timing: id 1 | task 8 | graphs reused = 1 0.32.458.891 I slot print_timing: id 1 | task 8 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.458.906 I slot release: id 1 | task 8 | stop processing: n_tokens = 111, truncated = 0 0.32.459.176 I slot print_timing: id 2 | task 9 | prompt eval time = 1319.58 ms / 161 tokens ( 8.20 ms per token, 122.01 tokens per second) 0.32.459.178 I slot print_timing: id 2 | task 9 | eval time = 40.03 ms / 2 tokens ( 40.03 ms per token, 24.98 tokens per second) 0.32.459.178 I slot print_timing: id 2 | task 9 | total time = 1359.62 ms / 163 tokens 0.32.459.179 I slot print_timing: id 2 | task 9 | graphs reused = 1 0.32.459.179 I slot print_timing: id 2 | task 9 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.459.196 I slot release: id 2 | task 9 | stop processing: n_tokens = 162, truncated = 0 0.32.459.507 I slot print_timing: id 3 | task 10 | prompt eval time = 1319.98 ms / 199 tokens ( 6.63 ms per token, 150.76 tokens per second) 0.32.459.511 I slot print_timing: id 3 | task 10 | eval time = 39.96 ms / 2 tokens ( 39.96 ms per token, 25.03 tokens per second) 0.32.459.511 I slot print_timing: id 3 | task 10 | total time = 1359.94 ms / 201 tokens 0.32.459.511 I slot print_timing: id 3 | task 10 | graphs reused = 1 0.32.459.512 I slot print_timing: id 3 | task 10 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.459.532 I slot release: id 3 | task 10 | stop processing: n_tokens = 200, truncated = 0 0.32.464.938 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.179 0.32.465.221 I slot launch_slot_: id 0 | task 14 | processing task, is_child = 0 0.32.466.521 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.252 (> 0.100 thold), f_keep = 0.270 0.32.466.554 I slot launch_slot_: id 1 | task 15 | processing task, is_child = 0 0.32.466.589 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.192 (> 0.100 thold), f_keep = 0.179 0.32.466.622 I slot launch_slot_: id 2 | task 16 | processing task, is_child = 0 0.32.466.641 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.250 (> 0.100 thold), f_keep = 0.145 0.32.466.674 I slot launch_slot_: id 3 | task 17 | processing task, is_child = 0 0.33.472.719 I slot print_timing: id 0 | task 14 | prompt eval time = 966.11 ms / 127 tokens ( 7.61 ms per token, 131.46 tokens per second) 0.33.472.721 I slot print_timing: id 0 | task 14 | eval time = 39.93 ms / 2 tokens ( 39.93 ms per token, 25.05 tokens per second) 0.33.472.721 I slot print_timing: id 0 | task 14 | total time = 1006.04 ms / 129 tokens 0.33.472.722 I slot print_timing: id 0 | task 14 | graphs reused = 1 0.33.472.722 I slot print_timing: id 0 | task 14 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.472.746 I slot release: id 0 | task 14 | stop processing: n_tokens = 128, truncated = 0 0.33.473.028 I slot print_timing: id 1 | task 15 | prompt eval time = 966.38 ms / 119 tokens ( 8.12 ms per token, 123.14 tokens per second) 0.33.473.033 I slot print_timing: id 1 | task 15 | eval time = 39.95 ms / 2 tokens ( 39.95 ms per token, 25.03 tokens per second) 0.33.473.034 I slot print_timing: id 1 | task 15 | total time = 1006.33 ms / 121 tokens 0.33.473.034 I slot print_timing: id 1 | task 15 | graphs reused = 1 0.33.473.034 I slot print_timing: id 1 | task 15 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.473.048 I slot release: id 1 | task 15 | stop processing: n_tokens = 120, truncated = 0 0.33.473.324 I slot print_timing: id 2 | task 16 | prompt eval time = 966.65 ms / 151 tokens ( 6.40 ms per token, 156.21 tokens per second) 0.33.473.326 I slot print_timing: id 2 | task 16 | eval time = 39.96 ms / 2 tokens ( 39.96 ms per token, 25.02 tokens per second) 0.33.473.327 I slot print_timing: id 2 | task 16 | total time = 1006.62 ms / 153 tokens 0.33.473.327 I slot print_timing: id 2 | task 16 | graphs reused = 1 0.33.473.327 I slot print_timing: id 2 | task 16 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.473.340 I slot release: id 2 | task 16 | stop processing: n_tokens = 152, truncated = 0 0.33.473.749 I slot print_timing: id 3 | task 17 | prompt eval time = 967.02 ms / 116 tokens ( 8.34 ms per token, 119.96 tokens per second) 0.33.473.751 I slot print_timing: id 3 | task 17 | eval time = 40.01 ms / 2 tokens ( 40.01 ms per token, 24.99 tokens per second) 0.33.473.752 I slot print_timing: id 3 | task 17 | total time = 1007.03 ms / 118 tokens 0.33.473.752 I slot print_timing: id 3 | task 17 | graphs reused = 1 0.33.473.752 I slot print_timing: id 3 | task 17 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.473.763 I slot release: id 3 | task 17 | stop processing: n_tokens = 117, truncated = 0 0.33.477.881 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.203 (> 0.100 thold), f_keep = 0.227 0.33.478.282 I slot launch_slot_: id 0 | task 21 | processing task, is_child = 0 0.33.479.271 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.215 (> 0.100 thold), f_keep = 0.242 0.33.479.302 I slot launch_slot_: id 1 | task 22 | processing task, is_child = 0 0.33.479.334 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.242 (> 0.100 thold), f_keep = 0.191 0.33.479.363 I slot launch_slot_: id 2 | task 24 | processing task, is_child = 0 0.33.479.380 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.158 (> 0.100 thold), f_keep = 0.248 0.33.479.407 I slot launch_slot_: id 3 | task 23 | processing task, is_child = 0 0.34.653.239 I slot print_timing: id 0 | task 21 | prompt eval time = 1133.70 ms / 143 tokens ( 7.93 ms per token, 126.14 tokens per second) 0.34.653.242 I slot print_timing: id 0 | task 21 | eval time = 40.12 ms / 2 tokens ( 40.12 ms per token, 24.92 tokens per second) 0.34.653.242 I slot print_timing: id 0 | task 21 | total time = 1173.82 ms / 145 tokens 0.34.653.243 I slot print_timing: id 0 | task 21 | graphs reused = 1 0.34.653.243 I slot print_timing: id 0 | task 21 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.653.268 I slot release: id 0 | task 21 | stop processing: n_tokens = 144, truncated = 0 0.34.653.539 I slot print_timing: id 1 | task 22 | prompt eval time = 1133.97 ms / 135 tokens ( 8.40 ms per token, 119.05 tokens per second) 0.34.653.542 I slot print_timing: id 1 | task 22 | eval time = 40.14 ms / 2 tokens ( 40.14 ms per token, 24.91 tokens per second) 0.34.653.543 I slot print_timing: id 1 | task 22 | total time = 1174.11 ms / 137 tokens 0.34.653.543 I slot print_timing: id 1 | task 22 | graphs reused = 1 0.34.653.543 I slot print_timing: id 1 | task 22 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.653.557 I slot release: id 1 | task 22 | stop processing: n_tokens = 136, truncated = 0 0.34.653.851 I slot print_timing: id 2 | task 24 | prompt eval time = 1134.27 ms / 120 tokens ( 9.45 ms per token, 105.80 tokens per second) 0.34.653.853 I slot print_timing: id 2 | task 24 | eval time = 40.15 ms / 2 tokens ( 40.15 ms per token, 24.91 tokens per second) 0.34.653.854 I slot print_timing: id 2 | task 24 | total time = 1174.42 ms / 122 tokens 0.34.653.854 I slot print_timing: id 2 | task 24 | graphs reused = 1 0.34.653.854 I slot print_timing: id 2 | task 24 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.653.866 I slot release: id 2 | task 24 | stop processing: n_tokens = 121, truncated = 0 0.34.654.140 I slot print_timing: id 3 | task 23 | prompt eval time = 1134.57 ms / 184 tokens ( 6.17 ms per token, 162.18 tokens per second) 0.34.654.142 I slot print_timing: id 3 | task 23 | eval time = 40.12 ms / 2 tokens ( 40.12 ms per token, 24.92 tokens per second) 0.34.654.142 I slot print_timing: id 3 | task 23 | total time = 1174.69 ms / 186 tokens 0.34.654.142 I slot print_timing: id 3 | task 23 | graphs reused = 1 0.34.654.143 I slot print_timing: id 3 | task 23 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.654.159 I slot release: id 3 | task 23 | stop processing: n_tokens = 185, truncated = 0 0.34.658.387 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.162 (> 0.100 thold), f_keep = 0.201 0.34.658.841 I slot launch_slot_: id 0 | task 29 | processing task, is_child = 0 0.34.659.938 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.232 (> 0.100 thold), f_keep = 0.213 0.34.660.087 I slot launch_slot_: id 1 | task 28 | processing task, is_child = 0 0.34.660.124 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.221 (> 0.100 thold), f_keep = 0.240 0.34.660.256 I slot launch_slot_: id 2 | task 31 | processing task, is_child = 0 0.34.660.275 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.206 (> 0.100 thold), f_keep = 0.157 0.34.660.304 I slot launch_slot_: id 3 | task 30 | processing task, is_child = 0 0.35.761.231 I slot print_timing: id 0 | task 29 | prompt eval time = 1061.05 ms / 179 tokens ( 5.93 ms per token, 168.70 tokens per second) 0.35.761.234 I slot print_timing: id 0 | task 29 | eval time = 39.88 ms / 2 tokens ( 39.88 ms per token, 25.08 tokens per second) 0.35.761.234 I slot print_timing: id 0 | task 29 | total time = 1100.92 ms / 181 tokens 0.35.761.235 I slot print_timing: id 0 | task 29 | graphs reused = 1 0.35.761.235 I slot print_timing: id 0 | task 29 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.761.258 I slot release: id 0 | task 29 | stop processing: n_tokens = 180, truncated = 0 0.35.761.522 I slot print_timing: id 1 | task 28 | prompt eval time = 1061.30 ms / 125 tokens ( 8.49 ms per token, 117.78 tokens per second) 0.35.761.525 I slot print_timing: id 1 | task 28 | eval time = 39.90 ms / 2 tokens ( 39.90 ms per token, 25.06 tokens per second) 0.35.761.525 I slot print_timing: id 1 | task 28 | total time = 1101.20 ms / 127 tokens 0.35.761.525 I slot print_timing: id 1 | task 28 | graphs reused = 1 0.35.761.526 I slot print_timing: id 1 | task 28 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.761.541 I slot release: id 1 | task 28 | stop processing: n_tokens = 126, truncated = 0 0.35.761.848 I slot print_timing: id 2 | task 31 | prompt eval time = 1061.58 ms / 131 tokens ( 8.10 ms per token, 123.40 tokens per second) 0.35.761.849 I slot print_timing: id 2 | task 31 | eval time = 39.94 ms / 2 tokens ( 39.94 ms per token, 25.04 tokens per second) 0.35.761.850 I slot print_timing: id 2 | task 31 | total time = 1101.52 ms / 133 tokens 0.35.761.850 I slot print_timing: id 2 | task 31 | graphs reused = 1 0.35.761.850 I slot print_timing: id 2 | task 31 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.761.867 I slot release: id 2 | task 31 | stop processing: n_tokens = 132, truncated = 0 0.35.762.164 I slot print_timing: id 3 | task 30 | prompt eval time = 1061.89 ms / 141 tokens ( 7.53 ms per token, 132.78 tokens per second) 0.35.762.166 I slot print_timing: id 3 | task 30 | eval time = 39.94 ms / 2 tokens ( 39.94 ms per token, 25.04 tokens per second) 0.35.762.166 I slot print_timing: id 3 | task 30 | total time = 1101.82 ms / 143 tokens 0.35.762.166 I slot print_timing: id 3 | task 30 | graphs reused = 1 0.35.762.167 I slot print_timing: id 3 | task 30 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.762.187 I slot release: id 3 | task 30 | stop processing: n_tokens = 142, truncated = 0 0.35.765.686 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.257 (> 0.100 thold), f_keep = 0.161 0.35.766.148 I slot launch_slot_: id 0 | task 36 | processing task, is_child = 0 0.35.767.145 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.203 (> 0.100 thold), f_keep = 0.230 0.35.767.183 I slot launch_slot_: id 1 | task 35 | processing task, is_child = 0 0.35.767.219 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.246 (> 0.100 thold), f_keep = 0.227 0.35.767.246 I slot launch_slot_: id 2 | task 37 | processing task, is_child = 0 0.35.767.262 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.200 (> 0.100 thold), f_keep = 0.204 0.35.767.293 I slot launch_slot_: id 3 | task 38 | processing task, is_child = 0 0.36.898.432 I slot print_timing: id 0 | task 36 | prompt eval time = 1091.03 ms / 113 tokens ( 9.66 ms per token, 103.57 tokens per second) 0.36.898.435 I slot print_timing: id 0 | task 36 | eval time = 40.10 ms / 2 tokens ( 40.10 ms per token, 24.94 tokens per second) 0.36.898.435 I slot print_timing: id 0 | task 36 | total time = 1131.13 ms / 115 tokens 0.36.898.436 I slot print_timing: id 0 | task 36 | graphs reused = 1 0.36.898.436 I slot print_timing: id 0 | task 36 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.898.455 I slot release: id 0 | task 36 | stop processing: n_tokens = 114, truncated = 0 0.36.898.720 I slot print_timing: id 1 | task 35 | prompt eval time = 1091.29 ms / 143 tokens ( 7.63 ms per token, 131.04 tokens per second) 0.36.898.722 I slot print_timing: id 1 | task 35 | eval time = 40.11 ms / 2 tokens ( 40.11 ms per token, 24.93 tokens per second) 0.36.898.723 I slot print_timing: id 1 | task 35 | total time = 1131.41 ms / 145 tokens 0.36.898.723 I slot print_timing: id 1 | task 35 | graphs reused = 1 0.36.898.723 I slot print_timing: id 1 | task 35 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.898.737 I slot release: id 1 | task 35 | stop processing: n_tokens = 144, truncated = 0 0.36.899.025 I slot print_timing: id 2 | task 37 | prompt eval time = 1091.58 ms / 122 tokens ( 8.95 ms per token, 111.77 tokens per second) 0.36.899.028 I slot print_timing: id 2 | task 37 | eval time = 40.12 ms / 2 tokens ( 40.12 ms per token, 24.92 tokens per second) 0.36.899.029 I slot print_timing: id 2 | task 37 | total time = 1131.70 ms / 124 tokens 0.36.899.029 I slot print_timing: id 2 | task 37 | graphs reused = 1 0.36.899.029 I slot print_timing: id 2 | task 37 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.899.044 I slot release: id 2 | task 37 | stop processing: n_tokens = 123, truncated = 0 0.36.899.364 I slot print_timing: id 3 | task 38 | prompt eval time = 1092.01 ms / 145 tokens ( 7.53 ms per token, 132.78 tokens per second) 0.36.899.365 I slot print_timing: id 3 | task 38 | eval time = 40.02 ms / 2 tokens ( 40.02 ms per token, 24.99 tokens per second) 0.36.899.366 I slot print_timing: id 3 | task 38 | total time = 1132.03 ms / 147 tokens 0.36.899.366 I slot print_timing: id 3 | task 38 | graphs reused = 1 0.36.899.366 I slot print_timing: id 3 | task 38 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.899.380 I slot release: id 3 | task 38 | stop processing: n_tokens = 146, truncated = 0 0.36.903.298 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.264 (> 0.100 thold), f_keep = 0.254 0.36.903.543 I slot launch_slot_: id 0 | task 44 | processing task, is_child = 0 0.36.904.627 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.236 (> 0.100 thold), f_keep = 0.201 0.36.904.660 I slot launch_slot_: id 1 | task 43 | processing task, is_child = 0 0.36.904.693 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.261 (> 0.100 thold), f_keep = 0.244 0.36.904.721 I slot launch_slot_: id 2 | task 42 | processing task, is_child = 0 0.36.904.740 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.199 0.36.904.769 I slot launch_slot_: id 3 | task 45 | processing task, is_child = 0 0.37.924.538 I slot print_timing: id 0 | task 44 | prompt eval time = 979.77 ms / 110 tokens ( 8.91 ms per token, 112.27 tokens per second) 0.37.924.539 I slot print_timing: id 0 | task 44 | eval time = 39.99 ms / 2 tokens ( 39.99 ms per token, 25.01 tokens per second) 0.37.924.540 I slot print_timing: id 0 | task 44 | total time = 1019.76 ms / 112 tokens 0.37.924.540 I slot print_timing: id 0 | task 44 | graphs reused = 1 0.37.924.541 I slot print_timing: id 0 | task 44 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.924.559 I slot release: id 0 | task 44 | stop processing: n_tokens = 111, truncated = 0 0.37.924.831 I slot print_timing: id 1 | task 43 | prompt eval time = 980.05 ms / 123 tokens ( 7.97 ms per token, 125.50 tokens per second) 0.37.924.833 I slot print_timing: id 1 | task 43 | eval time = 40.00 ms / 2 tokens ( 40.00 ms per token, 25.00 tokens per second) 0.37.924.834 I slot print_timing: id 1 | task 43 | total time = 1020.05 ms / 125 tokens 0.37.924.834 I slot print_timing: id 1 | task 43 | graphs reused = 1 0.37.924.834 I slot print_timing: id 1 | task 43 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.924.849 I slot release: id 1 | task 43 | stop processing: n_tokens = 124, truncated = 0 0.37.925.123 I slot print_timing: id 2 | task 42 | prompt eval time = 980.33 ms / 115 tokens ( 8.52 ms per token, 117.31 tokens per second) 0.37.925.127 I slot print_timing: id 2 | task 42 | eval time = 40.00 ms / 2 tokens ( 40.00 ms per token, 25.00 tokens per second) 0.37.925.128 I slot print_timing: id 2 | task 42 | total time = 1020.33 ms / 117 tokens 0.37.925.128 I slot print_timing: id 2 | task 42 | graphs reused = 1 0.37.925.128 I slot print_timing: id 2 | task 42 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.925.141 I slot release: id 2 | task 42 | stop processing: n_tokens = 116, truncated = 0 0.37.925.522 I slot print_timing: id 3 | task 45 | prompt eval time = 980.70 ms / 146 tokens ( 6.72 ms per token, 148.87 tokens per second) 0.37.925.524 I slot print_timing: id 3 | task 45 | eval time = 40.01 ms / 2 tokens ( 40.01 ms per token, 24.99 tokens per second) 0.37.925.525 I slot print_timing: id 3 | task 45 | total time = 1020.72 ms / 148 tokens 0.37.925.525 I slot print_timing: id 3 | task 45 | graphs reused = 1 0.37.925.525 I slot print_timing: id 3 | task 45 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.925.539 I slot release: id 3 | task 45 | stop processing: n_tokens = 147, truncated = 0 0.37.929.199 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.212 (> 0.100 thold), f_keep = 0.261 0.37.929.441 I slot launch_slot_: id 0 | task 49 | processing task, is_child = 0 0.37.930.363 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.252 (> 0.100 thold), f_keep = 0.284 0.37.930.395 I slot launch_slot_: id 2 | task 50 | processing task, is_child = 0 0.37.930.429 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.282 (> 0.100 thold), f_keep = 0.234 0.37.930.456 I slot launch_slot_: id 1 | task 51 | processing task, is_child = 0 0.37.930.474 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.254 (> 0.100 thold), f_keep = 0.197 0.37.930.617 I slot launch_slot_: id 3 | task 52 | processing task, is_child = 0 0.39.024.688 I slot print_timing: id 0 | task 49 | prompt eval time = 1054.02 ms / 137 tokens ( 7.69 ms per token, 129.98 tokens per second) 0.39.024.691 I slot print_timing: id 0 | task 49 | eval time = 40.05 ms / 2 tokens ( 40.05 ms per token, 24.97 tokens per second) 0.39.024.691 I slot print_timing: id 0 | task 49 | total time = 1094.06 ms / 139 tokens 0.39.024.692 I slot print_timing: id 0 | task 49 | graphs reused = 1 0.39.024.692 I slot print_timing: id 0 | task 49 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.024.713 I slot release: id 0 | task 49 | stop processing: n_tokens = 138, truncated = 0 0.39.024.974 I slot print_timing: id 1 | task 51 | prompt eval time = 1054.27 ms / 103 tokens ( 10.24 ms per token, 97.70 tokens per second) 0.39.024.975 I slot print_timing: id 1 | task 51 | eval time = 40.07 ms / 2 tokens ( 40.07 ms per token, 24.95 tokens per second) 0.39.024.976 I slot print_timing: id 1 | task 51 | total time = 1094.34 ms / 105 tokens 0.39.024.976 I slot print_timing: id 1 | task 51 | graphs reused = 1 0.39.024.976 I slot print_timing: id 1 | task 51 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.024.990 I slot release: id 1 | task 51 | stop processing: n_tokens = 104, truncated = 0 0.39.025.267 I slot print_timing: id 2 | task 50 | prompt eval time = 1054.57 ms / 131 tokens ( 8.05 ms per token, 124.22 tokens per second) 0.39.025.269 I slot print_timing: id 2 | task 50 | eval time = 40.06 ms / 2 tokens ( 40.06 ms per token, 24.96 tokens per second) 0.39.025.269 I slot print_timing: id 2 | task 50 | total time = 1094.63 ms / 133 tokens 0.39.025.269 I slot print_timing: id 2 | task 50 | graphs reused = 1 0.39.025.270 I slot print_timing: id 2 | task 50 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.025.282 I slot release: id 2 | task 50 | stop processing: n_tokens = 132, truncated = 0 0.39.025.583 I slot print_timing: id 3 | task 52 | prompt eval time = 1054.90 ms / 114 tokens ( 9.25 ms per token, 108.07 tokens per second) 0.39.025.585 I slot print_timing: id 3 | task 52 | eval time = 40.03 ms / 2 tokens ( 40.03 ms per token, 24.98 tokens per second) 0.39.025.587 I slot print_timing: id 3 | task 52 | total time = 1094.93 ms / 116 tokens 0.39.025.588 I slot print_timing: id 3 | task 52 | graphs reused = 1 0.39.025.588 I slot print_timing: id 3 | task 52 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.025.598 I slot release: id 3 | task 52 | stop processing: n_tokens = 115, truncated = 0 0.39.029.888 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.163 (> 0.100 thold), f_keep = 0.210 0.39.030.352 I slot launch_slot_: id 0 | task 56 | processing task, is_child = 0 0.39.031.151 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.220 (> 0.100 thold), f_keep = 0.279 0.39.031.184 I slot launch_slot_: id 1 | task 57 | processing task, is_child = 0 0.39.031.216 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.156 (> 0.100 thold), f_keep = 0.220 0.39.031.360 I slot launch_slot_: id 2 | task 58 | processing task, is_child = 0 0.39.031.378 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.173 (> 0.100 thold), f_keep = 0.252 0.39.031.406 I slot launch_slot_: id 3 | task 59 | processing task, is_child = 0 0.40.346.311 I slot print_timing: id 0 | task 56 | prompt eval time = 1274.94 ms / 178 tokens ( 7.16 ms per token, 139.61 tokens per second) 0.40.346.314 I slot print_timing: id 0 | task 56 | eval time = 39.95 ms / 2 tokens ( 39.95 ms per token, 25.03 tokens per second) 0.40.346.314 I slot print_timing: id 0 | task 56 | total time = 1314.89 ms / 180 tokens 0.40.346.315 I slot print_timing: id 0 | task 56 | graphs reused = 1 0.40.346.315 I slot print_timing: id 0 | task 56 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.346.340 I slot release: id 0 | task 56 | stop processing: n_tokens = 179, truncated = 0 0.40.346.639 I slot print_timing: id 1 | task 57 | prompt eval time = 1275.23 ms / 132 tokens ( 9.66 ms per token, 103.51 tokens per second) 0.40.346.641 I slot print_timing: id 1 | task 57 | eval time = 39.98 ms / 2 tokens ( 39.98 ms per token, 25.01 tokens per second) 0.40.346.642 I slot print_timing: id 1 | task 57 | total time = 1315.22 ms / 134 tokens 0.40.346.642 I slot print_timing: id 1 | task 57 | graphs reused = 1 0.40.346.643 I slot print_timing: id 1 | task 57 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.346.656 I slot release: id 1 | task 57 | stop processing: n_tokens = 133, truncated = 0 0.40.346.947 I slot print_timing: id 2 | task 58 | prompt eval time = 1275.50 ms / 186 tokens ( 6.86 ms per token, 145.82 tokens per second) 0.40.346.949 I slot print_timing: id 2 | task 58 | eval time = 40.01 ms / 2 tokens ( 40.01 ms per token, 24.99 tokens per second) 0.40.346.950 I slot print_timing: id 2 | task 58 | total time = 1315.51 ms / 188 tokens 0.40.346.950 I slot print_timing: id 2 | task 58 | graphs reused = 1 0.40.346.950 I slot print_timing: id 2 | task 58 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.346.968 I slot release: id 2 | task 58 | stop processing: n_tokens = 187, truncated = 0 0.40.347.271 I slot print_timing: id 3 | task 59 | prompt eval time = 1275.81 ms / 168 tokens ( 7.59 ms per token, 131.68 tokens per second) 0.40.347.273 I slot print_timing: id 3 | task 59 | eval time = 40.02 ms / 2 tokens ( 40.02 ms per token, 24.99 tokens per second) 0.40.347.274 I slot print_timing: id 3 | task 59 | total time = 1315.83 ms / 170 tokens 0.40.347.274 I slot print_timing: id 3 | task 59 | graphs reused = 1 0.40.347.274 I slot print_timing: id 3 | task 59 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.347.286 I slot release: id 3 | task 59 | stop processing: n_tokens = 169, truncated = 0 0.40.351.161 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.193 (> 0.100 thold), f_keep = 0.162 0.40.351.694 I slot launch_slot_: id 0 | task 63 | processing task, is_child = 0 0.40.352.973 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 0.40.353.141 I slot launch_slot_: id 1 | task 64 | processing task, is_child = 0 0.40.353.180 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.173 (> 0.100 thold), f_keep = 0.155 0.40.353.231 I slot launch_slot_: id 2 | task 65 | processing task, is_child = 0 0.40.353.254 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.234 (> 0.100 thold), f_keep = 0.172 0.40.353.287 I slot launch_slot_: id 3 | task 66 | processing task, is_child = 0 0.41.519.514 I slot print_timing: id 0 | task 63 | prompt eval time = 1126.14 ms / 150 tokens ( 7.51 ms per token, 133.20 tokens per second) 0.41.519.517 I slot print_timing: id 0 | task 63 | eval time = 40.07 ms / 2 tokens ( 40.07 ms per token, 24.95 tokens per second) 0.41.519.517 I slot print_timing: id 0 | task 63 | total time = 1166.22 ms / 152 tokens 0.41.519.518 I slot print_timing: id 0 | task 63 | graphs reused = 1 0.41.519.518 I slot print_timing: id 0 | task 63 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.519.543 I slot release: id 0 | task 63 | stop processing: n_tokens = 151, truncated = 0 0.41.519.826 I slot print_timing: id 1 | task 64 | prompt eval time = 1126.41 ms / 141 tokens ( 7.99 ms per token, 125.18 tokens per second) 0.41.519.827 I slot print_timing: id 1 | task 64 | eval time = 40.10 ms / 2 tokens ( 40.10 ms per token, 24.94 tokens per second) 0.41.519.828 I slot print_timing: id 1 | task 64 | total time = 1166.51 ms / 143 tokens 0.41.519.828 I slot print_timing: id 1 | task 64 | graphs reused = 1 0.41.519.829 I slot print_timing: id 1 | task 64 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.519.845 I slot release: id 1 | task 64 | stop processing: n_tokens = 142, truncated = 0 0.41.520.120 I slot print_timing: id 2 | task 65 | prompt eval time = 1126.67 ms / 168 tokens ( 6.71 ms per token, 149.11 tokens per second) 0.41.520.122 I slot print_timing: id 2 | task 65 | eval time = 40.12 ms / 2 tokens ( 40.12 ms per token, 24.92 tokens per second) 0.41.520.122 I slot print_timing: id 2 | task 65 | total time = 1166.79 ms / 170 tokens 0.41.520.122 I slot print_timing: id 2 | task 65 | graphs reused = 1 0.41.520.123 I slot print_timing: id 2 | task 65 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.520.136 I slot release: id 2 | task 65 | stop processing: n_tokens = 169, truncated = 0 0.41.537.016 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.221 (> 0.100 thold), f_keep = 0.192 0.41.537.215 I slot launch_slot_: id 0 | task 71 | processing task, is_child = 0 0.41.538.027 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.270 (> 0.100 thold), f_keep = 0.211 0.41.538.067 I slot launch_slot_: id 1 | task 72 | processing task, is_child = 0 0.41.538.088 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.177 (> 0.100 thold), f_keep = 0.172 0.41.538.130 I slot launch_slot_: id 2 | task 73 | processing task, is_child = 0 0.42.334.647 I slot print_timing: id 3 | task 66 | prompt eval time = 1127.10 ms / 124 tokens ( 9.09 ms per token, 110.02 tokens per second) 0.42.334.649 I slot print_timing: id 3 | task 66 | eval time = 854.20 ms / 4 tokens ( 284.73 ms per token, 3.51 tokens per second) 0.42.334.649 I slot print_timing: id 3 | task 66 | total time = 1981.30 ms / 128 tokens 0.42.334.650 I slot print_timing: id 3 | task 66 | graphs reused = 2 0.42.334.650 I slot print_timing: id 3 | task 66 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.334.669 I slot release: id 3 | task 66 | stop processing: n_tokens = 127, truncated = 0 0.42.415.380 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.236 0.42.415.841 I slot launch_slot_: id 3 | task 76 | processing task, is_child = 0 0.42.748.644 I slot print_timing: id 0 | task 71 | prompt eval time = 876.66 ms / 131 tokens ( 6.69 ms per token, 149.43 tokens per second) 0.42.748.648 I slot print_timing: id 0 | task 71 | eval time = 333.85 ms / 2 tokens ( 333.85 ms per token, 3.00 tokens per second) 0.42.748.649 I slot print_timing: id 0 | task 71 | total time = 1210.51 ms / 133 tokens 0.42.748.649 I slot print_timing: id 0 | task 71 | graphs reused = 2 0.42.748.650 I slot print_timing: id 0 | task 71 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.748.667 I slot release: id 0 | task 71 | stop processing: n_tokens = 132, truncated = 0 0.42.748.945 I slot print_timing: id 1 | task 72 | prompt eval time = 876.92 ms / 111 tokens ( 7.90 ms per token, 126.58 tokens per second) 0.42.748.947 I slot print_timing: id 1 | task 72 | eval time = 333.86 ms / 2 tokens ( 333.86 ms per token, 3.00 tokens per second) 0.42.748.947 I slot print_timing: id 1 | task 72 | total time = 1210.79 ms / 113 tokens 0.42.748.947 I slot print_timing: id 1 | task 72 | graphs reused = 2 0.42.748.947 I slot print_timing: id 1 | task 72 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.748.963 I slot release: id 1 | task 72 | stop processing: n_tokens = 112, truncated = 0 0.42.749.246 I slot print_timing: id 2 | task 73 | prompt eval time = 877.20 ms / 164 tokens ( 5.35 ms per token, 186.96 tokens per second) 0.42.749.247 I slot print_timing: id 2 | task 73 | eval time = 333.87 ms / 2 tokens ( 333.87 ms per token, 3.00 tokens per second) 0.42.749.248 I slot print_timing: id 2 | task 73 | total time = 1211.07 ms / 166 tokens 0.42.749.248 I slot print_timing: id 2 | task 73 | graphs reused = 2 0.42.749.248 I slot print_timing: id 2 | task 73 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.749.266 I slot release: id 2 | task 73 | stop processing: n_tokens = 165, truncated = 0 0.42.783.559 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.220 0.42.783.944 I slot launch_slot_: id 0 | task 79 | processing task, is_child = 0 0.42.784.511 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.259 (> 0.100 thold), f_keep = 0.259 0.42.784.554 I slot launch_slot_: id 1 | task 80 | processing task, is_child = 0 0.42.784.576 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.181 (> 0.100 thold), f_keep = 0.182 0.42.784.611 I slot launch_slot_: id 2 | task 81 | processing task, is_child = 0 0.43.682.922 I slot print_timing: id 3 | task 76 | prompt eval time = 367.71 ms / 160 tokens ( 2.30 ms per token, 435.13 tokens per second) 0.43.682.927 I slot print_timing: id 3 | task 76 | eval time = 899.36 ms / 2 tokens ( 899.36 ms per token, 1.11 tokens per second) 0.43.682.927 I slot print_timing: id 3 | task 76 | total time = 1267.07 ms / 162 tokens 0.43.682.928 I slot print_timing: id 3 | task 76 | graphs reused = 2 0.43.682.928 I slot print_timing: id 3 | task 76 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.682.950 I slot release: id 3 | task 76 | stop processing: n_tokens = 161, truncated = 0 0.43.763.718 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.270 (> 0.100 thold), f_keep = 0.186 0.43.764.337 I slot launch_slot_: id 3 | task 84 | processing task, is_child = 0 0.44.060.369 I slot print_timing: id 0 | task 79 | prompt eval time = 978.44 ms / 166 tokens ( 5.89 ms per token, 169.66 tokens per second) 0.44.060.372 I slot print_timing: id 0 | task 79 | eval time = 297.31 ms / 2 tokens ( 297.31 ms per token, 3.36 tokens per second) 0.44.060.372 I slot print_timing: id 0 | task 79 | total time = 1275.75 ms / 168 tokens 0.44.060.373 I slot print_timing: id 0 | task 79 | graphs reused = 2 0.44.060.373 I slot print_timing: id 0 | task 79 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.060.394 I slot release: id 0 | task 79 | stop processing: n_tokens = 167, truncated = 0 0.44.060.685 I slot print_timing: id 1 | task 80 | prompt eval time = 978.70 ms / 112 tokens ( 8.74 ms per token, 114.44 tokens per second) 0.44.060.686 I slot print_timing: id 1 | task 80 | eval time = 297.35 ms / 2 tokens ( 297.35 ms per token, 3.36 tokens per second) 0.44.060.687 I slot print_timing: id 1 | task 80 | total time = 1276.05 ms / 114 tokens 0.44.060.687 I slot print_timing: id 1 | task 80 | graphs reused = 2 0.44.060.687 I slot print_timing: id 1 | task 80 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.060.701 I slot release: id 1 | task 80 | stop processing: n_tokens = 113, truncated = 0 0.44.061.006 I slot print_timing: id 2 | task 81 | prompt eval time = 979.07 ms / 166 tokens ( 5.90 ms per token, 169.55 tokens per second) 0.44.061.009 I slot print_timing: id 2 | task 81 | eval time = 297.29 ms / 2 tokens ( 297.29 ms per token, 3.36 tokens per second) 0.44.061.009 I slot print_timing: id 2 | task 81 | total time = 1276.36 ms / 168 tokens 0.44.061.010 I slot print_timing: id 2 | task 81 | graphs reused = 2 0.44.061.010 I slot print_timing: id 2 | task 81 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.061.026 I slot release: id 2 | task 81 | stop processing: n_tokens = 167, truncated = 0 0.44.095.135 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.218 (> 0.100 thold), f_keep = 0.174 0.44.095.600 I slot launch_slot_: id 0 | task 87 | processing task, is_child = 0 0.44.096.335 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.200 (> 0.100 thold), f_keep = 0.257 0.44.096.382 I slot launch_slot_: id 1 | task 88 | processing task, is_child = 0 0.44.096.403 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.174 0.44.096.594 I slot launch_slot_: id 2 | task 89 | processing task, is_child = 0 0.44.754.350 I slot print_timing: id 3 | task 84 | prompt eval time = 330.79 ms / 111 tokens ( 2.98 ms per token, 335.56 tokens per second) 0.44.754.353 I slot print_timing: id 3 | task 84 | eval time = 659.22 ms / 2 tokens ( 659.22 ms per token, 1.52 tokens per second) 0.44.754.353 I slot print_timing: id 3 | task 84 | total time = 990.00 ms / 113 tokens 0.44.754.354 I slot print_timing: id 3 | task 84 | graphs reused = 2 0.44.754.354 I slot print_timing: id 3 | task 84 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.754.372 I slot release: id 3 | task 84 | stop processing: n_tokens = 112, truncated = 0 0.44.835.424 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.238 (> 0.100 thold), f_keep = 0.259 0.44.835.754 I slot launch_slot_: id 3 | task 92 | processing task, is_child = 0 0.45.139.640 I slot print_timing: id 0 | task 87 | prompt eval time = 738.16 ms / 133 tokens ( 5.55 ms per token, 180.18 tokens per second) 0.45.139.645 I slot print_timing: id 0 | task 87 | eval time = 304.88 ms / 2 tokens ( 304.88 ms per token, 3.28 tokens per second) 0.45.139.645 I slot print_timing: id 0 | task 87 | total time = 1043.04 ms / 135 tokens 0.45.139.646 I slot print_timing: id 0 | task 87 | graphs reused = 2 0.45.139.646 I slot print_timing: id 0 | task 87 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.139.667 I slot release: id 0 | task 87 | stop processing: n_tokens = 134, truncated = 0 0.45.139.929 I slot print_timing: id 1 | task 88 | prompt eval time = 738.48 ms / 145 tokens ( 5.09 ms per token, 196.35 tokens per second) 0.45.139.931 I slot print_timing: id 1 | task 88 | eval time = 304.83 ms / 2 tokens ( 304.83 ms per token, 3.28 tokens per second) 0.45.139.932 I slot print_timing: id 1 | task 88 | total time = 1043.31 ms / 147 tokens 0.45.139.932 I slot print_timing: id 1 | task 88 | graphs reused = 2 0.45.139.932 I slot print_timing: id 1 | task 88 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.139.945 I slot release: id 1 | task 88 | stop processing: n_tokens = 146, truncated = 0 0.45.140.237 I slot print_timing: id 2 | task 89 | prompt eval time = 738.79 ms / 127 tokens ( 5.82 ms per token, 171.90 tokens per second) 0.45.140.239 I slot print_timing: id 2 | task 89 | eval time = 304.82 ms / 2 tokens ( 304.82 ms per token, 3.28 tokens per second) 0.45.140.240 I slot print_timing: id 2 | task 89 | total time = 1043.61 ms / 129 tokens 0.45.140.240 I slot print_timing: id 2 | task 89 | graphs reused = 2 0.45.140.241 I slot print_timing: id 2 | task 89 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.140.252 I slot release: id 2 | task 89 | stop processing: n_tokens = 128, truncated = 0 0.45.174.121 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.205 (> 0.100 thold), f_keep = 0.234 0.45.174.510 I slot launch_slot_: id 2 | task 95 | processing task, is_child = 0 0.45.175.261 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.207 (> 0.100 thold), f_keep = 0.216 0.45.175.437 I slot launch_slot_: id 0 | task 96 | processing task, is_child = 0 0.45.175.468 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.199 0.45.175.502 I slot launch_slot_: id 1 | task 97 | processing task, is_child = 0 0.45.881.491 I slot print_timing: id 3 | task 92 | prompt eval time = 338.36 ms / 122 tokens ( 2.77 ms per token, 360.56 tokens per second) 0.45.881.497 I slot print_timing: id 3 | task 92 | eval time = 707.37 ms / 2 tokens ( 707.37 ms per token, 1.41 tokens per second) 0.45.881.497 I slot print_timing: id 3 | task 92 | total time = 1045.73 ms / 124 tokens 0.45.881.498 I slot print_timing: id 3 | task 92 | graphs reused = 2 0.45.881.498 I slot print_timing: id 3 | task 92 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.881.523 I slot release: id 3 | task 92 | stop processing: n_tokens = 123, truncated = 0 0.45.962.447 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.218 (> 0.100 thold), f_keep = 0.236 0.45.963.229 I slot launch_slot_: id 3 | task 100 | processing task, is_child = 0 0.46.271.765 I slot print_timing: id 0 | task 96 | prompt eval time = 786.28 ms / 140 tokens ( 5.62 ms per token, 178.05 tokens per second) 0.46.271.770 I slot print_timing: id 0 | task 96 | eval time = 309.98 ms / 2 tokens ( 309.98 ms per token, 3.23 tokens per second) 0.46.271.771 I slot print_timing: id 0 | task 96 | total time = 1096.26 ms / 142 tokens 0.46.271.771 I slot print_timing: id 0 | task 96 | graphs reused = 2 0.46.271.772 I slot print_timing: id 0 | task 96 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.271.790 I slot release: id 0 | task 96 | stop processing: n_tokens = 141, truncated = 0 0.46.272.068 I slot print_timing: id 1 | task 97 | prompt eval time = 786.53 ms / 126 tokens ( 6.24 ms per token, 160.20 tokens per second) 0.46.272.070 I slot print_timing: id 1 | task 97 | eval time = 310.01 ms / 2 tokens ( 310.01 ms per token, 3.23 tokens per second) 0.46.272.070 I slot print_timing: id 1 | task 97 | total time = 1096.55 ms / 128 tokens 0.46.272.071 I slot print_timing: id 1 | task 97 | graphs reused = 2 0.46.272.071 I slot print_timing: id 1 | task 97 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.272.083 I slot release: id 1 | task 97 | stop processing: n_tokens = 127, truncated = 0 0.46.272.373 I slot print_timing: id 2 | task 95 | prompt eval time = 786.91 ms / 146 tokens ( 5.39 ms per token, 185.54 tokens per second) 0.46.272.375 I slot print_timing: id 2 | task 95 | eval time = 309.93 ms / 2 tokens ( 309.93 ms per token, 3.23 tokens per second) 0.46.272.375 I slot print_timing: id 2 | task 95 | total time = 1096.84 ms / 148 tokens 0.46.272.376 I slot print_timing: id 2 | task 95 | graphs reused = 2 0.46.272.376 I slot print_timing: id 2 | task 95 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.272.395 I slot release: id 2 | task 95 | stop processing: n_tokens = 147, truncated = 0 0.46.306.696 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.250 (> 0.100 thold), f_keep = 0.204 0.46.307.096 I slot launch_slot_: id 2 | task 103 | processing task, is_child = 0 0.46.307.636 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.236 (> 0.100 thold), f_keep = 0.206 0.46.307.675 I slot launch_slot_: id 0 | task 104 | processing task, is_child = 0 0.46.307.699 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.264 (> 0.100 thold), f_keep = 0.228 0.46.307.861 I slot launch_slot_: id 1 | task 105 | processing task, is_child = 0 0.46.918.291 I slot print_timing: id 3 | task 100 | prompt eval time = 343.46 ms / 133 tokens ( 2.58 ms per token, 387.24 tokens per second) 0.46.918.293 I slot print_timing: id 3 | task 100 | eval time = 611.60 ms / 2 tokens ( 611.60 ms per token, 1.64 tokens per second) 0.46.918.294 I slot print_timing: id 3 | task 100 | total time = 955.05 ms / 135 tokens 0.46.918.294 I slot print_timing: id 3 | task 100 | graphs reused = 2 0.46.918.295 I slot print_timing: id 3 | task 100 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.918.315 I slot release: id 3 | task 100 | stop processing: n_tokens = 134, truncated = 0 0.46.999.042 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.170 (> 0.100 thold), f_keep = 0.216 0.46.999.695 I slot launch_slot_: id 3 | task 108 | processing task, is_child = 0 0.47.350.409 I slot print_timing: id 0 | task 104 | prompt eval time = 690.56 ms / 123 tokens ( 5.61 ms per token, 178.12 tokens per second) 0.47.350.412 I slot print_timing: id 0 | task 104 | eval time = 351.98 ms / 2 tokens ( 351.98 ms per token, 2.84 tokens per second) 0.47.350.412 I slot print_timing: id 0 | task 104 | total time = 1042.54 ms / 125 tokens 0.47.350.413 I slot print_timing: id 0 | task 104 | graphs reused = 2 0.47.350.413 I slot print_timing: id 0 | task 104 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.350.437 I slot release: id 0 | task 104 | stop processing: n_tokens = 124, truncated = 0 0.47.350.712 I slot print_timing: id 1 | task 105 | prompt eval time = 690.82 ms / 110 tokens ( 6.28 ms per token, 159.23 tokens per second) 0.47.350.716 I slot print_timing: id 1 | task 105 | eval time = 352.00 ms / 2 tokens ( 352.00 ms per token, 2.84 tokens per second) 0.47.350.717 I slot print_timing: id 1 | task 105 | total time = 1042.83 ms / 112 tokens 0.47.350.717 I slot print_timing: id 1 | task 105 | graphs reused = 2 0.47.350.717 I slot print_timing: id 1 | task 105 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.350.730 I slot release: id 1 | task 105 | stop processing: n_tokens = 111, truncated = 0 0.47.351.013 I slot print_timing: id 2 | task 103 | prompt eval time = 691.13 ms / 120 tokens ( 5.76 ms per token, 173.63 tokens per second) 0.47.351.015 I slot print_timing: id 2 | task 103 | eval time = 351.98 ms / 2 tokens ( 351.98 ms per token, 2.84 tokens per second) 0.47.351.015 I slot print_timing: id 2 | task 103 | total time = 1043.11 ms / 122 tokens 0.47.351.015 I slot print_timing: id 2 | task 103 | graphs reused = 2 0.47.351.015 I slot print_timing: id 2 | task 103 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.351.028 I slot release: id 2 | task 103 | stop processing: n_tokens = 121, truncated = 0 0.47.385.155 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.217 (> 0.100 thold), f_keep = 0.270 0.47.385.400 I slot launch_slot_: id 1 | task 111 | processing task, is_child = 0 0.47.386.094 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.125 (> 0.100 thold), f_keep = 0.234 0.47.386.131 I slot launch_slot_: id 0 | task 112 | processing task, is_child = 0 0.47.386.159 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.256 (> 0.100 thold), f_keep = 0.248 0.47.386.206 I slot launch_slot_: id 2 | task 113 | processing task, is_child = 0 0.48.316.009 I slot print_timing: id 3 | task 108 | prompt eval time = 385.44 ms / 171 tokens ( 2.25 ms per token, 443.64 tokens per second) 0.48.316.011 I slot print_timing: id 3 | task 108 | eval time = 930.85 ms / 2 tokens ( 930.85 ms per token, 1.07 tokens per second) 0.48.316.012 I slot print_timing: id 3 | task 108 | total time = 1316.30 ms / 173 tokens 0.48.316.012 I slot print_timing: id 3 | task 108 | graphs reused = 2 0.48.316.013 I slot print_timing: id 3 | task 108 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.316.039 I slot release: id 3 | task 108 | stop processing: n_tokens = 172, truncated = 0 0.48.396.512 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.165 (> 0.100 thold), f_keep = 0.169 0.48.397.015 I slot launch_slot_: id 3 | task 116 | processing task, is_child = 0 0.48.749.235 I slot print_timing: id 0 | task 112 | prompt eval time = 1009.64 ms / 232 tokens ( 4.35 ms per token, 229.79 tokens per second) 0.48.749.239 I slot print_timing: id 0 | task 112 | eval time = 353.39 ms / 2 tokens ( 353.39 ms per token, 2.83 tokens per second) 0.48.749.240 I slot print_timing: id 0 | task 112 | total time = 1363.02 ms / 234 tokens 0.48.749.240 I slot print_timing: id 0 | task 112 | graphs reused = 2 0.48.749.241 I slot print_timing: id 0 | task 112 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.749.267 I slot release: id 0 | task 112 | stop processing: n_tokens = 233, truncated = 0 0.48.749.536 I slot print_timing: id 1 | task 111 | prompt eval time = 1009.89 ms / 138 tokens ( 7.32 ms per token, 136.65 tokens per second) 0.48.749.539 I slot print_timing: id 1 | task 111 | eval time = 353.42 ms / 2 tokens ( 353.42 ms per token, 2.83 tokens per second) 0.48.749.540 I slot print_timing: id 1 | task 111 | total time = 1363.31 ms / 140 tokens 0.48.749.540 I slot print_timing: id 1 | task 111 | graphs reused = 2 0.48.749.540 I slot print_timing: id 1 | task 111 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.749.553 I slot release: id 1 | task 111 | stop processing: n_tokens = 139, truncated = 0 0.48.749.820 I slot print_timing: id 2 | task 113 | prompt eval time = 1010.27 ms / 117 tokens ( 8.63 ms per token, 115.81 tokens per second) 0.48.749.822 I slot print_timing: id 2 | task 113 | eval time = 353.31 ms / 2 tokens ( 353.31 ms per token, 2.83 tokens per second) 0.48.749.822 I slot print_timing: id 2 | task 113 | total time = 1363.58 ms / 119 tokens 0.48.749.822 I slot print_timing: id 2 | task 113 | graphs reused = 2 0.48.749.823 I slot print_timing: id 2 | task 113 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.749.836 I slot release: id 2 | task 113 | stop processing: n_tokens = 118, truncated = 0 0.48.784.222 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.263 0.48.784.587 I slot launch_slot_: id 2 | task 119 | processing task, is_child = 0 0.48.785.483 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.184 (> 0.100 thold), f_keep = 0.124 0.48.785.524 I slot launch_slot_: id 0 | task 120 | processing task, is_child = 0 0.48.785.545 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.210 (> 0.100 thold), f_keep = 0.216 0.48.785.737 I slot launch_slot_: id 1 | task 121 | processing task, is_child = 0 0.49.520.918 I slot print_timing: id 3 | task 116 | prompt eval time = 387.20 ms / 176 tokens ( 2.20 ms per token, 454.55 tokens per second) 0.49.520.920 I slot print_timing: id 3 | task 116 | eval time = 736.70 ms / 2 tokens ( 736.70 ms per token, 1.36 tokens per second) 0.49.520.920 I slot print_timing: id 3 | task 116 | total time = 1123.89 ms / 178 tokens 0.49.520.921 I slot print_timing: id 3 | task 116 | graphs reused = 2 0.49.520.921 I slot print_timing: id 3 | task 116 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.520.947 I slot release: id 3 | task 116 | stop processing: n_tokens = 177, truncated = 0 0.49.602.110 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.128 (> 0.100 thold), f_keep = 0.164 0.49.602.950 I slot launch_slot_: id 3 | task 124 | processing task, is_child = 0 0.49.996.138 I slot print_timing: id 0 | task 120 | prompt eval time = 815.67 ms / 158 tokens ( 5.16 ms per token, 193.71 tokens per second) 0.49.996.142 I slot print_timing: id 0 | task 120 | eval time = 394.72 ms / 2 tokens ( 394.72 ms per token, 2.53 tokens per second) 0.49.996.142 I slot print_timing: id 0 | task 120 | total time = 1210.39 ms / 160 tokens 0.49.996.142 I slot print_timing: id 0 | task 120 | graphs reused = 2 0.49.996.143 I slot print_timing: id 0 | task 120 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.996.163 I slot release: id 0 | task 120 | stop processing: n_tokens = 159, truncated = 0 0.49.996.466 I slot print_timing: id 1 | task 121 | prompt eval time = 815.94 ms / 143 tokens ( 5.71 ms per token, 175.26 tokens per second) 0.49.996.469 I slot print_timing: id 1 | task 121 | eval time = 394.77 ms / 2 tokens ( 394.77 ms per token, 2.53 tokens per second) 0.49.996.469 I slot print_timing: id 1 | task 121 | total time = 1210.70 ms / 145 tokens 0.49.996.469 I slot print_timing: id 1 | task 121 | graphs reused = 2 0.49.996.470 I slot print_timing: id 1 | task 121 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.996.483 I slot release: id 1 | task 121 | stop processing: n_tokens = 144, truncated = 0 0.49.996.886 I slot print_timing: id 2 | task 119 | prompt eval time = 816.33 ms / 156 tokens ( 5.23 ms per token, 191.10 tokens per second) 0.49.996.888 I slot print_timing: id 2 | task 119 | eval time = 394.78 ms / 2 tokens ( 394.78 ms per token, 2.53 tokens per second) 0.49.996.889 I slot print_timing: id 2 | task 119 | total time = 1211.11 ms / 158 tokens 0.49.996.889 I slot print_timing: id 2 | task 119 | graphs reused = 2 0.49.996.889 I slot print_timing: id 2 | task 119 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.996.911 I slot release: id 2 | task 119 | stop processing: n_tokens = 157, truncated = 0 0.50.031.151 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.299 (> 0.100 thold), f_keep = 0.222 0.50.031.588 I slot launch_slot_: id 1 | task 127 | processing task, is_child = 0 0.50.032.430 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.256 (> 0.100 thold), f_keep = 0.191 0.50.032.471 I slot launch_slot_: id 2 | task 128 | processing task, is_child = 0 0.50.032.502 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.153 (> 0.100 thold), f_keep = 0.182 0.50.032.670 I slot launch_slot_: id 0 | task 129 | processing task, is_child = 0 0.50.799.471 I slot print_timing: id 3 | task 124 | prompt eval time = 428.19 ms / 227 tokens ( 1.89 ms per token, 530.14 tokens per second) 0.50.799.474 I slot print_timing: id 3 | task 124 | eval time = 768.32 ms / 2 tokens ( 768.32 ms per token, 1.30 tokens per second) 0.50.799.474 I slot print_timing: id 3 | task 124 | total time = 1196.51 ms / 229 tokens 0.50.799.474 I slot print_timing: id 3 | task 124 | graphs reused = 2 0.50.799.475 I slot print_timing: id 3 | task 124 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.799.501 I slot release: id 3 | task 124 | stop processing: n_tokens = 228, truncated = 0 0.50.880.516 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.203 (> 0.100 thold), f_keep = 0.127 0.50.881.467 I slot launch_slot_: id 3 | task 132 | processing task, is_child = 0 0.51.204.535 I slot print_timing: id 0 | task 129 | prompt eval time = 847.18 ms / 189 tokens ( 4.48 ms per token, 223.09 tokens per second) 0.51.204.539 I slot print_timing: id 0 | task 129 | eval time = 324.67 ms / 2 tokens ( 324.67 ms per token, 3.08 tokens per second) 0.51.204.539 I slot print_timing: id 0 | task 129 | total time = 1171.86 ms / 191 tokens 0.51.204.539 I slot print_timing: id 0 | task 129 | graphs reused = 2 0.51.204.540 I slot print_timing: id 0 | task 129 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.204.561 I slot release: id 0 | task 129 | stop processing: n_tokens = 190, truncated = 0 0.51.204.829 I slot print_timing: id 1 | task 127 | prompt eval time = 847.44 ms / 107 tokens ( 7.92 ms per token, 126.26 tokens per second) 0.51.204.832 I slot print_timing: id 1 | task 127 | eval time = 324.70 ms / 2 tokens ( 324.70 ms per token, 3.08 tokens per second) 0.51.204.832 I slot print_timing: id 1 | task 127 | total time = 1172.14 ms / 109 tokens 0.51.204.832 I slot print_timing: id 1 | task 127 | graphs reused = 2 0.51.204.833 I slot print_timing: id 1 | task 127 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.204.844 I slot release: id 1 | task 127 | stop processing: n_tokens = 108, truncated = 0 0.51.205.146 I slot print_timing: id 2 | task 128 | prompt eval time = 847.80 ms / 117 tokens ( 7.25 ms per token, 138.00 tokens per second) 0.51.205.148 I slot print_timing: id 2 | task 128 | eval time = 324.64 ms / 2 tokens ( 324.64 ms per token, 3.08 tokens per second) 0.51.205.148 I slot print_timing: id 2 | task 128 | total time = 1172.44 ms / 119 tokens 0.51.205.148 I slot print_timing: id 2 | task 128 | graphs reused = 2 0.51.205.149 I slot print_timing: id 2 | task 128 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.205.172 I slot release: id 2 | task 128 | stop processing: n_tokens = 118, truncated = 0 0.51.239.390 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.210 (> 0.100 thold), f_keep = 0.153 0.51.239.842 I slot launch_slot_: id 0 | task 135 | processing task, is_child = 0 0.51.240.185 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.168 (> 0.100 thold), f_keep = 0.269 0.51.240.222 I slot launch_slot_: id 1 | task 136 | processing task, is_child = 0 0.51.240.246 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.244 (> 0.100 thold), f_keep = 0.254 0.51.240.274 I slot launch_slot_: id 2 | task 137 | processing task, is_child = 0 0.52.084.734 I slot print_timing: id 3 | task 132 | prompt eval time = 357.91 ms / 143 tokens ( 2.50 ms per token, 399.54 tokens per second) 0.52.084.738 I slot print_timing: id 3 | task 132 | eval time = 845.34 ms / 2 tokens ( 845.34 ms per token, 1.18 tokens per second) 0.52.084.739 I slot print_timing: id 3 | task 132 | total time = 1203.26 ms / 145 tokens 0.52.084.739 I slot print_timing: id 3 | task 132 | graphs reused = 2 0.52.084.739 I slot print_timing: id 3 | task 132 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.084.760 I slot release: id 3 | task 132 | stop processing: n_tokens = 144, truncated = 0 0.52.165.802 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.264 (> 0.100 thold), f_keep = 0.201 0.52.166.722 I slot launch_slot_: id 3 | task 140 | processing task, is_child = 0 0.52.461.735 I slot print_timing: id 0 | task 135 | prompt eval time = 924.85 ms / 138 tokens ( 6.70 ms per token, 149.21 tokens per second) 0.52.461.737 I slot print_timing: id 0 | task 135 | eval time = 296.60 ms / 2 tokens ( 296.60 ms per token, 3.37 tokens per second) 0.52.461.738 I slot print_timing: id 0 | task 135 | total time = 1221.45 ms / 140 tokens 0.52.461.738 I slot print_timing: id 0 | task 135 | graphs reused = 2 0.52.461.739 I slot print_timing: id 0 | task 135 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.461.761 I slot release: id 0 | task 135 | stop processing: n_tokens = 139, truncated = 0 0.52.462.056 I slot print_timing: id 1 | task 136 | prompt eval time = 925.11 ms / 173 tokens ( 5.35 ms per token, 187.01 tokens per second) 0.52.462.058 I slot print_timing: id 1 | task 136 | eval time = 296.64 ms / 2 tokens ( 296.64 ms per token, 3.37 tokens per second) 0.52.462.058 I slot print_timing: id 1 | task 136 | total time = 1221.75 ms / 175 tokens 0.52.462.059 I slot print_timing: id 1 | task 136 | graphs reused = 2 0.52.462.059 I slot print_timing: id 1 | task 136 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.462.075 I slot release: id 1 | task 136 | stop processing: n_tokens = 174, truncated = 0 0.52.462.362 I slot print_timing: id 2 | task 137 | prompt eval time = 925.48 ms / 123 tokens ( 7.52 ms per token, 132.90 tokens per second) 0.52.462.364 I slot print_timing: id 2 | task 137 | eval time = 296.56 ms / 2 tokens ( 296.56 ms per token, 3.37 tokens per second) 0.52.462.365 I slot print_timing: id 2 | task 137 | total time = 1222.05 ms / 125 tokens 0.52.462.365 I slot print_timing: id 2 | task 137 | graphs reused = 2 0.52.462.365 I slot print_timing: id 2 | task 137 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.462.379 I slot release: id 2 | task 137 | stop processing: n_tokens = 124, truncated = 0 0.52.496.452 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.180 (> 0.100 thold), f_keep = 0.209 0.52.496.827 I slot launch_slot_: id 0 | task 143 | processing task, is_child = 0 0.52.497.649 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.213 (> 0.100 thold), f_keep = 0.167 0.52.497.693 I slot launch_slot_: id 1 | task 144 | processing task, is_child = 0 0.52.497.714 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.216 (> 0.100 thold), f_keep = 0.234 0.52.497.743 I slot launch_slot_: id 2 | task 145 | processing task, is_child = 0 0.53.224.808 I slot print_timing: id 3 | task 140 | prompt eval time = 329.72 ms / 110 tokens ( 3.00 ms per token, 333.62 tokens per second) 0.53.224.810 I slot print_timing: id 3 | task 140 | eval time = 728.36 ms / 2 tokens ( 728.36 ms per token, 1.37 tokens per second) 0.53.224.810 I slot print_timing: id 3 | task 140 | total time = 1058.08 ms / 112 tokens 0.53.224.810 I slot print_timing: id 3 | task 140 | graphs reused = 2 0.53.224.811 I slot print_timing: id 3 | task 140 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.224.826 I slot release: id 3 | task 140 | stop processing: n_tokens = 111, truncated = 0 0.53.305.540 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.246 (> 0.100 thold), f_keep = 0.270 0.53.306.041 I slot launch_slot_: id 3 | task 148 | processing task, is_child = 0 0.53.606.237 I slot print_timing: id 0 | task 143 | prompt eval time = 807.20 ms / 161 tokens ( 5.01 ms per token, 199.45 tokens per second) 0.53.606.238 I slot print_timing: id 0 | task 143 | eval time = 301.28 ms / 2 tokens ( 301.28 ms per token, 3.32 tokens per second) 0.53.606.239 I slot print_timing: id 0 | task 143 | total time = 1108.48 ms / 163 tokens 0.53.606.239 I slot print_timing: id 0 | task 143 | graphs reused = 2 0.53.606.240 I slot print_timing: id 0 | task 143 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.606.264 I slot release: id 0 | task 143 | stop processing: n_tokens = 162, truncated = 0 0.53.606.550 I slot print_timing: id 1 | task 144 | prompt eval time = 807.46 ms / 136 tokens ( 5.94 ms per token, 168.43 tokens per second) 0.53.606.552 I slot print_timing: id 1 | task 144 | eval time = 301.32 ms / 2 tokens ( 301.32 ms per token, 3.32 tokens per second) 0.53.606.553 I slot print_timing: id 1 | task 144 | total time = 1108.78 ms / 138 tokens 0.53.606.553 I slot print_timing: id 1 | task 144 | graphs reused = 2 0.53.606.553 I slot print_timing: id 1 | task 144 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.606.568 I slot release: id 1 | task 144 | stop processing: n_tokens = 137, truncated = 0 0.53.606.889 I slot print_timing: id 2 | task 145 | prompt eval time = 807.75 ms / 134 tokens ( 6.03 ms per token, 165.89 tokens per second) 0.53.606.891 I slot print_timing: id 2 | task 145 | eval time = 301.35 ms / 2 tokens ( 301.35 ms per token, 3.32 tokens per second) 0.53.606.891 I slot print_timing: id 2 | task 145 | total time = 1109.10 ms / 136 tokens 0.53.606.891 I slot print_timing: id 2 | task 145 | graphs reused = 2 0.53.606.892 I slot print_timing: id 2 | task 145 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.606.911 I slot release: id 2 | task 145 | stop processing: n_tokens = 135, truncated = 0 0.53.641.470 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.221 (> 0.100 thold), f_keep = 0.179 0.53.641.897 I slot launch_slot_: id 0 | task 151 | processing task, is_child = 0 0.53.642.603 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.160 (> 0.100 thold), f_keep = 0.212 0.53.642.640 I slot launch_slot_: id 1 | task 152 | processing task, is_child = 0 0.53.642.666 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.166 (> 0.100 thold), f_keep = 0.215 0.53.642.714 I slot launch_slot_: id 2 | task 153 | processing task, is_child = 0 0.54.447.077 I slot print_timing: id 3 | task 148 | prompt eval time = 335.42 ms / 122 tokens ( 2.75 ms per token, 363.73 tokens per second) 0.54.447.079 I slot print_timing: id 3 | task 148 | eval time = 805.61 ms / 2 tokens ( 805.61 ms per token, 1.24 tokens per second) 0.54.447.079 I slot print_timing: id 3 | task 148 | total time = 1141.02 ms / 124 tokens 0.54.447.080 I slot print_timing: id 3 | task 148 | graphs reused = 2 0.54.447.080 I slot print_timing: id 3 | task 148 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.447.102 I slot release: id 3 | task 148 | stop processing: n_tokens = 123, truncated = 0 0.54.528.211 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.170 (> 0.100 thold), f_keep = 0.236 0.54.528.812 I slot launch_slot_: id 3 | task 156 | processing task, is_child = 0 0.54.879.145 I slot print_timing: id 0 | task 151 | prompt eval time = 884.82 ms / 131 tokens ( 6.75 ms per token, 148.05 tokens per second) 0.54.879.150 I slot print_timing: id 0 | task 151 | eval time = 351.60 ms / 2 tokens ( 351.60 ms per token, 2.84 tokens per second) 0.54.879.151 I slot print_timing: id 0 | task 151 | total time = 1236.42 ms / 133 tokens 0.54.879.151 I slot print_timing: id 0 | task 151 | graphs reused = 2 0.54.879.152 I slot print_timing: id 0 | task 151 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.879.170 I slot release: id 0 | task 151 | stop processing: n_tokens = 132, truncated = 0 0.54.879.444 I slot print_timing: id 1 | task 152 | prompt eval time = 885.08 ms / 181 tokens ( 4.89 ms per token, 204.50 tokens per second) 0.54.879.446 I slot print_timing: id 1 | task 152 | eval time = 351.63 ms / 2 tokens ( 351.63 ms per token, 2.84 tokens per second) 0.54.879.447 I slot print_timing: id 1 | task 152 | total time = 1236.71 ms / 183 tokens 0.54.879.447 I slot print_timing: id 1 | task 152 | graphs reused = 2 0.54.879.447 I slot print_timing: id 1 | task 152 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.879.468 I slot release: id 1 | task 152 | stop processing: n_tokens = 182, truncated = 0 0.54.879.751 I slot print_timing: id 2 | task 153 | prompt eval time = 885.45 ms / 175 tokens ( 5.06 ms per token, 197.64 tokens per second) 0.54.879.753 I slot print_timing: id 2 | task 153 | eval time = 351.55 ms / 2 tokens ( 351.55 ms per token, 2.84 tokens per second) 0.54.879.754 I slot print_timing: id 2 | task 153 | total time = 1237.00 ms / 177 tokens 0.54.879.754 I slot print_timing: id 2 | task 153 | graphs reused = 2 0.54.879.754 I slot print_timing: id 2 | task 153 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.879.773 I slot release: id 2 | task 153 | stop processing: n_tokens = 176, truncated = 0 0.54.913.977 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.236 (> 0.100 thold), f_keep = 0.220 0.54.914.474 I slot launch_slot_: id 0 | task 159 | processing task, is_child = 0 0.54.915.401 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.232 (> 0.100 thold), f_keep = 0.159 0.54.915.445 I slot launch_slot_: id 1 | task 160 | processing task, is_child = 0 0.54.915.467 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.252 (> 0.100 thold), f_keep = 0.165 0.54.915.506 I slot launch_slot_: id 2 | task 161 | processing task, is_child = 0 0.55.511.551 I slot print_timing: id 3 | task 156 | prompt eval time = 385.15 ms / 171 tokens ( 2.25 ms per token, 443.98 tokens per second) 0.55.511.553 I slot print_timing: id 3 | task 156 | eval time = 597.57 ms / 2 tokens ( 597.57 ms per token, 1.67 tokens per second) 0.55.511.553 I slot print_timing: id 3 | task 156 | total time = 982.73 ms / 173 tokens 0.55.511.554 I slot print_timing: id 3 | task 156 | graphs reused = 2 0.55.511.554 I slot print_timing: id 3 | task 156 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.511.579 I slot release: id 3 | task 156 | stop processing: n_tokens = 172, truncated = 0 0.55.592.416 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.250 (> 0.100 thold), f_keep = 0.169 0.55.593.404 I slot launch_slot_: id 3 | task 164 | processing task, is_child = 0 0.55.890.114 I slot print_timing: id 0 | task 159 | prompt eval time = 676.28 ms / 123 tokens ( 5.50 ms per token, 181.88 tokens per second) 0.55.890.119 I slot print_timing: id 0 | task 159 | eval time = 298.32 ms / 2 tokens ( 298.32 ms per token, 3.35 tokens per second) 0.55.890.120 I slot print_timing: id 0 | task 159 | total time = 974.60 ms / 125 tokens 0.55.890.120 I slot print_timing: id 0 | task 159 | graphs reused = 2 0.55.890.120 I slot print_timing: id 0 | task 159 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.890.139 I slot release: id 0 | task 159 | stop processing: n_tokens = 124, truncated = 0 0.55.890.398 I slot print_timing: id 1 | task 160 | prompt eval time = 676.53 ms / 125 tokens ( 5.41 ms per token, 184.77 tokens per second) 0.55.890.400 I slot print_timing: id 1 | task 160 | eval time = 298.35 ms / 2 tokens ( 298.35 ms per token, 3.35 tokens per second) 0.55.890.401 I slot print_timing: id 1 | task 160 | total time = 974.88 ms / 127 tokens 0.55.890.401 I slot print_timing: id 1 | task 160 | graphs reused = 2 0.55.890.402 I slot print_timing: id 1 | task 160 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.890.414 I slot release: id 1 | task 160 | stop processing: n_tokens = 126, truncated = 0 0.55.890.705 I slot print_timing: id 2 | task 161 | prompt eval time = 676.87 ms / 115 tokens ( 5.89 ms per token, 169.90 tokens per second) 0.55.890.706 I slot print_timing: id 2 | task 161 | eval time = 298.29 ms / 2 tokens ( 298.29 ms per token, 3.35 tokens per second) 0.55.890.707 I slot print_timing: id 2 | task 161 | total time = 975.16 ms / 117 tokens 0.55.890.707 I slot print_timing: id 2 | task 161 | graphs reused = 2 0.55.890.708 I slot print_timing: id 2 | task 161 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.890.718 I slot release: id 2 | task 161 | stop processing: n_tokens = 116, truncated = 0 0.55.925.059 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.223 (> 0.100 thold), f_keep = 0.234 0.55.925.543 I slot launch_slot_: id 0 | task 167 | processing task, is_child = 0 0.55.926.089 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.203 (> 0.100 thold), f_keep = 0.230 0.55.926.124 I slot launch_slot_: id 1 | task 168 | processing task, is_child = 0 0.55.926.144 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.225 (> 0.100 thold), f_keep = 0.250 0.55.926.293 I slot launch_slot_: id 2 | task 169 | processing task, is_child = 0 0.56.542.697 I slot print_timing: id 3 | task 164 | prompt eval time = 331.64 ms / 116 tokens ( 2.86 ms per token, 349.77 tokens per second) 0.56.542.700 I slot print_timing: id 3 | task 164 | eval time = 617.64 ms / 2 tokens ( 617.64 ms per token, 1.62 tokens per second) 0.56.542.700 I slot print_timing: id 3 | task 164 | total time = 949.28 ms / 118 tokens 0.56.542.701 I slot print_timing: id 3 | task 164 | graphs reused = 2 0.56.542.701 I slot print_timing: id 3 | task 164 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.542.719 I slot release: id 3 | task 164 | stop processing: n_tokens = 117, truncated = 0 0.56.623.769 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.223 (> 0.100 thold), f_keep = 0.248 0.56.624.038 I slot launch_slot_: id 3 | task 172 | processing task, is_child = 0 0.56.930.508 I slot print_timing: id 0 | task 167 | prompt eval time = 696.83 ms / 130 tokens ( 5.36 ms per token, 186.56 tokens per second) 0.56.930.513 I slot print_timing: id 0 | task 167 | eval time = 307.38 ms / 2 tokens ( 307.38 ms per token, 3.25 tokens per second) 0.56.930.513 I slot print_timing: id 0 | task 167 | total time = 1004.21 ms / 132 tokens 0.56.930.513 I slot print_timing: id 0 | task 167 | graphs reused = 2 0.56.930.514 I slot print_timing: id 0 | task 167 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.930.534 I slot release: id 0 | task 167 | stop processing: n_tokens = 131, truncated = 0 0.56.930.806 I slot print_timing: id 1 | task 168 | prompt eval time = 697.10 ms / 143 tokens ( 4.87 ms per token, 205.14 tokens per second) 0.56.930.808 I slot print_timing: id 1 | task 168 | eval time = 307.40 ms / 2 tokens ( 307.40 ms per token, 3.25 tokens per second) 0.56.930.809 I slot print_timing: id 1 | task 168 | total time = 1004.50 ms / 145 tokens 0.56.930.809 I slot print_timing: id 1 | task 168 | graphs reused = 2 0.56.930.809 I slot print_timing: id 1 | task 168 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.930.826 I slot release: id 1 | task 168 | stop processing: n_tokens = 144, truncated = 0 0.56.931.198 I slot print_timing: id 2 | task 169 | prompt eval time = 697.44 ms / 129 tokens ( 5.41 ms per token, 184.96 tokens per second) 0.56.931.201 I slot print_timing: id 2 | task 169 | eval time = 307.43 ms / 2 tokens ( 307.43 ms per token, 3.25 tokens per second) 0.56.931.201 I slot print_timing: id 2 | task 169 | total time = 1004.88 ms / 131 tokens 0.56.931.202 I slot print_timing: id 2 | task 169 | graphs reused = 2 0.56.931.202 I slot print_timing: id 2 | task 169 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.931.218 I slot release: id 2 | task 169 | stop processing: n_tokens = 130, truncated = 0 0.56.965.621 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.234 (> 0.100 thold), f_keep = 0.221 0.56.966.011 I slot launch_slot_: id 0 | task 175 | processing task, is_child = 0 0.56.966.693 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.225 (> 0.100 thold), f_keep = 0.201 0.56.966.733 I slot launch_slot_: id 1 | task 176 | processing task, is_child = 0 0.56.966.755 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.286 (> 0.100 thold), f_keep = 0.231 0.56.966.790 I slot launch_slot_: id 2 | task 177 | processing task, is_child = 0 0.57.640.987 I slot print_timing: id 3 | task 172 | prompt eval time = 341.57 ms / 130 tokens ( 2.63 ms per token, 380.59 tokens per second) 0.57.640.992 I slot print_timing: id 3 | task 172 | eval time = 675.37 ms / 2 tokens ( 675.37 ms per token, 1.48 tokens per second) 0.57.640.993 I slot print_timing: id 3 | task 172 | total time = 1016.94 ms / 132 tokens 0.57.640.993 I slot print_timing: id 3 | task 172 | graphs reused = 2 0.57.640.993 I slot print_timing: id 3 | task 172 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.641.014 I slot release: id 3 | task 172 | stop processing: n_tokens = 131, truncated = 0 0.57.721.823 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.180 (> 0.100 thold), f_keep = 0.221 0.57.722.412 I slot launch_slot_: id 3 | task 180 | processing task, is_child = 0 0.58.055.358 I slot print_timing: id 0 | task 175 | prompt eval time = 754.38 ms / 124 tokens ( 6.08 ms per token, 164.37 tokens per second) 0.58.055.363 I slot print_timing: id 0 | task 175 | eval time = 334.18 ms / 2 tokens ( 334.18 ms per token, 2.99 tokens per second) 0.58.055.364 I slot print_timing: id 0 | task 175 | total time = 1088.56 ms / 126 tokens 0.58.055.364 I slot print_timing: id 0 | task 175 | graphs reused = 2 0.58.055.364 I slot print_timing: id 0 | task 175 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.055.384 I slot release: id 0 | task 175 | stop processing: n_tokens = 125, truncated = 0 0.58.055.653 I slot print_timing: id 1 | task 176 | prompt eval time = 754.63 ms / 129 tokens ( 5.85 ms per token, 170.94 tokens per second) 0.58.055.655 I slot print_timing: id 1 | task 176 | eval time = 334.21 ms / 2 tokens ( 334.21 ms per token, 2.99 tokens per second) 0.58.055.655 I slot print_timing: id 1 | task 176 | total time = 1088.84 ms / 131 tokens 0.58.055.655 I slot print_timing: id 1 | task 176 | graphs reused = 2 0.58.055.656 I slot print_timing: id 1 | task 176 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.055.668 I slot release: id 1 | task 176 | stop processing: n_tokens = 130, truncated = 0 0.58.055.960 I slot print_timing: id 2 | task 177 | prompt eval time = 754.99 ms / 105 tokens ( 7.19 ms per token, 139.07 tokens per second) 0.58.055.962 I slot print_timing: id 2 | task 177 | eval time = 334.14 ms / 2 tokens ( 334.14 ms per token, 2.99 tokens per second) 0.58.055.962 I slot print_timing: id 2 | task 177 | total time = 1089.13 ms / 107 tokens 0.58.055.962 I slot print_timing: id 2 | task 177 | graphs reused = 2 0.58.055.963 I slot print_timing: id 2 | task 177 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.055.976 I slot release: id 2 | task 177 | stop processing: n_tokens = 106, truncated = 0 0.58.090.379 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 0.58.090.746 I slot launch_slot_: id 0 | task 183 | processing task, is_child = 0 0.58.091.261 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.172 (> 0.100 thold), f_keep = 0.223 0.58.091.300 I slot launch_slot_: id 1 | task 184 | processing task, is_child = 0 0.58.091.325 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.203 (> 0.100 thold), f_keep = 0.274 0.58.091.363 I slot launch_slot_: id 2 | task 185 | processing task, is_child = 0 0.58.882.971 I slot print_timing: id 3 | task 180 | prompt eval time = 367.96 ms / 161 tokens ( 2.29 ms per token, 437.55 tokens per second) 0.58.882.973 I slot print_timing: id 3 | task 180 | eval time = 792.59 ms / 2 tokens ( 792.59 ms per token, 1.26 tokens per second) 0.58.882.974 I slot print_timing: id 3 | task 180 | total time = 1160.55 ms / 163 tokens 0.58.882.974 I slot print_timing: id 3 | task 180 | graphs reused = 2 0.58.882.975 I slot print_timing: id 3 | task 180 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.882.996 I slot release: id 3 | task 180 | stop processing: n_tokens = 162, truncated = 0 0.58.964.089 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.257 (> 0.100 thold), f_keep = 0.179 0.58.964.971 I slot launch_slot_: id 3 | task 188 | processing task, is_child = 0 0.59.264.008 I slot print_timing: id 0 | task 183 | prompt eval time = 872.04 ms / 155 tokens ( 5.63 ms per token, 177.74 tokens per second) 0.59.264.013 I slot print_timing: id 0 | task 183 | eval time = 300.60 ms / 2 tokens ( 300.60 ms per token, 3.33 tokens per second) 0.59.264.014 I slot print_timing: id 0 | task 183 | total time = 1172.64 ms / 157 tokens 0.59.264.014 I slot print_timing: id 0 | task 183 | graphs reused = 2 0.59.264.014 I slot print_timing: id 0 | task 183 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.264.036 I slot release: id 0 | task 183 | stop processing: n_tokens = 156, truncated = 0 0.59.264.317 I slot print_timing: id 1 | task 184 | prompt eval time = 872.30 ms / 169 tokens ( 5.16 ms per token, 193.74 tokens per second) 0.59.264.320 I slot print_timing: id 1 | task 184 | eval time = 300.63 ms / 2 tokens ( 300.63 ms per token, 3.33 tokens per second) 0.59.264.320 I slot print_timing: id 1 | task 184 | total time = 1172.93 ms / 171 tokens 0.59.264.321 I slot print_timing: id 1 | task 184 | graphs reused = 2 0.59.264.321 I slot print_timing: id 1 | task 184 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.264.335 I slot release: id 1 | task 184 | stop processing: n_tokens = 170, truncated = 0 0.59.264.620 I slot print_timing: id 2 | task 185 | prompt eval time = 872.68 ms / 143 tokens ( 6.10 ms per token, 163.86 tokens per second) 0.59.264.622 I slot print_timing: id 2 | task 185 | eval time = 300.54 ms / 2 tokens ( 300.54 ms per token, 3.33 tokens per second) 0.59.264.622 I slot print_timing: id 2 | task 185 | total time = 1173.22 ms / 145 tokens 0.59.264.622 I slot print_timing: id 2 | task 185 | graphs reused = 2 0.59.264.623 I slot print_timing: id 2 | task 185 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.264.635 I slot release: id 2 | task 185 | stop processing: n_tokens = 144, truncated = 0 0.59.298.928 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.210 (> 0.100 thold), f_keep = 0.186 0.59.299.316 I slot launch_slot_: id 0 | task 191 | processing task, is_child = 0 0.59.300.094 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.261 (> 0.100 thold), f_keep = 0.171 0.59.300.140 I slot launch_slot_: id 1 | task 192 | processing task, is_child = 0 0.59.300.161 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.193 (> 0.100 thold), f_keep = 0.201 0.59.300.204 I slot launch_slot_: id 2 | task 193 | processing task, is_child = 0 1.00.106.951 I slot print_timing: id 3 | task 188 | prompt eval time = 333.94 ms / 113 tokens ( 2.96 ms per token, 338.38 tokens per second) 1.00.106.956 I slot print_timing: id 3 | task 188 | eval time = 808.02 ms / 2 tokens ( 808.02 ms per token, 1.24 tokens per second) 1.00.106.957 I slot print_timing: id 3 | task 188 | total time = 1141.97 ms / 115 tokens 1.00.106.957 I slot print_timing: id 3 | task 188 | graphs reused = 2 1.00.106.958 I slot print_timing: id 3 | task 188 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.106.982 I slot release: id 3 | task 188 | stop processing: n_tokens = 114, truncated = 0 1.00.188.096 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.265 (> 0.100 thold), f_keep = 0.263 1.00.188.430 I slot launch_slot_: id 3 | task 196 | processing task, is_child = 0 1.00.486.875 I slot print_timing: id 0 | task 191 | prompt eval time = 887.23 ms / 138 tokens ( 6.43 ms per token, 155.54 tokens per second) 1.00.486.883 I slot print_timing: id 0 | task 191 | eval time = 299.43 ms / 2 tokens ( 299.43 ms per token, 3.34 tokens per second) 1.00.486.883 I slot print_timing: id 0 | task 191 | total time = 1186.66 ms / 140 tokens 1.00.486.884 I slot print_timing: id 0 | task 191 | graphs reused = 2 1.00.486.884 I slot print_timing: id 0 | task 191 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.486.904 I slot release: id 0 | task 191 | stop processing: n_tokens = 139, truncated = 0 1.00.487.184 I slot print_timing: id 1 | task 192 | prompt eval time = 887.49 ms / 111 tokens ( 8.00 ms per token, 125.07 tokens per second) 1.00.487.186 I slot print_timing: id 1 | task 192 | eval time = 299.46 ms / 2 tokens ( 299.46 ms per token, 3.34 tokens per second) 1.00.487.186 I slot print_timing: id 1 | task 192 | total time = 1186.96 ms / 113 tokens 1.00.487.186 I slot print_timing: id 1 | task 192 | graphs reused = 2 1.00.487.187 I slot print_timing: id 1 | task 192 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.487.202 I slot release: id 1 | task 192 | stop processing: n_tokens = 112, truncated = 0 1.00.487.481 I slot print_timing: id 2 | task 193 | prompt eval time = 887.85 ms / 150 tokens ( 5.92 ms per token, 168.95 tokens per second) 1.00.487.482 I slot print_timing: id 2 | task 193 | eval time = 299.39 ms / 2 tokens ( 299.39 ms per token, 3.34 tokens per second) 1.00.487.483 I slot print_timing: id 2 | task 193 | total time = 1187.24 ms / 152 tokens 1.00.487.483 I slot print_timing: id 2 | task 193 | graphs reused = 2 1.00.487.483 I slot print_timing: id 2 | task 193 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.487.502 I slot release: id 2 | task 193 | stop processing: n_tokens = 151, truncated = 0 1.00.521.992 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.190 (> 0.100 thold), f_keep = 0.209 1.00.522.409 I slot launch_slot_: id 0 | task 199 | processing task, is_child = 0 1.00.522.949 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.254 (> 0.100 thold), f_keep = 0.259 1.00.523.143 I slot launch_slot_: id 1 | task 200 | processing task, is_child = 0 1.00.523.164 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.221 (> 0.100 thold), f_keep = 0.192 1.00.523.339 I slot launch_slot_: id 2 | task 201 | processing task, is_child = 0 1.01.290.261 I slot print_timing: id 3 | task 196 | prompt eval time = 333.55 ms / 113 tokens ( 2.95 ms per token, 338.78 tokens per second) 1.01.290.265 I slot print_timing: id 3 | task 196 | eval time = 768.27 ms / 2 tokens ( 768.27 ms per token, 1.30 tokens per second) 1.01.290.266 I slot print_timing: id 3 | task 196 | total time = 1101.82 ms / 115 tokens 1.01.290.266 I slot print_timing: id 3 | task 196 | graphs reused = 2 1.01.290.267 I slot print_timing: id 3 | task 196 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.290.285 I slot release: id 3 | task 196 | stop processing: n_tokens = 114, truncated = 0 1.01.370.955 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.254 1.01.371.250 I slot launch_slot_: id 3 | task 204 | processing task, is_child = 0 1.01.677.090 I slot print_timing: id 0 | task 199 | prompt eval time = 846.97 ms / 153 tokens ( 5.54 ms per token, 180.65 tokens per second) 1.01.677.092 I slot print_timing: id 0 | task 199 | eval time = 306.78 ms / 2 tokens ( 306.78 ms per token, 3.26 tokens per second) 1.01.677.093 I slot print_timing: id 0 | task 199 | total time = 1153.74 ms / 155 tokens 1.01.677.093 I slot print_timing: id 0 | task 199 | graphs reused = 2 1.01.677.094 I slot print_timing: id 0 | task 199 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.677.112 I slot release: id 0 | task 199 | stop processing: n_tokens = 154, truncated = 0 1.01.677.393 I slot print_timing: id 1 | task 200 | prompt eval time = 847.24 ms / 114 tokens ( 7.43 ms per token, 134.56 tokens per second) 1.01.677.395 I slot print_timing: id 1 | task 200 | eval time = 306.80 ms / 2 tokens ( 306.80 ms per token, 3.26 tokens per second) 1.01.677.396 I slot print_timing: id 1 | task 200 | total time = 1154.03 ms / 116 tokens 1.01.677.396 I slot print_timing: id 1 | task 200 | graphs reused = 2 1.01.677.396 I slot print_timing: id 1 | task 200 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.677.416 I slot release: id 1 | task 200 | stop processing: n_tokens = 115, truncated = 0 1.01.677.698 I slot print_timing: id 2 | task 201 | prompt eval time = 847.58 ms / 131 tokens ( 6.47 ms per token, 154.56 tokens per second) 1.01.677.701 I slot print_timing: id 2 | task 201 | eval time = 306.75 ms / 2 tokens ( 306.75 ms per token, 3.26 tokens per second) 1.01.677.701 I slot print_timing: id 2 | task 201 | total time = 1154.33 ms / 133 tokens 1.01.677.701 I slot print_timing: id 2 | task 201 | graphs reused = 2 1.01.677.702 I slot print_timing: id 2 | task 201 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.677.725 I slot release: id 2 | task 201 | stop processing: n_tokens = 132, truncated = 0 1.01.712.083 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.185 (> 0.100 thold), f_keep = 0.188 1.01.712.499 I slot launch_slot_: id 0 | task 207 | processing task, is_child = 0 1.01.713.055 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.252 (> 0.100 thold), f_keep = 0.261 1.01.713.097 I slot launch_slot_: id 1 | task 208 | processing task, is_child = 0 1.01.713.118 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.171 (> 0.100 thold), f_keep = 0.220 1.01.713.156 I slot launch_slot_: id 2 | task 209 | processing task, is_child = 0 1.02.592.940 I slot print_timing: id 3 | task 204 | prompt eval time = 340.82 ms / 126 tokens ( 2.70 ms per token, 369.69 tokens per second) 1.02.592.945 I slot print_timing: id 3 | task 204 | eval time = 880.85 ms / 2 tokens ( 880.85 ms per token, 1.14 tokens per second) 1.02.592.946 I slot print_timing: id 3 | task 204 | total time = 1221.67 ms / 128 tokens 1.02.592.946 I slot print_timing: id 3 | task 204 | graphs reused = 2 1.02.592.947 I slot print_timing: id 3 | task 204 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.592.969 I slot release: id 3 | task 204 | stop processing: n_tokens = 127, truncated = 0 1.02.674.131 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.223 (> 0.100 thold), f_keep = 0.228 1.02.674.800 I slot launch_slot_: id 3 | task 212 | processing task, is_child = 0 1.02.980.865 I slot print_timing: id 0 | task 207 | prompt eval time = 960.28 ms / 157 tokens ( 6.12 ms per token, 163.49 tokens per second) 1.02.980.870 I slot print_timing: id 0 | task 207 | eval time = 307.42 ms / 2 tokens ( 307.42 ms per token, 3.25 tokens per second) 1.02.980.870 I slot print_timing: id 0 | task 207 | total time = 1267.70 ms / 159 tokens 1.02.980.870 I slot print_timing: id 0 | task 207 | graphs reused = 2 1.02.980.871 I slot print_timing: id 0 | task 207 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.980.891 I slot release: id 0 | task 207 | stop processing: n_tokens = 158, truncated = 0 1.02.981.181 I slot print_timing: id 1 | task 208 | prompt eval time = 960.55 ms / 119 tokens ( 8.07 ms per token, 123.89 tokens per second) 1.02.981.183 I slot print_timing: id 1 | task 208 | eval time = 307.46 ms / 2 tokens ( 307.46 ms per token, 3.25 tokens per second) 1.02.981.183 I slot print_timing: id 1 | task 208 | total time = 1268.00 ms / 121 tokens 1.02.981.183 I slot print_timing: id 1 | task 208 | graphs reused = 2 1.02.981.184 I slot print_timing: id 1 | task 208 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.981.194 I slot release: id 1 | task 208 | stop processing: n_tokens = 120, truncated = 0 1.02.981.497 I slot print_timing: id 2 | task 209 | prompt eval time = 960.93 ms / 170 tokens ( 5.65 ms per token, 176.91 tokens per second) 1.02.981.498 I slot print_timing: id 2 | task 209 | eval time = 307.38 ms / 2 tokens ( 307.38 ms per token, 3.25 tokens per second) 1.02.981.499 I slot print_timing: id 2 | task 209 | total time = 1268.31 ms / 172 tokens 1.02.981.499 I slot print_timing: id 2 | task 209 | graphs reused = 2 1.02.981.499 I slot print_timing: id 2 | task 209 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.981.513 I slot release: id 2 | task 209 | stop processing: n_tokens = 171, truncated = 0 1.03.015.819 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.159 (> 0.100 thold), f_keep = 0.184 1.03.016.225 I slot launch_slot_: id 0 | task 215 | processing task, is_child = 0 1.03.016.835 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.264 (> 0.100 thold), f_keep = 0.242 1.03.016.874 I slot launch_slot_: id 1 | task 216 | processing task, is_child = 0 1.03.016.896 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.187 (> 0.100 thold), f_keep = 0.170 1.03.016.947 I slot launch_slot_: id 2 | task 217 | processing task, is_child = 0 1.03.915.162 I slot print_timing: id 3 | task 212 | prompt eval time = 341.01 ms / 130 tokens ( 2.62 ms per token, 381.22 tokens per second) 1.03.915.167 I slot print_timing: id 3 | task 212 | eval time = 899.34 ms / 2 tokens ( 899.34 ms per token, 1.11 tokens per second) 1.03.915.168 I slot print_timing: id 3 | task 212 | total time = 1240.35 ms / 132 tokens 1.03.915.168 I slot print_timing: id 3 | task 212 | graphs reused = 2 1.03.915.169 I slot print_timing: id 3 | task 212 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.915.192 I slot release: id 3 | task 212 | stop processing: n_tokens = 131, truncated = 0 1.03.996.039 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.215 (> 0.100 thold), f_keep = 0.221 1.03.996.924 I slot launch_slot_: id 3 | task 220 | processing task, is_child = 0 1.04.315.020 I slot print_timing: id 0 | task 215 | prompt eval time = 978.38 ms / 182 tokens ( 5.38 ms per token, 186.02 tokens per second) 1.04.315.025 I slot print_timing: id 0 | task 215 | eval time = 319.68 ms / 2 tokens ( 319.68 ms per token, 3.13 tokens per second) 1.04.315.025 I slot print_timing: id 0 | task 215 | total time = 1298.07 ms / 184 tokens 1.04.315.026 I slot print_timing: id 0 | task 215 | graphs reused = 2 1.04.315.026 I slot print_timing: id 0 | task 215 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.315.047 I slot release: id 0 | task 215 | stop processing: n_tokens = 183, truncated = 0 1.04.315.355 I slot print_timing: id 1 | task 216 | prompt eval time = 978.65 ms / 110 tokens ( 8.90 ms per token, 112.40 tokens per second) 1.04.315.357 I slot print_timing: id 1 | task 216 | eval time = 319.73 ms / 2 tokens ( 319.73 ms per token, 3.13 tokens per second) 1.04.315.357 I slot print_timing: id 1 | task 216 | total time = 1298.38 ms / 112 tokens 1.04.315.358 I slot print_timing: id 1 | task 216 | graphs reused = 2 1.04.315.358 I slot print_timing: id 1 | task 216 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.315.371 I slot release: id 1 | task 216 | stop processing: n_tokens = 111, truncated = 0 1.04.315.685 I slot print_timing: id 2 | task 217 | prompt eval time = 979.04 ms / 155 tokens ( 6.32 ms per token, 158.32 tokens per second) 1.04.315.687 I slot print_timing: id 2 | task 217 | eval time = 319.66 ms / 2 tokens ( 319.66 ms per token, 3.13 tokens per second) 1.04.315.688 I slot print_timing: id 2 | task 217 | total time = 1298.70 ms / 157 tokens 1.04.315.688 I slot print_timing: id 2 | task 217 | graphs reused = 2 1.04.315.688 I slot print_timing: id 2 | task 217 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.315.701 I slot release: id 2 | task 217 | stop processing: n_tokens = 156, truncated = 0 1.04.350.035 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.248 (> 0.100 thold), f_keep = 0.158 1.04.350.642 I slot launch_slot_: id 0 | task 223 | processing task, is_child = 0 1.04.351.261 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.213 (> 0.100 thold), f_keep = 0.261 1.04.351.297 I slot launch_slot_: id 1 | task 224 | processing task, is_child = 0 1.04.351.320 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.181 (> 0.100 thold), f_keep = 0.186 1.04.351.361 I slot launch_slot_: id 2 | task 225 | processing task, is_child = 0 1.05.160.784 I slot print_timing: id 3 | task 220 | prompt eval time = 353.10 ms / 135 tokens ( 2.62 ms per token, 382.33 tokens per second) 1.05.160.789 I slot print_timing: id 3 | task 220 | eval time = 810.75 ms / 2 tokens ( 810.75 ms per token, 1.23 tokens per second) 1.05.160.790 I slot print_timing: id 3 | task 220 | total time = 1163.85 ms / 137 tokens 1.05.160.790 I slot print_timing: id 3 | task 220 | graphs reused = 2 1.05.160.790 I slot print_timing: id 3 | task 220 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.160.808 I slot release: id 3 | task 220 | stop processing: n_tokens = 136, truncated = 0 1.05.241.641 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.216 (> 0.100 thold), f_keep = 0.213 1.05.242.314 I slot launch_slot_: id 3 | task 228 | processing task, is_child = 0 1.05.558.861 I slot print_timing: id 0 | task 223 | prompt eval time = 889.68 ms / 117 tokens ( 7.60 ms per token, 131.51 tokens per second) 1.05.558.866 I slot print_timing: id 0 | task 223 | eval time = 317.81 ms / 2 tokens ( 317.81 ms per token, 3.15 tokens per second) 1.05.558.866 I slot print_timing: id 0 | task 223 | total time = 1207.49 ms / 119 tokens 1.05.558.867 I slot print_timing: id 0 | task 223 | graphs reused = 2 1.05.558.867 I slot print_timing: id 0 | task 223 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.558.886 I slot release: id 0 | task 223 | stop processing: n_tokens = 118, truncated = 0 1.05.559.182 I slot print_timing: id 1 | task 224 | prompt eval time = 889.96 ms / 136 tokens ( 6.54 ms per token, 152.82 tokens per second) 1.05.559.190 I slot print_timing: id 1 | task 224 | eval time = 317.84 ms / 2 tokens ( 317.84 ms per token, 3.15 tokens per second) 1.05.559.190 I slot print_timing: id 1 | task 224 | total time = 1207.80 ms / 138 tokens 1.05.559.191 I slot print_timing: id 1 | task 224 | graphs reused = 2 1.05.559.191 I slot print_timing: id 1 | task 224 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.559.204 I slot release: id 1 | task 224 | stop processing: n_tokens = 137, truncated = 0 1.05.559.505 I slot print_timing: id 2 | task 225 | prompt eval time = 890.24 ms / 160 tokens ( 5.56 ms per token, 179.73 tokens per second) 1.05.559.510 I slot print_timing: id 2 | task 225 | eval time = 317.86 ms / 2 tokens ( 317.86 ms per token, 3.15 tokens per second) 1.05.559.511 I slot print_timing: id 2 | task 225 | total time = 1208.10 ms / 162 tokens 1.05.559.511 I slot print_timing: id 2 | task 225 | graphs reused = 2 1.05.559.511 I slot print_timing: id 2 | task 225 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.559.524 I slot release: id 2 | task 225 | stop processing: n_tokens = 161, truncated = 0 1.05.593.626 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.242 (> 0.100 thold), f_keep = 0.254 1.05.593.856 I slot launch_slot_: id 0 | task 231 | processing task, is_child = 0 1.05.594.642 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.246 (> 0.100 thold), f_keep = 0.212 1.05.594.812 I slot launch_slot_: id 1 | task 232 | processing task, is_child = 0 1.05.594.834 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.192 (> 0.100 thold), f_keep = 0.180 1.05.594.870 I slot launch_slot_: id 2 | task 233 | processing task, is_child = 0 1.06.301.372 I slot print_timing: id 3 | task 228 | prompt eval time = 351.30 ms / 134 tokens ( 2.62 ms per token, 381.44 tokens per second) 1.06.301.377 I slot print_timing: id 3 | task 228 | eval time = 707.75 ms / 2 tokens ( 707.75 ms per token, 1.41 tokens per second) 1.06.301.377 I slot print_timing: id 3 | task 228 | total time = 1059.05 ms / 136 tokens 1.06.301.378 I slot print_timing: id 3 | task 228 | graphs reused = 2 1.06.301.378 I slot print_timing: id 3 | task 228 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.301.396 I slot release: id 3 | task 228 | stop processing: n_tokens = 135, truncated = 0 1.06.382.112 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.186 (> 0.100 thold), f_keep = 0.215 1.06.382.830 I slot launch_slot_: id 3 | task 236 | processing task, is_child = 0 1.06.711.768 I slot print_timing: id 0 | task 231 | prompt eval time = 786.45 ms / 124 tokens ( 6.34 ms per token, 157.67 tokens per second) 1.06.711.770 I slot print_timing: id 0 | task 231 | eval time = 330.44 ms / 2 tokens ( 330.44 ms per token, 3.03 tokens per second) 1.06.711.771 I slot print_timing: id 0 | task 231 | total time = 1116.89 ms / 126 tokens 1.06.711.771 I slot print_timing: id 0 | task 231 | graphs reused = 2 1.06.711.772 I slot print_timing: id 0 | task 231 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.711.790 I slot release: id 0 | task 231 | stop processing: n_tokens = 125, truncated = 0 1.06.712.091 I slot print_timing: id 1 | task 232 | prompt eval time = 786.77 ms / 118 tokens ( 6.67 ms per token, 149.98 tokens per second) 1.06.712.093 I slot print_timing: id 1 | task 232 | eval time = 330.44 ms / 2 tokens ( 330.44 ms per token, 3.03 tokens per second) 1.06.712.093 I slot print_timing: id 1 | task 232 | total time = 1117.20 ms / 120 tokens 1.06.712.094 I slot print_timing: id 1 | task 232 | graphs reused = 2 1.06.712.094 I slot print_timing: id 1 | task 232 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.712.106 I slot release: id 1 | task 232 | stop processing: n_tokens = 119, truncated = 0 1.06.712.411 I slot print_timing: id 2 | task 233 | prompt eval time = 787.21 ms / 151 tokens ( 5.21 ms per token, 191.82 tokens per second) 1.06.712.413 I slot print_timing: id 2 | task 233 | eval time = 330.30 ms / 2 tokens ( 330.30 ms per token, 3.03 tokens per second) 1.06.712.414 I slot print_timing: id 2 | task 233 | total time = 1117.51 ms / 153 tokens 1.06.712.414 I slot print_timing: id 2 | task 233 | graphs reused = 2 1.06.712.414 I slot print_timing: id 2 | task 233 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.712.429 I slot release: id 2 | task 233 | stop processing: n_tokens = 152, truncated = 0 1.06.746.475 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.195 (> 0.100 thold), f_keep = 0.232 1.06.746.829 I slot launch_slot_: id 0 | task 239 | processing task, is_child = 0 1.06.747.562 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.179 (> 0.100 thold), f_keep = 0.244 1.06.747.602 I slot launch_slot_: id 1 | task 240 | processing task, is_child = 0 1.06.747.623 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.191 1.06.747.662 I slot launch_slot_: id 2 | task 241 | processing task, is_child = 0 1.07.447.610 I slot print_timing: id 3 | task 236 | prompt eval time = 363.64 ms / 156 tokens ( 2.33 ms per token, 429.00 tokens per second) 1.07.447.614 I slot print_timing: id 3 | task 236 | eval time = 701.13 ms / 2 tokens ( 701.13 ms per token, 1.43 tokens per second) 1.07.447.615 I slot print_timing: id 3 | task 236 | total time = 1064.77 ms / 158 tokens 1.07.447.615 I slot print_timing: id 3 | task 236 | graphs reused = 2 1.07.447.616 I slot print_timing: id 3 | task 236 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.447.638 I slot release: id 3 | task 236 | stop processing: n_tokens = 157, truncated = 0 1.07.528.702 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.186 (> 0.100 thold), f_keep = 0.185 1.07.529.450 I slot launch_slot_: id 3 | task 244 | processing task, is_child = 0 1.07.860.561 I slot print_timing: id 0 | task 239 | prompt eval time = 780.36 ms / 149 tokens ( 5.24 ms per token, 190.94 tokens per second) 1.07.860.566 I slot print_timing: id 0 | task 239 | eval time = 332.53 ms / 2 tokens ( 332.53 ms per token, 3.01 tokens per second) 1.07.860.566 I slot print_timing: id 0 | task 239 | total time = 1112.89 ms / 151 tokens 1.07.860.567 I slot print_timing: id 0 | task 239 | graphs reused = 2 1.07.860.567 I slot print_timing: id 0 | task 239 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.860.587 I slot release: id 0 | task 239 | stop processing: n_tokens = 150, truncated = 0 1.07.861.141 I slot print_timing: id 2 | task 241 | prompt eval time = 781.00 ms / 154 tokens ( 5.07 ms per token, 197.18 tokens per second) 1.07.861.142 I slot print_timing: id 2 | task 241 | eval time = 332.44 ms / 2 tokens ( 332.44 ms per token, 3.01 tokens per second) 1.07.861.143 I slot print_timing: id 2 | task 241 | total time = 1113.44 ms / 156 tokens 1.07.861.143 I slot print_timing: id 2 | task 241 | graphs reused = 2 1.07.861.144 I slot print_timing: id 2 | task 241 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.861.158 I slot release: id 2 | task 241 | stop processing: n_tokens = 155, truncated = 0 1.07.910.222 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.269 (> 0.100 thold), f_keep = 0.193 1.07.910.648 I slot launch_slot_: id 0 | task 247 | processing task, is_child = 0 1.07.911.052 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.252 (> 0.100 thold), f_keep = 0.187 1.07.911.090 I slot launch_slot_: id 2 | task 248 | processing task, is_child = 0 1.08.460.156 I slot print_timing: id 3 | task 244 | prompt eval time = 380.76 ms / 156 tokens ( 2.44 ms per token, 409.70 tokens per second) 1.08.460.161 I slot print_timing: id 3 | task 244 | eval time = 549.93 ms / 2 tokens ( 549.93 ms per token, 1.82 tokens per second) 1.08.460.162 I slot print_timing: id 3 | task 244 | total time = 930.69 ms / 158 tokens 1.08.460.162 I slot print_timing: id 3 | task 244 | graphs reused = 2 1.08.460.163 I slot print_timing: id 3 | task 244 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.460.187 I slot release: id 3 | task 244 | stop processing: n_tokens = 157, truncated = 0 1.08.544.968 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.156 (> 0.100 thold), f_keep = 0.185 1.08.545.449 I slot launch_slot_: id 3 | task 251 | processing task, is_child = 0 1.08.904.218 I slot print_timing: id 0 | task 247 | prompt eval time = 633.18 ms / 108 tokens ( 5.86 ms per token, 170.57 tokens per second) 1.08.904.220 I slot print_timing: id 0 | task 247 | eval time = 359.94 ms / 2 tokens ( 359.94 ms per token, 2.78 tokens per second) 1.08.904.221 I slot print_timing: id 0 | task 247 | total time = 993.12 ms / 110 tokens 1.08.904.221 I slot print_timing: id 0 | task 247 | graphs reused = 2 1.08.904.222 I slot print_timing: id 0 | task 247 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.904.238 I slot release: id 0 | task 247 | stop processing: n_tokens = 109, truncated = 0 1.08.904.817 I slot print_timing: id 2 | task 248 | prompt eval time = 633.85 ms / 115 tokens ( 5.51 ms per token, 181.43 tokens per second) 1.08.904.823 I slot print_timing: id 2 | task 248 | eval time = 359.86 ms / 2 tokens ( 359.86 ms per token, 2.78 tokens per second) 1.08.904.823 I slot print_timing: id 2 | task 248 | total time = 993.71 ms / 117 tokens 1.08.904.823 I slot print_timing: id 2 | task 248 | graphs reused = 2 1.08.904.823 I slot print_timing: id 2 | task 248 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.904.836 I slot release: id 2 | task 248 | stop processing: n_tokens = 116, truncated = 0 1.08.954.317 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.238 (> 0.100 thold), f_keep = 0.266 1.08.954.526 I slot launch_slot_: id 0 | task 254 | processing task, is_child = 0 1.08.954.707 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.282 (> 0.100 thold), f_keep = 0.250 1.08.954.889 I slot launch_slot_: id 2 | task 255 | processing task, is_child = 0 1.09.504.972 I slot print_timing: id 3 | task 251 | prompt eval time = 408.86 ms / 186 tokens ( 2.20 ms per token, 454.92 tokens per second) 1.09.504.974 I slot print_timing: id 3 | task 251 | eval time = 550.65 ms / 2 tokens ( 550.65 ms per token, 1.82 tokens per second) 1.09.504.975 I slot print_timing: id 3 | task 251 | total time = 959.51 ms / 188 tokens 1.09.504.975 I slot print_timing: id 3 | task 251 | graphs reused = 2 1.09.504.976 I slot print_timing: id 3 | task 251 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.505.003 I slot release: id 3 | task 251 | stop processing: n_tokens = 187, truncated = 0 1.09.589.700 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.257 (> 0.100 thold), f_keep = 0.155 1.09.590.347 I slot launch_slot_: id 3 | task 258 | processing task, is_child = 0 1.09.888.254 I slot print_timing: id 0 | task 254 | prompt eval time = 634.12 ms / 122 tokens ( 5.20 ms per token, 192.39 tokens per second) 1.09.888.259 I slot print_timing: id 0 | task 254 | eval time = 299.24 ms / 2 tokens ( 299.24 ms per token, 3.34 tokens per second) 1.09.888.260 I slot print_timing: id 0 | task 254 | total time = 933.36 ms / 124 tokens 1.09.888.260 I slot print_timing: id 0 | task 254 | graphs reused = 2 1.09.888.260 I slot print_timing: id 0 | task 254 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.888.280 I slot release: id 0 | task 254 | stop processing: n_tokens = 123, truncated = 0 1.09.888.894 I slot print_timing: id 2 | task 255 | prompt eval time = 634.78 ms / 103 tokens ( 6.16 ms per token, 162.26 tokens per second) 1.09.888.896 I slot print_timing: id 2 | task 255 | eval time = 299.20 ms / 2 tokens ( 299.20 ms per token, 3.34 tokens per second) 1.09.888.896 I slot print_timing: id 2 | task 255 | total time = 933.98 ms / 105 tokens 1.09.888.896 I slot print_timing: id 2 | task 255 | graphs reused = 2 1.09.888.896 I slot print_timing: id 2 | task 255 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.888.908 I slot release: id 2 | task 255 | stop processing: n_tokens = 104, truncated = 0 1.09.938.055 I slot print_timing: id 1 | task 240 | prompt eval time = 780.62 ms / 162 tokens ( 4.82 ms per token, 207.53 tokens per second) 1.09.938.060 I slot print_timing: id 1 | task 240 | eval time = 2409.74 ms / 11 tokens ( 240.97 ms per token, 4.15 tokens per second) 1.09.938.060 I slot print_timing: id 1 | task 240 | total time = 3190.37 ms / 173 tokens 1.09.938.061 I slot print_timing: id 1 | task 240 | graphs reused = 2 1.09.938.061 I slot print_timing: id 1 | task 240 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.938.081 I slot release: id 1 | task 240 | stop processing: n_tokens = 172, truncated = 0 1.09.938.407 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.234 (> 0.100 thold), f_keep = 0.174 1.09.938.938 I slot launch_slot_: id 1 | task 261 | processing task, is_child = 0 1.09.939.329 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.178 (> 0.100 thold), f_keep = 0.236 1.09.939.365 I slot launch_slot_: id 0 | task 262 | processing task, is_child = 0 1.10.514.582 I slot print_timing: id 3 | task 258 | prompt eval time = 348.05 ms / 113 tokens ( 3.08 ms per token, 324.66 tokens per second) 1.10.514.584 I slot print_timing: id 3 | task 258 | eval time = 576.17 ms / 2 tokens ( 576.17 ms per token, 1.74 tokens per second) 1.10.514.585 I slot print_timing: id 3 | task 258 | total time = 924.23 ms / 115 tokens 1.10.514.590 I slot print_timing: id 3 | task 258 | graphs reused = 2 1.10.514.590 I slot print_timing: id 3 | task 258 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.514.608 I slot release: id 3 | task 258 | stop processing: n_tokens = 114, truncated = 0 1.10.514.613 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.216 (> 0.100 thold), f_keep = 0.288 1.10.514.671 I slot launch_slot_: id 2 | task 264 | processing task, is_child = 0 1.10.875.429 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.254 1.10.875.484 I slot launch_slot_: id 3 | task 266 | processing task, is_child = 0 1.11.227.118 I slot print_timing: id 0 | task 262 | prompt eval time = 935.75 ms / 163 tokens ( 5.74 ms per token, 174.19 tokens per second) 1.11.227.123 I slot print_timing: id 0 | task 262 | eval time = 351.98 ms / 2 tokens ( 351.98 ms per token, 2.84 tokens per second) 1.11.227.123 I slot print_timing: id 0 | task 262 | total time = 1287.73 ms / 165 tokens 1.11.227.124 I slot print_timing: id 0 | task 262 | graphs reused = 2 1.11.227.124 I slot print_timing: id 0 | task 262 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.227.144 I slot release: id 0 | task 262 | stop processing: n_tokens = 164, truncated = 0 1.11.227.418 I slot print_timing: id 1 | task 261 | prompt eval time = 936.02 ms / 128 tokens ( 7.31 ms per token, 136.75 tokens per second) 1.11.227.420 I slot print_timing: id 1 | task 261 | eval time = 351.99 ms / 2 tokens ( 351.99 ms per token, 2.84 tokens per second) 1.11.227.420 I slot print_timing: id 1 | task 261 | total time = 1288.02 ms / 130 tokens 1.11.227.420 I slot print_timing: id 1 | task 261 | graphs reused = 2 1.11.227.421 I slot print_timing: id 1 | task 261 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.227.432 I slot release: id 1 | task 261 | stop processing: n_tokens = 129, truncated = 0 1.11.279.605 I slot print_timing: id 2 | task 264 | prompt eval time = 712.62 ms / 139 tokens ( 5.13 ms per token, 195.06 tokens per second) 1.11.279.610 I slot print_timing: id 2 | task 264 | eval time = 51.85 ms / 2 tokens ( 51.85 ms per token, 19.28 tokens per second) 1.11.279.611 I slot print_timing: id 2 | task 264 | total time = 764.47 ms / 141 tokens 1.11.279.611 I slot print_timing: id 2 | task 264 | graphs reused = 2 1.11.279.611 I slot print_timing: id 2 | task 264 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.279.626 I slot release: id 2 | task 264 | stop processing: n_tokens = 140, truncated = 0 1.11.279.938 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.240 (> 0.100 thold), f_keep = 0.177 1.11.280.459 I slot launch_slot_: id 0 | task 269 | processing task, is_child = 0 1.11.281.208 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.221 (> 0.100 thold), f_keep = 0.214 1.11.281.376 I slot launch_slot_: id 2 | task 270 | processing task, is_child = 0 1.11.842.321 I slot print_timing: id 3 | task 266 | prompt eval time = 404.38 ms / 127 tokens ( 3.18 ms per token, 314.06 tokens per second) 1.11.842.323 I slot print_timing: id 3 | task 266 | eval time = 562.38 ms / 2 tokens ( 562.38 ms per token, 1.78 tokens per second) 1.11.842.324 I slot print_timing: id 3 | task 266 | total time = 966.76 ms / 129 tokens 1.11.842.324 I slot print_timing: id 3 | task 266 | graphs reused = 2 1.11.842.324 I slot print_timing: id 3 | task 266 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.842.343 I slot release: id 3 | task 266 | stop processing: n_tokens = 128, truncated = 0 1.11.842.349 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.182 (> 0.100 thold), f_keep = 0.225 1.11.842.538 I slot launch_slot_: id 1 | task 272 | processing task, is_child = 0 1.12.215.596 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.204 (> 0.100 thold), f_keep = 0.227 1.12.215.660 I slot launch_slot_: id 3 | task 274 | processing task, is_child = 0 1.12.574.129 I slot print_timing: id 0 | task 269 | prompt eval time = 933.80 ms / 121 tokens ( 7.72 ms per token, 129.58 tokens per second) 1.12.574.131 I slot print_timing: id 0 | task 269 | eval time = 358.93 ms / 2 tokens ( 358.93 ms per token, 2.79 tokens per second) 1.12.574.132 I slot print_timing: id 0 | task 269 | total time = 1292.72 ms / 123 tokens 1.12.574.132 I slot print_timing: id 0 | task 269 | graphs reused = 2 1.12.574.132 I slot print_timing: id 0 | task 269 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.574.153 I slot release: id 0 | task 269 | stop processing: n_tokens = 122, truncated = 0 1.12.574.852 I slot print_timing: id 2 | task 270 | prompt eval time = 934.18 ms / 136 tokens ( 6.87 ms per token, 145.58 tokens per second) 1.12.574.854 I slot print_timing: id 2 | task 270 | eval time = 359.26 ms / 2 tokens ( 359.26 ms per token, 2.78 tokens per second) 1.12.574.854 I slot print_timing: id 2 | task 270 | total time = 1293.44 ms / 138 tokens 1.12.574.854 I slot print_timing: id 2 | task 270 | graphs reused = 2 1.12.574.855 I slot print_timing: id 2 | task 270 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.574.882 I slot release: id 2 | task 270 | stop processing: n_tokens = 137, truncated = 0 1.12.624.186 I slot print_timing: id 1 | task 272 | prompt eval time = 731.58 ms / 159 tokens ( 4.60 ms per token, 217.34 tokens per second) 1.12.624.188 I slot print_timing: id 1 | task 272 | eval time = 49.64 ms / 2 tokens ( 49.64 ms per token, 20.15 tokens per second) 1.12.624.188 I slot print_timing: id 1 | task 272 | total time = 781.22 ms / 161 tokens 1.12.624.189 I slot print_timing: id 1 | task 272 | graphs reused = 2 1.12.624.189 I slot print_timing: id 1 | task 272 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.624.209 I slot release: id 1 | task 272 | stop processing: n_tokens = 160, truncated = 0 1.12.624.594 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.242 (> 0.100 thold), f_keep = 0.238 1.12.624.856 I slot launch_slot_: id 0 | task 277 | processing task, is_child = 0 1.12.625.758 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.171 (> 0.100 thold), f_keep = 0.181 1.12.625.797 I slot launch_slot_: id 1 | task 278 | processing task, is_child = 0 1.13.216.588 I slot print_timing: id 3 | task 274 | prompt eval time = 408.86 ms / 142 tokens ( 2.88 ms per token, 347.31 tokens per second) 1.13.216.593 I slot print_timing: id 3 | task 274 | eval time = 592.00 ms / 2 tokens ( 592.00 ms per token, 1.69 tokens per second) 1.13.216.594 I slot print_timing: id 3 | task 274 | total time = 1000.86 ms / 144 tokens 1.13.216.594 I slot print_timing: id 3 | task 274 | graphs reused = 2 1.13.216.594 I slot print_timing: id 3 | task 274 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.216.612 I slot release: id 3 | task 274 | stop processing: n_tokens = 143, truncated = 0 1.13.216.616 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.158 (> 0.100 thold), f_keep = 0.212 1.13.216.664 I slot launch_slot_: id 2 | task 280 | processing task, is_child = 0 1.13.612.802 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.184 (> 0.100 thold), f_keep = 0.203 1.13.612.861 I slot launch_slot_: id 3 | task 282 | processing task, is_child = 0 1.13.989.012 I slot print_timing: id 0 | task 277 | prompt eval time = 986.69 ms / 120 tokens ( 8.22 ms per token, 121.62 tokens per second) 1.13.989.014 I slot print_timing: id 0 | task 277 | eval time = 376.50 ms / 2 tokens ( 376.50 ms per token, 2.66 tokens per second) 1.13.989.014 I slot print_timing: id 0 | task 277 | total time = 1363.19 ms / 122 tokens 1.13.989.015 I slot print_timing: id 0 | task 277 | graphs reused = 2 1.13.989.015 I slot print_timing: id 0 | task 277 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.989.037 I slot release: id 0 | task 277 | stop processing: n_tokens = 121, truncated = 0 1.13.989.322 I slot print_timing: id 1 | task 278 | prompt eval time = 986.95 ms / 170 tokens ( 5.81 ms per token, 172.25 tokens per second) 1.13.989.324 I slot print_timing: id 1 | task 278 | eval time = 376.53 ms / 2 tokens ( 376.53 ms per token, 2.66 tokens per second) 1.13.989.324 I slot print_timing: id 1 | task 278 | total time = 1363.48 ms / 172 tokens 1.13.989.325 I slot print_timing: id 1 | task 278 | graphs reused = 2 1.13.989.325 I slot print_timing: id 1 | task 278 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.989.343 I slot release: id 1 | task 278 | stop processing: n_tokens = 171, truncated = 0 1.14.041.876 I slot print_timing: id 2 | task 280 | prompt eval time = 772.51 ms / 184 tokens ( 4.20 ms per token, 238.18 tokens per second) 1.14.041.881 I slot print_timing: id 2 | task 280 | eval time = 52.21 ms / 2 tokens ( 52.21 ms per token, 19.15 tokens per second) 1.14.041.882 I slot print_timing: id 2 | task 280 | total time = 824.73 ms / 186 tokens 1.14.041.882 I slot print_timing: id 2 | task 280 | graphs reused = 2 1.14.041.882 I slot print_timing: id 2 | task 280 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.041.903 I slot release: id 2 | task 280 | stop processing: n_tokens = 185, truncated = 0 1.14.042.298 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.282 (> 0.100 thold), f_keep = 0.240 1.14.042.676 I slot launch_slot_: id 0 | task 286 | processing task, is_child = 0 1.14.043.680 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.216 (> 0.100 thold), f_keep = 0.170 1.14.043.854 I slot launch_slot_: id 1 | task 285 | processing task, is_child = 0 1.14.572.957 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.232 (> 0.100 thold), f_keep = 0.157 1.14.573.016 I slot launch_slot_: id 2 | task 288 | processing task, is_child = 0 1.15.009.891 I slot print_timing: id 0 | task 286 | prompt eval time = 890.03 ms / 103 tokens ( 8.64 ms per token, 115.73 tokens per second) 1.15.009.895 I slot print_timing: id 0 | task 286 | eval time = 75.97 ms / 2 tokens ( 75.97 ms per token, 13.16 tokens per second) 1.15.009.896 I slot print_timing: id 0 | task 286 | total time = 966.00 ms / 105 tokens 1.15.009.896 I slot print_timing: id 0 | task 286 | graphs reused = 2 1.15.009.896 I slot print_timing: id 0 | task 286 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.009.916 I slot release: id 0 | task 286 | stop processing: n_tokens = 104, truncated = 0 1.15.010.201 I slot print_timing: id 1 | task 285 | prompt eval time = 890.32 ms / 134 tokens ( 6.64 ms per token, 150.51 tokens per second) 1.15.010.202 I slot print_timing: id 1 | task 285 | eval time = 75.98 ms / 2 tokens ( 75.98 ms per token, 13.16 tokens per second) 1.15.010.203 I slot print_timing: id 1 | task 285 | total time = 966.30 ms / 136 tokens 1.15.010.203 I slot print_timing: id 1 | task 285 | graphs reused = 2 1.15.010.203 I slot print_timing: id 1 | task 285 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.010.216 I slot release: id 1 | task 285 | stop processing: n_tokens = 135, truncated = 0 1.15.035.686 I slot print_timing: id 2 | task 288 | prompt eval time = 437.41 ms / 125 tokens ( 3.50 ms per token, 285.77 tokens per second) 1.15.035.691 I slot print_timing: id 2 | task 288 | eval time = 25.15 ms / 2 tokens ( 25.15 ms per token, 39.76 tokens per second) 1.15.035.692 I slot print_timing: id 2 | task 288 | total time = 462.56 ms / 127 tokens 1.15.035.692 I slot print_timing: id 2 | task 288 | graphs reused = 2 1.15.035.693 I slot print_timing: id 2 | task 288 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.035.706 I slot release: id 2 | task 288 | stop processing: n_tokens = 126, truncated = 0 1.15.036.008 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.200 (> 0.100 thold), f_keep = 0.279 1.15.036.249 I slot launch_slot_: id 0 | task 292 | processing task, is_child = 0 1.15.421.354 I slot print_timing: id 0 | task 292 | prompt eval time = 352.56 ms / 145 tokens ( 2.43 ms per token, 411.28 tokens per second) 1.15.421.357 I slot print_timing: id 0 | task 292 | eval time = 31.84 ms / 2 tokens ( 31.84 ms per token, 31.40 tokens per second) 1.15.421.357 I slot print_timing: id 0 | task 292 | total time = 384.40 ms / 147 tokens 1.15.421.357 I slot print_timing: id 0 | task 292 | graphs reused = 2 1.15.421.358 I slot print_timing: id 0 | task 292 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.421.375 I slot release: id 0 | task 292 | stop processing: n_tokens = 146, truncated = 0 1.15.466.142 I slot print_timing: id 3 | task 282 | prompt eval time = 429.36 ms / 158 tokens ( 2.72 ms per token, 367.99 tokens per second) 1.15.466.147 I slot print_timing: id 3 | task 282 | eval time = 1423.84 ms / 11 tokens ( 142.38 ms per token, 7.02 tokens per second) 1.15.466.148 I slot print_timing: id 3 | task 282 | total time = 1853.20 ms / 169 tokens 1.15.466.148 I slot print_timing: id 3 | task 282 | graphs reused = 5 1.15.466.149 I slot print_timing: id 3 | task 282 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.466.166 I slot release: id 3 | task 282 | stop processing: n_tokens = 168, truncated = 0 1.15.480.779 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 135, t_last = 337781907321 1.15.480.884 I slot launch_slot_: id 1 | task 299 | processing task, is_child = 0 1.15.481.851 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 126, t_last = 337781932811 1.15.481.894 I slot launch_slot_: id 2 | task 301 | processing task, is_child = 0 1.15.481.946 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 146, t_last = 337782318480 1.15.481.984 I slot launch_slot_: id 0 | task 300 | processing task, is_child = 0 1.15.482.009 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 168, t_last = 337782363271 1.15.482.046 I slot launch_slot_: id 3 | task 302 | processing task, is_child = 0 1.20.830.011 I slot print_timing: id 0 | task 300 | prompt processing, n_tokens = 1129, progress = 1.00, t = 5.35 s / 211.11 tokens per second 1.21.054.253 I slot print_timing: id 1 | task 299 | prompt processing, n_tokens = 1155, progress = 1.00, t = 5.35 s / 215.97 tokens per second 1.21.054.442 I slot print_timing: id 2 | task 301 | prompt processing, n_tokens = 1144, progress = 1.00, t = 5.35 s / 213.92 tokens per second 1.21.054.609 I slot print_timing: id 3 | task 302 | prompt processing, n_tokens = 637, progress = 0.55, t = 5.35 s / 119.11 tokens per second 1.21.807.606 I slot print_timing: id 3 | task 302 | prompt processing, n_tokens = 1149, progress = 1.00, t = 6.32 s / 181.67 tokens per second 1.25.847.121 I slot print_timing: id 0 | task 300 | n_gen = 100, tg = 24.50 t/s, tg_3s = 24.75 t/s 1.25.847.678 I slot print_timing: id 1 | task 299 | n_gen = 100, tg = 24.50 t/s, tg_3s = 24.75 t/s 1.25.848.230 I slot print_timing: id 2 | task 301 | n_gen = 100, tg = 24.50 t/s, tg_3s = 24.75 t/s 1.25.889.515 I slot print_timing: id 3 | task 302 | n_gen = 100, tg = 24.67 t/s, tg_3s = 24.92 t/s 1.28.887.271 I slot print_timing: id 0 | task 300 | n_gen = 175, tg = 24.58 t/s, tg_3s = 24.67 t/s 1.28.887.869 I slot print_timing: id 1 | task 299 | n_gen = 175, tg = 24.57 t/s, tg_3s = 24.67 t/s 1.28.888.480 I slot print_timing: id 2 | task 301 | n_gen = 175, tg = 24.57 t/s, tg_3s = 24.67 t/s 1.28.929.563 I slot print_timing: id 3 | task 302 | n_gen = 175, tg = 24.67 t/s, tg_3s = 24.67 t/s 1.31.925.413 I slot print_timing: id 0 | task 300 | n_gen = 250, tg = 24.61 t/s, tg_3s = 24.69 t/s 1.31.925.990 I slot print_timing: id 1 | task 299 | n_gen = 250, tg = 24.61 t/s, tg_3s = 24.69 t/s 1.31.926.595 I slot print_timing: id 2 | task 301 | n_gen = 250, tg = 24.61 t/s, tg_3s = 24.69 t/s 1.31.967.630 I slot print_timing: id 3 | task 302 | n_gen = 250, tg = 24.68 t/s, tg_3s = 24.69 t/s 1.34.930.277 I slot print_timing: id 0 | task 300 | n_gen = 324, tg = 24.61 t/s, tg_3s = 24.63 t/s 1.34.930.826 I slot print_timing: id 1 | task 299 | n_gen = 324, tg = 24.61 t/s, tg_3s = 24.63 t/s 1.34.931.434 I slot print_timing: id 2 | task 301 | n_gen = 324, tg = 24.61 t/s, tg_3s = 24.63 t/s 1.34.972.786 I slot print_timing: id 3 | task 302 | n_gen = 324, tg = 24.66 t/s, tg_3s = 24.62 t/s 1.36.592.425 I slot print_timing: id 0 | task 300 | prompt eval time = 6324.95 ms / 1133 tokens ( 5.58 ms per token, 179.13 tokens per second) 1.36.592.429 I slot print_timing: id 0 | task 300 | eval time = 14785.42 ms / 365 tokens ( 40.62 ms per token, 24.62 tokens per second) 1.36.592.430 I slot print_timing: id 0 | task 300 | total time = 21110.37 ms / 1498 tokens 1.36.592.431 I slot print_timing: id 0 | task 300 | graphs reused = 368 1.36.592.432 I slot print_timing: id 0 | task 300 | graph reallocs = 0 / 0 (same size) / (changed size) 1.36.592.530 I slot release: id 0 | task 300 | stop processing: n_tokens = 1497, truncated = 0 1.36.629.331 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.713 1.36.629.370 I slot launch_slot_: id 0 | task 671 | processing task, is_child = 0 1.37.952.294 I slot print_timing: id 1 | task 299 | n_gen = 378, tg = 23.35 t/s, tg_3s = 17.87 t/s 1.37.952.576 I slot print_timing: id 2 | task 301 | n_gen = 378, tg = 23.35 t/s, tg_3s = 17.87 t/s 1.37.994.243 I slot print_timing: id 3 | task 302 | n_gen = 378, tg = 23.39 t/s, tg_3s = 17.87 t/s 1.40.960.775 I slot print_timing: id 1 | task 299 | n_gen = 452, tg = 23.55 t/s, tg_3s = 24.60 t/s 1.40.961.347 I slot print_timing: id 2 | task 301 | n_gen = 452, tg = 23.55 t/s, tg_3s = 24.59 t/s 1.41.002.516 I slot print_timing: id 3 | task 302 | n_gen = 452, tg = 23.58 t/s, tg_3s = 24.60 t/s 1.41.610.862 I slot print_timing: id 0 | task 671 | n_gen = 100, tg = 24.64 t/s, tg_3s = 24.89 t/s 1.43.971.212 I slot print_timing: id 1 | task 299 | n_gen = 526, tg = 23.69 t/s, tg_3s = 24.58 t/s 1.43.971.868 I slot print_timing: id 2 | task 301 | n_gen = 526, tg = 23.69 t/s, tg_3s = 24.58 t/s 1.44.013.205 I slot print_timing: id 3 | task 302 | n_gen = 526, tg = 23.72 t/s, tg_3s = 24.58 t/s 1.44.616.596 I slot print_timing: id 0 | task 671 | n_gen = 174, tg = 24.63 t/s, tg_3s = 24.62 t/s 1.46.972.138 I slot print_timing: id 1 | task 299 | n_gen = 600, tg = 23.80 t/s, tg_3s = 24.66 t/s 1.46.972.766 I slot print_timing: id 2 | task 301 | n_gen = 600, tg = 23.80 t/s, tg_3s = 24.66 t/s 1.47.013.984 I slot print_timing: id 3 | task 302 | n_gen = 600, tg = 23.83 t/s, tg_3s = 24.66 t/s 1.47.621.423 I slot print_timing: id 0 | task 671 | n_gen = 248, tg = 24.63 t/s, tg_3s = 24.63 t/s 1.49.981.152 I slot print_timing: id 1 | task 299 | n_gen = 674, tg = 23.89 t/s, tg_3s = 24.59 t/s 1.49.981.691 I slot print_timing: id 2 | task 301 | n_gen = 674, tg = 23.89 t/s, tg_3s = 24.59 t/s 1.50.022.820 I slot print_timing: id 3 | task 302 | n_gen = 674, tg = 23.91 t/s, tg_3s = 24.59 t/s 1.50.632.401 I slot print_timing: id 0 | task 671 | n_gen = 322, tg = 24.62 t/s, tg_3s = 24.58 t/s 1.52.414.548 I slot print_timing: id 2 | task 301 | prompt eval time = 6325.50 ms / 1148 tokens ( 5.51 ms per token, 181.49 tokens per second) 1.52.414.555 I slot print_timing: id 2 | task 301 | eval time = 30606.94 ms / 734 tokens ( 41.76 ms per token, 23.95 tokens per second) 1.52.414.556 I slot print_timing: id 2 | task 301 | total time = 36932.44 ms / 1882 tokens 1.52.414.557 I slot print_timing: id 2 | task 301 | graphs reused = 731 1.52.414.557 I slot print_timing: id 2 | task 301 | graph reallocs = 0 / 0 (same size) / (changed size) 1.52.414.678 I slot release: id 2 | task 301 | stop processing: n_tokens = 1881, truncated = 0 1.52.458.228 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.568 1.52.458.269 I slot launch_slot_: id 2 | task 1041 | processing task, is_child = 0 1.53.370.212 I slot print_timing: id 1 | task 299 | n_gen = 737, tg = 23.32 t/s, tg_3s = 18.59 t/s 1.53.370.492 I slot print_timing: id 3 | task 302 | n_gen = 736, tg = 23.34 t/s, tg_3s = 18.52 t/s 1.53.645.717 I slot print_timing: id 0 | task 671 | n_gen = 375, tg = 23.30 t/s, tg_3s = 17.59 t/s 1.54.585.698 I slot print_timing: id 3 | task 302 | prompt eval time = 6394.43 ms / 1153 tokens ( 5.55 ms per token, 180.31 tokens per second) 1.54.585.705 I slot print_timing: id 3 | task 302 | eval time = 32709.14 ms / 765 tokens ( 42.81 ms per token, 23.36 tokens per second) 1.54.585.706 I slot print_timing: id 3 | task 302 | total time = 39103.57 ms / 1918 tokens 1.54.585.706 I slot print_timing: id 3 | task 302 | graphs reused = 758 1.54.585.707 I slot print_timing: id 3 | task 302 | graph reallocs = 0 / 0 (same size) / (changed size) 1.54.585.807 I slot release: id 3 | task 302 | stop processing: n_tokens = 1917, truncated = 0 1.54.620.688 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.904 (> 0.100 thold), f_keep = 0.557 1.54.620.734 I slot launch_slot_: id 3 | task 1074 | processing task, is_child = 0 1.56.381.119 I slot print_timing: id 1 | task 299 | n_gen = 790, tg = 22.82 t/s, tg_3s = 17.60 t/s 1.56.664.430 I slot print_timing: id 0 | task 671 | n_gen = 429, tg = 22.44 t/s, tg_3s = 17.89 t/s 1.58.291.377 I slot print_timing: id 2 | task 1041 | n_gen = 100, tg = 20.43 t/s, tg_3s = 20.64 t/s 1.59.387.134 I slot print_timing: id 1 | task 299 | n_gen = 864, tg = 22.96 t/s, tg_3s = 24.62 t/s 1.59.591.533 I slot print_timing: id 3 | task 1074 | n_gen = 100, tg = 24.62 t/s, tg_3s = 24.87 t/s 1.59.671.202 I slot print_timing: id 0 | task 671 | n_gen = 503, tg = 22.74 t/s, tg_3s = 24.61 t/s 2.01.304.501 I slot print_timing: id 2 | task 1041 | n_gen = 174, tg = 22.01 t/s, tg_3s = 24.56 t/s 2.02.401.850 I slot print_timing: id 1 | task 299 | n_gen = 938, tg = 23.08 t/s, tg_3s = 24.55 t/s 2.02.606.991 I slot print_timing: id 3 | task 1074 | n_gen = 174, tg = 24.59 t/s, tg_3s = 24.54 t/s 2.02.687.045 I slot print_timing: id 0 | task 671 | n_gen = 577, tg = 22.95 t/s, tg_3s = 24.54 t/s 2.04.321.424 I slot print_timing: id 2 | task 1041 | n_gen = 248, tg = 22.71 t/s, tg_3s = 24.53 t/s 2.05.423.310 I slot print_timing: id 1 | task 299 | n_gen = 1012, tg = 23.18 t/s, tg_3s = 24.49 t/s 2.05.628.742 I slot print_timing: id 3 | task 1074 | n_gen = 248, tg = 24.56 t/s, tg_3s = 24.49 t/s 2.05.708.658 I slot print_timing: id 0 | task 671 | n_gen = 651, tg = 23.12 t/s, tg_3s = 24.49 t/s 2.05.913.202 I slot print_timing: id 1 | task 299 | prompt eval time = 6325.24 ms / 1159 tokens ( 5.46 ms per token, 183.23 tokens per second) 2.05.913.210 I slot print_timing: id 1 | task 299 | eval time = 44105.89 ms / 1024 tokens ( 43.11 ms per token, 23.19 tokens per second) 2.05.913.212 I slot print_timing: id 1 | task 299 | total time = 50431.12 ms / 2183 tokens 2.05.913.212 I slot print_timing: id 1 | task 299 | graphs reused = 1010 2.05.913.213 I slot print_timing: id 1 | task 299 | graph reallocs = 0 / 0 (same size) / (changed size) 2.05.913.343 I slot release: id 1 | task 299 | stop processing: n_tokens = 2182, truncated = 0 2.05.957.517 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.489 2.05.963.355 I slot launch_slot_: id 1 | task 1333 | processing task, is_child = 0 2.07.347.297 I slot print_timing: id 2 | task 1041 | n_gen = 305, tg = 21.87 t/s, tg_3s = 18.84 t/s 2.08.646.790 I slot print_timing: id 3 | task 1074 | n_gen = 305, tg = 23.25 t/s, tg_3s = 18.89 t/s 2.08.725.968 I slot print_timing: id 0 | task 671 | n_gen = 708, tg = 22.71 t/s, tg_3s = 18.89 t/s 2.09.049.923 I slot print_timing: id 0 | task 671 | prompt eval time = 964.05 ms / 554 tokens ( 1.74 ms per token, 574.66 tokens per second) 2.09.049.930 I slot print_timing: id 0 | task 671 | eval time = 31456.50 ms / 716 tokens ( 44.00 ms per token, 22.73 tokens per second) 2.09.049.932 I slot print_timing: id 0 | task 671 | total time = 32420.54 ms / 1270 tokens 2.09.049.933 I slot print_timing: id 0 | task 671 | graphs reused = 1066 2.09.049.933 I slot print_timing: id 0 | task 671 | graph reallocs = 0 / 0 (same size) / (changed size) 2.09.050.033 I slot release: id 0 | task 671 | stop processing: n_tokens = 1886, truncated = 0 2.09.087.077 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.901 (> 0.100 thold), f_keep = 0.566 2.09.087.112 I slot launch_slot_: id 0 | task 1394 | processing task, is_child = 0 2.10.359.407 I slot print_timing: id 2 | task 1041 | n_gen = 361, tg = 21.29 t/s, tg_3s = 18.59 t/s 2.11.493.995 I slot print_timing: id 1 | task 1333 | n_gen = 100, tg = 20.81 t/s, tg_3s = 21.02 t/s 2.11.657.024 I slot print_timing: id 3 | task 1074 | n_gen = 361, tg = 22.38 t/s, tg_3s = 18.60 t/s 2.13.398.192 I slot print_timing: id 2 | task 1041 | n_gen = 436, tg = 21.80 t/s, tg_3s = 24.68 t/s 2.13.963.670 I slot print_timing: id 0 | task 1394 | n_gen = 100, tg = 24.71 t/s, tg_3s = 24.95 t/s 2.14.531.962 I slot print_timing: id 1 | task 1333 | n_gen = 175, tg = 22.32 t/s, tg_3s = 24.69 t/s 2.14.694.483 I slot print_timing: id 3 | task 1074 | n_gen = 436, tg = 22.75 t/s, tg_3s = 24.69 t/s 2.16.438.256 I slot print_timing: id 2 | task 1041 | n_gen = 511, tg = 22.18 t/s, tg_3s = 24.67 t/s 2.16.964.508 I slot print_timing: id 0 | task 1394 | n_gen = 174, tg = 24.69 t/s, tg_3s = 24.66 t/s 2.17.532.593 I slot print_timing: id 1 | task 1333 | n_gen = 249, tg = 22.97 t/s, tg_3s = 24.66 t/s 2.17.695.584 I slot print_timing: id 3 | task 1074 | n_gen = 510, tg = 23.01 t/s, tg_3s = 24.66 t/s 2.19.358.618 I slot print_timing: id 3 | task 1074 | prompt eval time = 950.31 ms / 544 tokens ( 1.75 ms per token, 572.44 tokens per second) 2.19.358.625 I slot print_timing: id 3 | task 1074 | eval time = 23787.56 ms / 551 tokens ( 43.25 ms per token, 23.12 tokens per second) 2.19.358.626 I slot print_timing: id 3 | task 1074 | total time = 24737.88 ms / 1095 tokens 2.19.358.627 I slot print_timing: id 3 | task 1074 | graphs reused = 1297 2.19.358.628 I slot print_timing: id 3 | task 1074 | graph reallocs = 0 / 0 (same size) / (changed size) 2.19.358.728 I slot release: id 3 | task 1074 | stop processing: n_tokens = 1731, truncated = 0 2.19.393.915 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.882 (> 0.100 thold), f_keep = 0.617 2.19.393.956 I slot launch_slot_: id 3 | task 1631 | processing task, is_child = 0 2.19.592.555 I slot print_timing: id 2 | task 1041 | n_gen = 585, tg = 22.34 t/s, tg_3s = 23.46 t/s 2.20.282.761 I slot print_timing: id 0 | task 1394 | n_gen = 236, tg = 22.76 t/s, tg_3s = 18.68 t/s 2.20.550.248 I slot print_timing: id 1 | task 1333 | n_gen = 303, tg = 21.86 t/s, tg_3s = 17.89 t/s 2.22.625.838 I slot print_timing: id 2 | task 1041 | n_gen = 643, tg = 22.00 t/s, tg_3s = 19.12 t/s 2.23.314.815 I slot print_timing: id 0 | task 1394 | n_gen = 310, tg = 23.13 t/s, tg_3s = 24.41 t/s 2.23.559.349 I slot print_timing: id 1 | task 1333 | n_gen = 377, tg = 22.35 t/s, tg_3s = 24.59 t/s 2.24.371.536 I slot print_timing: id 3 | task 1631 | n_gen = 100, tg = 24.63 t/s, tg_3s = 24.88 t/s 2.25.629.897 I slot print_timing: id 2 | task 1041 | n_gen = 717, tg = 22.25 t/s, tg_3s = 24.63 t/s 2.26.319.584 I slot print_timing: id 0 | task 1394 | n_gen = 384, tg = 23.41 t/s, tg_3s = 24.63 t/s 2.26.563.647 I slot print_timing: id 1 | task 1333 | n_gen = 451, tg = 22.70 t/s, tg_3s = 24.63 t/s 2.27.375.702 I slot print_timing: id 3 | task 1631 | n_gen = 174, tg = 24.63 t/s, tg_3s = 24.63 t/s 2.27.536.961 I slot print_timing: id 0 | task 1394 | prompt eval time = 869.32 ms / 531 tokens ( 1.64 ms per token, 610.82 tokens per second) 2.27.536.967 I slot print_timing: id 0 | task 1394 | eval time = 17580.52 ms / 414 tokens ( 42.57 ms per token, 23.49 tokens per second) 2.27.536.968 I slot print_timing: id 0 | task 1394 | total time = 18449.84 ms / 945 tokens 2.27.536.969 I slot print_timing: id 0 | task 1394 | graphs reused = 1472 2.27.536.970 I slot print_timing: id 0 | task 1394 | graph reallocs = 0 / 0 (same size) / (changed size) 2.27.537.070 I slot release: id 0 | task 1394 | stop processing: n_tokens = 1599, truncated = 0 2.27.573.861 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.668 2.27.573.898 I slot launch_slot_: id 0 | task 1813 | processing task, is_child = 0 2.28.638.265 I slot print_timing: id 2 | task 1041 | n_gen = 775, tg = 21.99 t/s, tg_3s = 19.28 t/s 2.29.570.130 I slot print_timing: id 1 | task 1333 | n_gen = 509, tg = 22.25 t/s, tg_3s = 19.29 t/s 2.30.381.181 I slot print_timing: id 3 | task 1631 | n_gen = 232, tg = 23.03 t/s, tg_3s = 19.30 t/s 2.31.027.050 I slot print_timing: id 1 | task 1333 | prompt eval time = 772.58 ms / 512 tokens ( 1.51 ms per token, 662.71 tokens per second) 2.31.027.057 I slot print_timing: id 1 | task 1333 | eval time = 24291.10 ms / 545 tokens ( 44.65 ms per token, 22.40 tokens per second) 2.31.027.058 I slot print_timing: id 1 | task 1333 | total time = 25063.68 ms / 1057 tokens 2.31.027.062 I slot print_timing: id 1 | task 1333 | graphs reused = 1539 2.31.027.063 I slot print_timing: id 1 | task 1333 | graph reallocs = 0 / 0 (same size) / (changed size) 2.31.027.165 I slot release: id 1 | task 1333 | stop processing: n_tokens = 1699, truncated = 0 2.31.070.963 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.629 2.31.071.002 I slot launch_slot_: id 1 | task 1884 | processing task, is_child = 0 2.31.760.186 I slot print_timing: id 2 | task 1041 | n_gen = 836, tg = 21.79 t/s, tg_3s = 19.54 t/s 2.33.016.104 I slot print_timing: id 0 | task 1813 | n_gen = 100, tg = 21.04 t/s, tg_3s = 21.25 t/s 2.33.386.258 I slot print_timing: id 3 | task 1631 | n_gen = 289, tg = 22.10 t/s, tg_3s = 18.97 t/s 2.34.764.152 I slot print_timing: id 2 | task 1041 | n_gen = 909, tg = 21.98 t/s, tg_3s = 24.30 t/s 2.35.859.171 I slot print_timing: id 1 | task 1884 | n_gen = 100, tg = 24.61 t/s, tg_3s = 24.86 t/s 2.36.020.728 I slot print_timing: id 0 | task 1813 | n_gen = 174, tg = 22.44 t/s, tg_3s = 24.63 t/s 2.36.387.196 I slot print_timing: id 3 | task 1631 | n_gen = 363, tg = 22.58 t/s, tg_3s = 24.66 t/s 2.37.770.379 I slot print_timing: id 2 | task 1041 | n_gen = 983, tg = 22.15 t/s, tg_3s = 24.62 t/s 2.38.868.492 I slot print_timing: id 1 | task 1884 | n_gen = 174, tg = 24.60 t/s, tg_3s = 24.59 t/s 2.39.031.134 I slot print_timing: id 0 | task 1813 | n_gen = 248, tg = 23.04 t/s, tg_3s = 24.58 t/s 2.39.400.348 I slot print_timing: id 3 | task 1631 | n_gen = 437, tg = 22.89 t/s, tg_3s = 24.56 t/s 2.39.440.504 I slot print_timing: id 2 | task 1041 | prompt eval time = 987.91 ms / 548 tokens ( 1.80 ms per token, 554.71 tokens per second) 2.39.440.511 I slot print_timing: id 2 | task 1041 | eval time = 45994.32 ms / 1024 tokens ( 44.96 ms per token, 22.24 tokens per second) 2.39.440.512 I slot print_timing: id 2 | task 1041 | total time = 46982.23 ms / 1572 tokens 2.39.440.513 I slot print_timing: id 2 | task 1041 | graphs reused = 1724 2.39.440.513 I slot print_timing: id 2 | task 1041 | graph reallocs = 0 / 0 (same size) / (changed size) 2.39.440.629 I slot release: id 2 | task 1041 | stop processing: n_tokens = 2203, truncated = 0 2.39.483.715 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.485 2.39.489.832 I slot launch_slot_: id 2 | task 2075 | processing task, is_child = 0 2.41.891.611 I slot print_timing: id 1 | task 1884 | n_gen = 232, tg = 22.97 t/s, tg_3s = 19.19 t/s 2.42.053.230 I slot print_timing: id 0 | task 1813 | n_gen = 306, tg = 22.19 t/s, tg_3s = 19.19 t/s 2.42.419.419 I slot print_timing: id 3 | task 1631 | n_gen = 495, tg = 22.39 t/s, tg_3s = 19.21 t/s 2.44.243.226 I slot print_timing: id 2 | task 2075 | n_gen = 100, tg = 24.67 t/s, tg_3s = 24.92 t/s 2.44.893.059 I slot print_timing: id 1 | task 1884 | n_gen = 306, tg = 23.36 t/s, tg_3s = 24.65 t/s 2.45.055.493 I slot print_timing: id 0 | task 1813 | n_gen = 380, tg = 22.63 t/s, tg_3s = 24.65 t/s 2.45.422.878 I slot print_timing: id 3 | task 1631 | n_gen = 569, tg = 22.66 t/s, tg_3s = 24.64 t/s 2.47.254.263 I slot print_timing: id 2 | task 2075 | n_gen = 174, tg = 24.63 t/s, tg_3s = 24.58 t/s 2.47.902.693 I slot print_timing: id 1 | task 1884 | n_gen = 380, tg = 23.59 t/s, tg_3s = 24.59 t/s 2.48.064.767 I slot print_timing: id 0 | task 1813 | n_gen = 454, tg = 22.93 t/s, tg_3s = 24.59 t/s 2.48.431.669 I slot print_timing: id 3 | task 1631 | n_gen = 643, tg = 22.86 t/s, tg_3s = 24.59 t/s 2.50.257.052 I slot print_timing: id 2 | task 2075 | n_gen = 248, tg = 24.63 t/s, tg_3s = 24.64 t/s 2.50.903.961 I slot print_timing: id 1 | task 1884 | n_gen = 454, tg = 23.76 t/s, tg_3s = 24.66 t/s 2.51.065.326 I slot print_timing: id 0 | task 1813 | n_gen = 528, tg = 23.16 t/s, tg_3s = 24.66 t/s 2.51.471.447 I slot print_timing: id 3 | task 1631 | n_gen = 718, tg = 23.04 t/s, tg_3s = 24.67 t/s 2.53.258.323 I slot print_timing: id 2 | task 2075 | n_gen = 322, tg = 24.64 t/s, tg_3s = 24.66 t/s 2.53.907.406 I slot print_timing: id 1 | task 1884 | n_gen = 528, tg = 23.88 t/s, tg_3s = 24.64 t/s 2.53.908.457 I slot print_timing: id 3 | task 1631 | prompt eval time = 958.49 ms / 546 tokens ( 1.76 ms per token, 569.65 tokens per second) 2.53.908.460 I slot print_timing: id 3 | task 1631 | eval time = 33556.01 ms / 778 tokens ( 43.19 ms per token, 23.16 tokens per second) 2.53.908.461 I slot print_timing: id 3 | task 1631 | total time = 34514.50 ms / 1324 tokens 2.53.908.462 I slot print_timing: id 3 | task 1631 | graphs reused = 2059 2.53.908.463 I slot print_timing: id 3 | task 1631 | graph reallocs = 0 / 0 (same size) / (changed size) 2.53.908.568 I slot release: id 3 | task 1631 | stop processing: n_tokens = 1988, truncated = 0 2.53.943.807 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.537 2.53.943.846 I slot launch_slot_: id 3 | task 2416 | processing task, is_child = 0 2.54.561.257 I slot print_timing: id 0 | task 1813 | n_gen = 600, tg = 22.82 t/s, tg_3s = 20.60 t/s 2.56.296.826 I slot print_timing: id 2 | task 2075 | n_gen = 382, tg = 23.71 t/s, tg_3s = 19.75 t/s 2.56.945.650 I slot print_timing: id 1 | task 1884 | n_gen = 588, tg = 23.38 t/s, tg_3s = 19.75 t/s 2.57.594.220 I slot print_timing: id 0 | task 1813 | n_gen = 674, tg = 22.98 t/s, tg_3s = 24.40 t/s 2.58.648.344 I slot print_timing: id 3 | task 2416 | n_gen = 100, tg = 24.64 t/s, tg_3s = 24.89 t/s 2.59.336.105 I slot print_timing: id 2 | task 2075 | n_gen = 457, tg = 23.87 t/s, tg_3s = 24.68 t/s 2.59.456.115 I slot print_timing: id 0 | task 1813 | prompt eval time = 736.25 ms / 498 tokens ( 1.48 ms per token, 676.40 tokens per second) 2.59.456.122 I slot print_timing: id 0 | task 1813 | eval time = 31145.96 ms / 720 tokens ( 43.32 ms per token, 23.08 tokens per second) 2.59.456.123 I slot print_timing: id 0 | task 1813 | total time = 31882.21 ms / 1218 tokens 2.59.456.124 I slot print_timing: id 0 | task 1813 | graphs reused = 2176 2.59.456.124 I slot print_timing: id 0 | task 1813 | graph reallocs = 0 / 0 (same size) / (changed size) 2.59.456.221 I slot release: id 0 | task 1813 | stop processing: n_tokens = 1887, truncated = 0 2.59.492.812 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.916 (> 0.100 thold), f_keep = 0.566 2.59.492.848 I slot launch_slot_: id 0 | task 2539 | processing task, is_child = 0 3.00.162.008 I slot print_timing: id 1 | task 1884 | n_gen = 652, tg = 22.98 t/s, tg_3s = 19.90 t/s 3.01.686.166 I slot print_timing: id 3 | task 2416 | n_gen = 159, tg = 22.39 t/s, tg_3s = 19.42 t/s 3.02.374.928 I slot print_timing: id 2 | task 2075 | n_gen = 516, tg = 23.26 t/s, tg_3s = 19.42 t/s 3.03.185.718 I slot print_timing: id 1 | task 1884 | n_gen = 726, tg = 23.13 t/s, tg_3s = 24.47 t/s 3.04.238.077 I slot print_timing: id 0 | task 2539 | n_gen = 100, tg = 24.69 t/s, tg_3s = 24.94 t/s 3.04.725.592 I slot print_timing: id 3 | task 2416 | n_gen = 234, tg = 23.08 t/s, tg_3s = 24.68 t/s 3.05.415.459 I slot print_timing: id 2 | task 2075 | n_gen = 591, tg = 23.43 t/s, tg_3s = 24.67 t/s 3.06.187.724 I slot print_timing: id 1 | task 1884 | n_gen = 800, tg = 23.26 t/s, tg_3s = 24.65 t/s 3.07.246.754 I slot print_timing: id 0 | task 2539 | n_gen = 174, tg = 24.65 t/s, tg_3s = 24.60 t/s 3.07.738.693 I slot print_timing: id 3 | task 2416 | n_gen = 308, tg = 23.42 t/s, tg_3s = 24.56 t/s 3.08.428.215 I slot print_timing: id 2 | task 2075 | n_gen = 665, tg = 23.55 t/s, tg_3s = 24.56 t/s 3.09.198.682 I slot print_timing: id 1 | task 1884 | n_gen = 874, tg = 23.37 t/s, tg_3s = 24.58 t/s 3.09.970.731 I slot print_timing: id 2 | task 2075 | prompt eval time = 739.78 ms / 479 tokens ( 1.54 ms per token, 647.49 tokens per second) 3.09.970.737 I slot print_timing: id 2 | task 2075 | eval time = 29741.10 ms / 703 tokens ( 42.37 ms per token, 23.60 tokens per second) 3.09.970.738 I slot print_timing: id 2 | task 2075 | total time = 30480.88 ms / 1182 tokens 3.09.970.739 I slot print_timing: id 2 | task 2075 | graphs reused = 2416 3.09.970.740 I slot print_timing: id 2 | task 2075 | graph reallocs = 0 / 0 (same size) / (changed size) 3.09.970.848 I slot release: id 2 | task 2075 | stop processing: n_tokens = 1845, truncated = 0 3.10.014.068 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.579 3.10.014.105 I slot launch_slot_: id 2 | task 2783 | processing task, is_child = 0 3.10.825.328 I slot print_timing: id 0 | task 2539 | n_gen = 244, tg = 22.93 t/s, tg_3s = 19.56 t/s 3.10.825.876 I slot print_timing: id 3 | task 2416 | n_gen = 366, tg = 22.54 t/s, tg_3s = 18.79 t/s 3.12.211.941 I slot print_timing: id 1 | task 1884 | n_gen = 929, tg = 22.98 t/s, tg_3s = 18.25 t/s 3.13.839.212 I slot print_timing: id 0 | task 2539 | n_gen = 317, tg = 23.22 t/s, tg_3s = 24.22 t/s 3.13.840.828 I slot print_timing: id 3 | task 2416 | n_gen = 439, tg = 22.80 t/s, tg_3s = 24.21 t/s 3.14.930.740 I slot print_timing: id 2 | task 2783 | n_gen = 100, tg = 24.58 t/s, tg_3s = 24.82 t/s 3.15.215.056 I slot print_timing: id 1 | task 1884 | n_gen = 1003, tg = 23.10 t/s, tg_3s = 24.64 t/s 3.16.071.970 I slot print_timing: id 1 | task 1884 | prompt eval time = 765.58 ms / 502 tokens ( 1.53 ms per token, 655.72 tokens per second) 3.16.071.974 I slot print_timing: id 1 | task 1884 | eval time = 44235.38 ms / 1024 tokens ( 43.24 ms per token, 23.13 tokens per second) 3.16.071.975 I slot print_timing: id 1 | task 1884 | total time = 45000.96 ms / 1526 tokens 3.16.071.976 I slot print_timing: id 1 | task 1884 | graphs reused = 2541 3.16.071.976 I slot print_timing: id 1 | task 1884 | graph reallocs = 0 / 0 (same size) / (changed size) 3.16.072.087 I slot release: id 1 | task 1884 | stop processing: n_tokens = 2168, truncated = 0 3.16.115.935 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.947 (> 0.100 thold), f_keep = 0.493 3.16.121.806 I slot launch_slot_: id 1 | task 2915 | processing task, is_child = 0 3.16.865.069 I slot print_timing: id 0 | task 2539 | n_gen = 375, tg = 22.48 t/s, tg_3s = 19.17 t/s 3.16.865.908 I slot print_timing: id 3 | task 2416 | n_gen = 497, tg = 22.31 t/s, tg_3s = 19.17 t/s 3.17.961.764 I slot print_timing: id 2 | task 2783 | n_gen = 158, tg = 22.24 t/s, tg_3s = 19.14 t/s 3.19.870.078 I slot print_timing: id 0 | task 2539 | n_gen = 449, tg = 22.81 t/s, tg_3s = 24.63 t/s 3.19.871.819 I slot print_timing: id 3 | task 2416 | n_gen = 571, tg = 22.58 t/s, tg_3s = 24.62 t/s 3.20.887.405 I slot print_timing: id 1 | task 2915 | n_gen = 100, tg = 24.61 t/s, tg_3s = 24.86 t/s 3.20.968.785 I slot print_timing: id 2 | task 2783 | n_gen = 232, tg = 22.95 t/s, tg_3s = 24.61 t/s 3.22.872.294 I slot print_timing: id 0 | task 2539 | n_gen = 523, tg = 23.05 t/s, tg_3s = 24.65 t/s 3.22.873.804 I slot print_timing: id 3 | task 2416 | n_gen = 645, tg = 22.80 t/s, tg_3s = 24.65 t/s 3.23.927.390 I slot print_timing: id 1 | task 2915 | n_gen = 175, tg = 24.64 t/s, tg_3s = 24.67 t/s 3.24.008.666 I slot print_timing: id 2 | task 2783 | n_gen = 307, tg = 23.35 t/s, tg_3s = 24.67 t/s 3.24.292.343 I slot print_timing: id 3 | task 2416 | prompt eval time = 687.15 ms / 442 tokens ( 1.55 ms per token, 643.23 tokens per second) 3.24.292.350 I slot print_timing: id 3 | task 2416 | eval time = 29661.33 ms / 680 tokens ( 43.68 ms per token, 22.89 tokens per second) 3.24.292.351 I slot print_timing: id 3 | task 2416 | total time = 30348.48 ms / 1122 tokens 3.24.292.352 I slot print_timing: id 3 | task 2416 | graphs reused = 2722 3.24.292.353 I slot print_timing: id 3 | task 2416 | graph reallocs = 0 / 0 (same size) / (changed size) 3.24.292.450 I slot release: id 3 | task 2416 | stop processing: n_tokens = 1816, truncated = 0 3.24.327.591 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.588 3.24.327.625 I slot launch_slot_: id 3 | task 3102 | processing task, is_child = 0 3.25.326.903 I slot print_timing: id 0 | task 2539 | prompt eval time = 735.48 ms / 496 tokens ( 1.48 ms per token, 674.39 tokens per second) 3.25.326.908 I slot print_timing: id 0 | task 2539 | eval time = 25098.57 ms / 568 tokens ( 44.27 ms per token, 22.59 tokens per second) 3.25.326.909 I slot print_timing: id 0 | task 2539 | total time = 25834.05 ms / 1064 tokens 3.25.326.909 I slot print_timing: id 0 | task 2539 | graphs reused = 2728 3.25.326.910 I slot print_timing: id 0 | task 2539 | graph reallocs = 0 / 0 (same size) / (changed size) 3.25.326.974 I slot release: id 0 | task 2539 | stop processing: n_tokens = 1733, truncated = 0 3.25.361.951 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.616 3.25.361.978 I slot launch_slot_: id 0 | task 3113 | processing task, is_child = 0 3.26.959.148 I slot print_timing: id 1 | task 2915 | n_gen = 219, tg = 21.60 t/s, tg_3s = 14.51 t/s 3.27.040.821 I slot print_timing: id 2 | task 2783 | n_gen = 351, tg = 21.69 t/s, tg_3s = 14.51 t/s 3.29.672.952 I slot print_timing: id 3 | task 3102 | n_gen = 100, tg = 21.41 t/s, tg_3s = 21.63 t/s 3.29.995.710 I slot print_timing: id 1 | task 2915 | n_gen = 294, tg = 22.31 t/s, tg_3s = 24.70 t/s 3.30.076.128 I slot print_timing: id 0 | task 3113 | n_gen = 100, tg = 24.72 t/s, tg_3s = 24.97 t/s 3.30.077.309 I slot print_timing: id 2 | task 2783 | n_gen = 426, tg = 22.16 t/s, tg_3s = 24.70 t/s 3.32.673.314 I slot print_timing: id 3 | task 3102 | n_gen = 174, tg = 22.69 t/s, tg_3s = 24.66 t/s 3.32.997.357 I slot print_timing: id 1 | task 2915 | n_gen = 368, tg = 22.75 t/s, tg_3s = 24.65 t/s 3.33.078.356 I slot print_timing: id 0 | task 3113 | n_gen = 174, tg = 24.69 t/s, tg_3s = 24.65 t/s 3.33.079.495 I slot print_timing: id 2 | task 2783 | n_gen = 500, tg = 22.50 t/s, tg_3s = 24.65 t/s 3.35.684.404 I slot print_timing: id 3 | task 3102 | n_gen = 248, tg = 23.23 t/s, tg_3s = 24.58 t/s 3.36.008.095 I slot print_timing: id 1 | task 2915 | n_gen = 442, tg = 23.04 t/s, tg_3s = 24.58 t/s 3.36.088.901 I slot print_timing: id 0 | task 3113 | n_gen = 248, tg = 24.66 t/s, tg_3s = 24.58 t/s 3.36.090.082 I slot print_timing: id 2 | task 2783 | n_gen = 574, tg = 22.75 t/s, tg_3s = 24.58 t/s 3.38.689.853 I slot print_timing: id 3 | task 3102 | n_gen = 322, tg = 23.53 t/s, tg_3s = 24.62 t/s 3.39.013.329 I slot print_timing: id 1 | task 2915 | n_gen = 516, tg = 23.25 t/s, tg_3s = 24.62 t/s 3.39.094.074 I slot print_timing: id 0 | task 3113 | n_gen = 322, tg = 24.65 t/s, tg_3s = 24.62 t/s 3.39.095.151 I slot print_timing: id 2 | task 2783 | n_gen = 648, tg = 22.95 t/s, tg_3s = 24.63 t/s 3.41.212.505 I slot print_timing: id 0 | task 3113 | prompt eval time = 708.87 ms / 472 tokens ( 1.50 ms per token, 665.85 tokens per second) 3.41.212.509 I slot print_timing: id 0 | task 3113 | eval time = 15141.65 ms / 374 tokens ( 40.59 ms per token, 24.63 tokens per second) 3.41.212.510 I slot print_timing: id 0 | task 3113 | total time = 15850.52 ms / 846 tokens 3.41.212.511 I slot print_timing: id 0 | task 3113 | graphs reused = 3099 3.41.212.512 I slot print_timing: id 0 | task 3113 | graph reallocs = 0 / 0 (same size) / (changed size) 3.41.212.610 I slot release: id 0 | task 3113 | stop processing: n_tokens = 1515, truncated = 0 3.41.249.771 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.947 (> 0.100 thold), f_keep = 0.705 3.41.249.807 I slot launch_slot_: id 0 | task 3490 | processing task, is_child = 0 3.41.882.517 I slot print_timing: id 3 | task 3102 | n_gen = 386, tg = 22.87 t/s, tg_3s = 20.05 t/s 3.42.029.136 I slot print_timing: id 1 | task 2915 | n_gen = 575, tg = 22.81 t/s, tg_3s = 19.56 t/s 3.42.108.519 I slot print_timing: id 2 | task 2783 | n_gen = 707, tg = 22.62 t/s, tg_3s = 19.58 t/s 3.44.888.034 I slot print_timing: id 3 | task 3102 | n_gen = 460, tg = 23.14 t/s, tg_3s = 24.62 t/s 3.45.048.670 I slot print_timing: id 1 | task 2915 | n_gen = 650, tg = 23.03 t/s, tg_3s = 24.84 t/s 3.45.129.821 I slot print_timing: id 2 | task 2783 | n_gen = 782, tg = 22.82 t/s, tg_3s = 24.82 t/s 3.45.940.331 I slot print_timing: id 0 | task 3490 | n_gen = 100, tg = 24.80 t/s, tg_3s = 25.05 t/s 3.46.550.865 I slot print_timing: id 1 | task 2915 | prompt eval time = 743.56 ms / 485 tokens ( 1.53 ms per token, 652.27 tokens per second) 3.46.550.872 I slot print_timing: id 1 | task 2915 | eval time = 29685.48 ms / 687 tokens ( 43.27 ms per token, 23.11 tokens per second) 3.46.550.873 I slot print_timing: id 1 | task 2915 | total time = 30429.04 ms / 1172 tokens 3.46.550.874 I slot print_timing: id 1 | task 2915 | graphs reused = 3213 3.46.550.874 I slot print_timing: id 1 | task 2915 | graph reallocs = 0 / 0 (same size) / (changed size) 3.46.550.972 I slot release: id 1 | task 2915 | stop processing: n_tokens = 1814, truncated = 0 3.46.594.567 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.589 3.46.594.610 I slot launch_slot_: id 1 | task 3608 | processing task, is_child = 0 3.47.901.374 I slot print_timing: id 3 | task 3102 | n_gen = 517, tg = 22.58 t/s, tg_3s = 18.92 t/s 3.48.143.531 I slot print_timing: id 2 | task 2783 | n_gen = 839, tg = 22.50 t/s, tg_3s = 18.91 t/s 3.48.713.046 I slot print_timing: id 3 | task 3102 | prompt eval time = 721.70 ms / 475 tokens ( 1.52 ms per token, 658.17 tokens per second) 3.48.713.055 I slot print_timing: id 3 | task 3102 | eval time = 23663.72 ms / 537 tokens ( 44.15 ms per token, 22.65 tokens per second) 3.48.713.055 I slot print_timing: id 3 | task 3102 | total time = 24385.41 ms / 1012 tokens 3.48.713.056 I slot print_timing: id 3 | task 3102 | graphs reused = 3245 3.48.713.057 I slot print_timing: id 3 | task 3102 | graph reallocs = 0 / 0 (same size) / (changed size) 3.48.713.167 I slot release: id 3 | task 3102 | stop processing: n_tokens = 1706, truncated = 0 3.48.747.916 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.626 3.48.747.945 I slot launch_slot_: id 3 | task 3645 | processing task, is_child = 0 3.49.365.933 I slot print_timing: id 0 | task 3490 | n_gen = 153, tg = 20.49 t/s, tg_3s = 15.47 t/s 3.51.147.216 I slot print_timing: id 2 | task 2783 | n_gen = 898, tg = 22.29 t/s, tg_3s = 19.64 t/s 3.51.999.133 I slot print_timing: id 1 | task 3608 | n_gen = 100, tg = 21.38 t/s, tg_3s = 21.60 t/s 3.52.405.056 I slot print_timing: id 0 | task 3490 | n_gen = 227, tg = 21.61 t/s, tg_3s = 24.35 t/s 3.53.467.065 I slot print_timing: id 3 | task 3645 | n_gen = 100, tg = 24.56 t/s, tg_3s = 24.80 t/s 3.54.159.375 I slot print_timing: id 2 | task 2783 | n_gen = 972, tg = 22.45 t/s, tg_3s = 24.57 t/s 3.54.932.139 I slot print_timing: id 0 | task 3490 | prompt eval time = 698.76 ms / 458 tokens ( 1.53 ms per token, 655.45 tokens per second) 3.54.932.147 I slot print_timing: id 0 | task 3490 | eval time = 12983.57 ms / 289 tokens ( 45.08 ms per token, 22.18 tokens per second) 3.54.932.148 I slot print_timing: id 0 | task 3490 | total time = 13682.33 ms / 747 tokens 3.54.932.149 I slot print_timing: id 0 | task 3490 | graphs reused = 3378 3.54.932.149 I slot print_timing: id 0 | task 3490 | graph reallocs = 0 / 0 (same size) / (changed size) 3.54.932.244 I slot release: id 0 | task 3490 | stop processing: n_tokens = 1416, truncated = 0 3.54.969.150 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.754 3.54.969.187 I slot launch_slot_: id 0 | task 3784 | processing task, is_child = 0 3.55.647.463 I slot print_timing: id 1 | task 3608 | n_gen = 174, tg = 20.90 t/s, tg_3s = 20.28 t/s 3.56.482.958 I slot print_timing: id 3 | task 3645 | n_gen = 158, tg = 22.28 t/s, tg_3s = 19.23 t/s 3.56.931.634 I slot print_timing: id 2 | task 2783 | prompt eval time = 888.17 ms / 527 tokens ( 1.69 ms per token, 593.35 tokens per second) 3.56.931.639 I slot print_timing: id 2 | task 2783 | eval time = 46029.35 ms / 1024 tokens ( 44.99 ms per token, 22.22 tokens per second) 3.56.931.640 I slot print_timing: id 2 | task 2783 | total time = 46917.52 ms / 1551 tokens 3.56.931.640 I slot print_timing: id 2 | task 2783 | graphs reused = 3408 3.56.931.641 I slot print_timing: id 2 | task 2783 | graph reallocs = 0 / 0 (same size) / (changed size) 3.56.931.760 I slot release: id 2 | task 2783 | stop processing: n_tokens = 2214, truncated = 0 3.56.974.952 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.943 (> 0.100 thold), f_keep = 0.482 3.56.981.111 I slot launch_slot_: id 2 | task 3818 | processing task, is_child = 0 3.58.673.187 I slot print_timing: id 1 | task 3608 | n_gen = 232, tg = 20.43 t/s, tg_3s = 19.17 t/s 3.59.485.763 I slot print_timing: id 3 | task 3645 | n_gen = 216, tg = 21.39 t/s, tg_3s = 19.32 t/s 4.00.373.795 I slot print_timing: id 0 | task 3784 | n_gen = 100, tg = 21.24 t/s, tg_3s = 21.46 t/s 4.01.708.036 I slot print_timing: id 1 | task 3608 | n_gen = 307, tg = 21.34 t/s, tg_3s = 24.71 t/s 4.01.708.631 I slot print_timing: id 2 | task 3818 | n_gen = 100, tg = 24.72 t/s, tg_3s = 24.97 t/s 4.02.518.340 I slot print_timing: id 3 | task 3645 | n_gen = 291, tg = 22.17 t/s, tg_3s = 24.73 t/s 4.03.407.635 I slot print_timing: id 0 | task 3784 | n_gen = 175, tg = 22.62 t/s, tg_3s = 24.72 t/s 4.04.417.841 I slot print_timing: id 1 | task 3608 | prompt eval time = 774.26 ms / 502 tokens ( 1.54 ms per token, 648.36 tokens per second) 4.04.417.853 I slot print_timing: id 1 | task 3608 | eval time = 17048.96 ms / 374 tokens ( 45.71 ms per token, 21.88 tokens per second) 4.04.417.853 I slot print_timing: id 1 | task 3608 | total time = 17823.22 ms / 876 tokens 4.04.417.854 I slot print_timing: id 1 | task 3608 | graphs reused = 3573 4.04.417.859 I slot print_timing: id 1 | task 3608 | graph reallocs = 0 / 0 (same size) / (changed size) 4.04.417.960 I slot release: id 1 | task 3608 | stop processing: n_tokens = 1518, truncated = 0 4.04.461.827 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.704 4.04.461.873 I slot launch_slot_: id 1 | task 3988 | processing task, is_child = 0 4.05.145.255 I slot print_timing: id 2 | task 3818 | n_gen = 169, tg = 22.57 t/s, tg_3s = 20.08 t/s 4.05.540.282 I slot print_timing: id 3 | task 3645 | n_gen = 349, tg = 21.61 t/s, tg_3s = 19.19 t/s 4.05.950.591 I slot print_timing: id 3 | task 3645 | prompt eval time = 687.50 ms / 443 tokens ( 1.55 ms per token, 644.37 tokens per second) 4.05.950.596 I slot print_timing: id 3 | task 3645 | eval time = 16515.14 ms / 359 tokens ( 46.13 ms per token, 21.68 tokens per second) 4.05.950.597 I slot print_timing: id 3 | task 3645 | total time = 17202.64 ms / 802 tokens 4.05.950.597 I slot print_timing: id 3 | task 3645 | graphs reused = 3590 4.05.950.598 I slot print_timing: id 3 | task 3645 | graph reallocs = 0 / 0 (same size) / (changed size) 4.05.950.693 I slot release: id 3 | task 3645 | stop processing: n_tokens = 1496, truncated = 0 4.05.985.743 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.945 (> 0.100 thold), f_keep = 0.714 4.05.985.783 I slot launch_slot_: id 3 | task 4010 | processing task, is_child = 0 4.06.597.984 I slot print_timing: id 0 | task 3784 | n_gen = 223, tg = 20.40 t/s, tg_3s = 15.05 t/s 4.08.162.256 I slot print_timing: id 2 | task 3818 | n_gen = 228, tg = 21.70 t/s, tg_3s = 19.56 t/s 4.09.612.468 I slot print_timing: id 0 | task 3784 | n_gen = 297, tg = 21.30 t/s, tg_3s = 24.55 t/s 4.09.814.518 I slot print_timing: id 1 | task 3988 | n_gen = 100, tg = 21.56 t/s, tg_3s = 21.77 t/s 4.10.661.813 I slot print_timing: id 3 | task 4010 | n_gen = 100, tg = 24.79 t/s, tg_3s = 25.04 t/s 4.11.185.619 I slot print_timing: id 2 | task 3818 | n_gen = 303, tg = 22.40 t/s, tg_3s = 24.81 t/s 4.12.561.818 I slot print_timing: id 2 | task 3818 | prompt eval time = 722.13 ms / 458 tokens ( 1.58 ms per token, 634.23 tokens per second) 4.12.561.825 I slot print_timing: id 2 | task 3818 | eval time = 14858.56 ms / 337 tokens ( 44.22 ms per token, 22.61 tokens per second) 4.12.561.826 I slot print_timing: id 2 | task 3818 | total time = 15580.69 ms / 795 tokens 4.12.561.827 I slot print_timing: id 2 | task 3818 | graphs reused = 3734 4.12.561.828 I slot print_timing: id 2 | task 3818 | graph reallocs = 0 / 0 (same size) / (changed size) 4.12.561.938 I slot release: id 2 | task 3818 | stop processing: n_tokens = 1469, truncated = 0 4.12.605.022 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.911 (> 0.100 thold), f_keep = 0.728 4.12.605.063 I slot launch_slot_: id 2 | task 4160 | processing task, is_child = 0 4.13.290.664 I slot print_timing: id 0 | task 3784 | n_gen = 372, tg = 21.11 t/s, tg_3s = 20.39 t/s 4.13.290.943 I slot print_timing: id 1 | task 3988 | n_gen = 170, tg = 20.94 t/s, tg_3s = 20.14 t/s 4.13.689.297 I slot print_timing: id 3 | task 4010 | n_gen = 158, tg = 22.36 t/s, tg_3s = 19.16 t/s 4.16.321.391 I slot print_timing: id 0 | task 3784 | n_gen = 446, tg = 21.59 t/s, tg_3s = 24.42 t/s 4.16.321.978 I slot print_timing: id 1 | task 3988 | n_gen = 244, tg = 21.89 t/s, tg_3s = 24.41 t/s 4.16.728.960 I slot print_timing: id 3 | task 4010 | n_gen = 233, tg = 23.06 t/s, tg_3s = 24.67 t/s 4.17.375.420 I slot print_timing: id 2 | task 4160 | n_gen = 100, tg = 24.70 t/s, tg_3s = 24.95 t/s 4.19.322.569 I slot print_timing: id 0 | task 3784 | n_gen = 520, tg = 21.98 t/s, tg_3s = 24.66 t/s 4.19.323.096 I slot print_timing: id 1 | task 3988 | n_gen = 318, tg = 22.48 t/s, tg_3s = 24.66 t/s 4.19.729.645 I slot print_timing: id 3 | task 4010 | n_gen = 307, tg = 23.43 t/s, tg_3s = 24.66 t/s 4.20.379.883 I slot print_timing: id 2 | task 4160 | n_gen = 174, tg = 24.67 t/s, tg_3s = 24.63 t/s 4.22.327.111 I slot print_timing: id 0 | task 3784 | n_gen = 594, tg = 22.28 t/s, tg_3s = 24.63 t/s 4.22.327.625 I slot print_timing: id 1 | task 3988 | n_gen = 392, tg = 22.86 t/s, tg_3s = 24.63 t/s 4.22.734.283 I slot print_timing: id 3 | task 4010 | n_gen = 381, tg = 23.65 t/s, tg_3s = 24.63 t/s 4.23.384.572 I slot print_timing: id 2 | task 4160 | n_gen = 248, tg = 24.66 t/s, tg_3s = 24.63 t/s 4.25.330.193 I slot print_timing: id 0 | task 3784 | n_gen = 668, tg = 22.52 t/s, tg_3s = 24.64 t/s 4.25.330.710 I slot print_timing: id 1 | task 3988 | n_gen = 466, tg = 23.12 t/s, tg_3s = 24.64 t/s 4.25.738.838 I slot print_timing: id 3 | task 4010 | n_gen = 455, tg = 23.81 t/s, tg_3s = 24.63 t/s 4.26.386.980 I slot print_timing: id 2 | task 4160 | n_gen = 322, tg = 24.65 t/s, tg_3s = 24.65 t/s 4.27.887.835 I slot print_timing: id 1 | task 3988 | prompt eval time = 759.89 ms / 494 tokens ( 1.54 ms per token, 650.09 tokens per second) 4.27.887.842 I slot print_timing: id 1 | task 3988 | eval time = 22666.06 ms / 529 tokens ( 42.93 ms per token, 23.29 tokens per second) 4.27.887.843 I slot print_timing: id 1 | task 3988 | total time = 23425.95 ms / 1023 tokens 4.27.887.844 I slot print_timing: id 1 | task 3988 | graphs reused = 4090 4.27.887.845 I slot print_timing: id 1 | task 3988 | graph reallocs = 0 / 0 (same size) / (changed size) 4.27.887.955 I slot release: id 1 | task 3988 | stop processing: n_tokens = 1665, truncated = 0 4.27.931.660 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.641 4.27.931.702 I slot launch_slot_: id 1 | task 4522 | processing task, is_child = 0 4.28.771.933 I slot print_timing: id 0 | task 3784 | n_gen = 734, tg = 22.17 t/s, tg_3s = 19.18 t/s 4.28.772.506 I slot print_timing: id 3 | task 4010 | n_gen = 511, tg = 23.07 t/s, tg_3s = 18.46 t/s 4.28.889.252 I slot print_timing: id 0 | task 3784 | prompt eval time = 744.56 ms / 510 tokens ( 1.46 ms per token, 684.97 tokens per second) 4.28.889.257 I slot print_timing: id 0 | task 3784 | eval time = 33175.50 ms / 736 tokens ( 45.14 ms per token, 22.15 tokens per second) 4.28.889.257 I slot print_timing: id 0 | task 3784 | total time = 33920.06 ms / 1246 tokens 4.28.889.258 I slot print_timing: id 0 | task 3784 | graphs reused = 4090 4.28.889.258 I slot print_timing: id 0 | task 3784 | graph reallocs = 0 / 0 (same size) / (changed size) 4.28.889.320 I slot release: id 0 | task 3784 | stop processing: n_tokens = 1915, truncated = 0 4.28.923.371 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.898 (> 0.100 thold), f_keep = 0.558 4.28.923.397 I slot launch_slot_: id 0 | task 4528 | processing task, is_child = 0 4.29.663.381 I slot print_timing: id 2 | task 4160 | n_gen = 367, tg = 22.46 t/s, tg_3s = 13.73 t/s 4.31.804.638 I slot print_timing: id 3 | task 4010 | n_gen = 568, tg = 22.56 t/s, tg_3s = 18.80 t/s 4.32.691.742 I slot print_timing: id 2 | task 4160 | n_gen = 441, tg = 22.77 t/s, tg_3s = 24.44 t/s 4.33.539.902 I slot print_timing: id 1 | task 4522 | n_gen = 100, tg = 21.10 t/s, tg_3s = 21.32 t/s 4.33.742.376 I slot print_timing: id 0 | task 4528 | n_gen = 100, tg = 24.67 t/s, tg_3s = 24.92 t/s 4.34.835.754 I slot print_timing: id 3 | task 4010 | n_gen = 643, tg = 22.79 t/s, tg_3s = 24.74 t/s 4.35.159.606 I slot print_timing: id 3 | task 4010 | prompt eval time = 681.85 ms / 435 tokens ( 1.57 ms per token, 637.97 tokens per second) 4.35.159.612 I slot print_timing: id 3 | task 4010 | eval time = 28491.97 ms / 651 tokens ( 43.83 ms per token, 22.81 tokens per second) 4.35.159.613 I slot print_timing: id 3 | task 4010 | total time = 29173.81 ms / 1086 tokens 4.35.159.614 I slot print_timing: id 3 | task 4010 | graphs reused = 4224 4.35.159.614 I slot print_timing: id 3 | task 4010 | graph reallocs = 0 / 0 (same size) / (changed size) 4.35.159.712 I slot release: id 3 | task 4010 | stop processing: n_tokens = 1780, truncated = 0 4.35.194.424 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.600 4.35.194.453 I slot launch_slot_: id 3 | task 4667 | processing task, is_child = 0 4.35.813.819 I slot print_timing: id 2 | task 4160 | n_gen = 504, tg = 22.41 t/s, tg_3s = 20.18 t/s 4.36.565.281 I slot print_timing: id 1 | task 4522 | n_gen = 160, tg = 20.60 t/s, tg_3s = 19.83 t/s 4.36.767.913 I slot print_timing: id 0 | task 4528 | n_gen = 160, tg = 22.59 t/s, tg_3s = 19.83 t/s 4.38.833.906 I slot print_timing: id 2 | task 4160 | n_gen = 578, tg = 22.66 t/s, tg_3s = 24.50 t/s 4.39.601.550 I slot print_timing: id 1 | task 4522 | n_gen = 235, tg = 21.76 t/s, tg_3s = 24.70 t/s 4.39.803.269 I slot print_timing: id 0 | task 4528 | n_gen = 235, tg = 23.23 t/s, tg_3s = 24.71 t/s 4.39.885.120 I slot print_timing: id 3 | task 4667 | n_gen = 100, tg = 24.74 t/s, tg_3s = 24.99 t/s 4.41.869.595 I slot print_timing: id 2 | task 4160 | n_gen = 653, tg = 22.88 t/s, tg_3s = 24.71 t/s 4.42.640.045 I slot print_timing: id 1 | task 4522 | n_gen = 310, tg = 22.41 t/s, tg_3s = 24.68 t/s 4.42.841.826 I slot print_timing: id 0 | task 4528 | n_gen = 310, tg = 23.57 t/s, tg_3s = 24.68 t/s 4.42.924.267 I slot print_timing: id 3 | task 4667 | n_gen = 175, tg = 24.71 t/s, tg_3s = 24.68 t/s 4.44.910.376 I slot print_timing: id 2 | task 4160 | n_gen = 728, tg = 23.05 t/s, tg_3s = 24.66 t/s 4.45.641.311 I slot print_timing: id 1 | task 4522 | n_gen = 384, tg = 22.81 t/s, tg_3s = 24.66 t/s 4.45.844.349 I slot print_timing: id 0 | task 4528 | n_gen = 384, tg = 23.77 t/s, tg_3s = 24.65 t/s 4.45.927.356 I slot print_timing: id 3 | task 4667 | n_gen = 249, tg = 24.69 t/s, tg_3s = 24.64 t/s 4.47.912.775 I slot print_timing: id 2 | task 4160 | n_gen = 802, tg = 23.19 t/s, tg_3s = 24.65 t/s 4.48.681.507 I slot print_timing: id 1 | task 4522 | n_gen = 459, tg = 23.09 t/s, tg_3s = 24.67 t/s 4.48.883.447 I slot print_timing: id 0 | task 4528 | n_gen = 459, tg = 23.91 t/s, tg_3s = 24.68 t/s 4.48.966.308 I slot print_timing: id 3 | task 4667 | n_gen = 324, tg = 24.69 t/s, tg_3s = 24.68 t/s 4.50.919.350 I slot print_timing: id 2 | task 4160 | n_gen = 876, tg = 23.30 t/s, tg_3s = 24.61 t/s 4.51.697.105 I slot print_timing: id 1 | task 4522 | n_gen = 533, tg = 23.28 t/s, tg_3s = 24.54 t/s 4.51.900.554 I slot print_timing: id 0 | task 4528 | n_gen = 533, tg = 24.00 t/s, tg_3s = 24.53 t/s 4.51.984.074 I slot print_timing: id 3 | task 4667 | n_gen = 398, tg = 24.66 t/s, tg_3s = 24.52 t/s 4.53.941.440 I slot print_timing: id 2 | task 4160 | n_gen = 950, tg = 23.39 t/s, tg_3s = 24.49 t/s 4.54.712.881 I slot print_timing: id 1 | task 4522 | n_gen = 607, tg = 23.43 t/s, tg_3s = 24.54 t/s 4.54.915.873 I slot print_timing: id 0 | task 4528 | n_gen = 607, tg = 24.06 t/s, tg_3s = 24.54 t/s 4.54.998.610 I slot print_timing: id 3 | task 4667 | n_gen = 472, tg = 24.64 t/s, tg_3s = 24.55 t/s 4.56.960.227 I slot print_timing: id 2 | task 4160 | prompt eval time = 761.85 ms / 498 tokens ( 1.53 ms per token, 653.68 tokens per second) 4.56.960.235 I slot print_timing: id 2 | task 4160 | eval time = 43593.31 ms / 1024 tokens ( 42.61 ms per token, 23.47 tokens per second) 4.56.960.236 I slot print_timing: id 2 | task 4160 | total time = 44355.16 ms / 1522 tokens 4.56.960.237 I slot print_timing: id 2 | task 4160 | graphs reused = 4740 4.56.960.238 I slot print_timing: id 2 | task 4160 | graph reallocs = 0 / 0 (same size) / (changed size) 4.56.960.341 I slot release: id 2 | task 4160 | stop processing: n_tokens = 2196, truncated = 0 4.57.003.810 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.944 (> 0.100 thold), f_keep = 0.486 4.57.009.747 I slot launch_slot_: id 2 | task 5190 | processing task, is_child = 0 4.57.731.495 I slot print_timing: id 1 | task 4522 | n_gen = 665, tg = 22.99 t/s, tg_3s = 19.21 t/s 4.57.931.232 I slot print_timing: id 0 | task 4528 | n_gen = 665, tg = 23.54 t/s, tg_3s = 19.23 t/s 4.58.015.499 I slot print_timing: id 3 | task 4667 | n_gen = 530, tg = 23.90 t/s, tg_3s = 19.23 t/s 4.58.381.936 I slot print_timing: id 3 | task 4667 | prompt eval time = 688.52 ms / 442 tokens ( 1.56 ms per token, 641.96 tokens per second) 4.58.381.941 I slot print_timing: id 3 | task 4667 | eval time = 22498.96 ms / 539 tokens ( 41.82 ms per token, 23.91 tokens per second) 4.58.381.943 I slot print_timing: id 3 | task 4667 | total time = 23187.47 ms / 981 tokens 4.58.381.943 I slot print_timing: id 3 | task 4667 | graphs reused = 4755 4.58.381.944 I slot print_timing: id 3 | task 4667 | graph reallocs = 0 / 0 (same size) / (changed size) 4.58.382.040 I slot release: id 3 | task 4667 | stop processing: n_tokens = 1675, truncated = 0 4.58.417.238 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.638 4.58.417.278 I slot launch_slot_: id 3 | task 5210 | processing task, is_child = 0 5.00.762.425 I slot print_timing: id 1 | task 4522 | n_gen = 725, tg = 22.69 t/s, tg_3s = 19.80 t/s 5.00.964.456 I slot print_timing: id 0 | task 4528 | n_gen = 725, tg = 23.18 t/s, tg_3s = 19.78 t/s 5.02.342.757 I slot print_timing: id 2 | task 5190 | n_gen = 100, tg = 21.47 t/s, tg_3s = 21.69 t/s 5.03.111.257 I slot print_timing: id 3 | task 5210 | n_gen = 100, tg = 24.74 t/s, tg_3s = 24.99 t/s 5.03.798.349 I slot print_timing: id 1 | task 4522 | n_gen = 800, tg = 22.86 t/s, tg_3s = 24.70 t/s 5.04.000.092 I slot print_timing: id 0 | task 4528 | n_gen = 800, tg = 23.31 t/s, tg_3s = 24.71 t/s 5.05.176.807 I slot print_timing: id 1 | task 4522 | prompt eval time = 916.98 ms / 533 tokens ( 1.72 ms per token, 581.25 tokens per second) 5.05.176.816 I slot print_timing: id 1 | task 4522 | eval time = 36328.11 ms / 834 tokens ( 43.61 ms per token, 22.93 tokens per second) 5.05.176.817 I slot print_timing: id 1 | task 4522 | total time = 37245.10 ms / 1367 tokens 5.05.176.818 I slot print_timing: id 1 | task 4522 | graphs reused = 4904 5.05.176.818 I slot print_timing: id 1 | task 4522 | graph reallocs = 0 / 0 (same size) / (changed size) 5.05.176.922 I slot release: id 1 | task 4522 | stop processing: n_tokens = 2009, truncated = 0 5.05.220.373 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.532 5.05.220.417 I slot launch_slot_: id 1 | task 5364 | processing task, is_child = 0 5.05.900.527 I slot print_timing: id 2 | task 5190 | n_gen = 172, tg = 20.93 t/s, tg_3s = 20.24 t/s 5.06.137.744 I slot print_timing: id 3 | task 5210 | n_gen = 158, tg = 22.34 t/s, tg_3s = 19.16 t/s 5.07.028.750 I slot print_timing: id 0 | task 4528 | n_gen = 858, tg = 22.98 t/s, tg_3s = 19.15 t/s 5.07.559.813 I slot print_timing: id 0 | task 4528 | prompt eval time = 806.00 ms / 519 tokens ( 1.55 ms per token, 643.92 tokens per second) 5.07.559.817 I slot print_timing: id 0 | task 4528 | eval time = 37830.40 ms / 871 tokens ( 43.48 ms per token, 23.00 tokens per second) 5.07.559.818 I slot print_timing: id 0 | task 4528 | total time = 38636.41 ms / 1390 tokens 5.07.559.819 I slot print_timing: id 0 | task 4528 | graphs reused = 4941 5.07.559.820 I slot print_timing: id 0 | task 4528 | graph reallocs = 0 / 0 (same size) / (changed size) 5.07.559.923 I slot release: id 0 | task 4528 | stop processing: n_tokens = 2059, truncated = 0 5.07.596.631 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.519 5.07.596.667 I slot launch_slot_: id 0 | task 5407 | processing task, is_child = 0 5.08.925.072 I slot print_timing: id 2 | task 5190 | n_gen = 230, tg = 20.46 t/s, tg_3s = 19.18 t/s 5.09.168.094 I slot print_timing: id 3 | task 5210 | n_gen = 217, tg = 21.47 t/s, tg_3s = 19.47 t/s 5.10.624.830 I slot print_timing: id 1 | task 5364 | n_gen = 100, tg = 21.30 t/s, tg_3s = 21.51 t/s 5.11.965.142 I slot print_timing: id 2 | task 5190 | n_gen = 305, tg = 21.36 t/s, tg_3s = 24.67 t/s 5.12.168.463 I slot print_timing: id 3 | task 5210 | n_gen = 291, tg = 22.21 t/s, tg_3s = 24.66 t/s 5.12.329.087 I slot print_timing: id 0 | task 5407 | n_gen = 100, tg = 24.63 t/s, tg_3s = 24.88 t/s 5.13.625.012 I slot print_timing: id 1 | task 5364 | n_gen = 174, tg = 22.62 t/s, tg_3s = 24.67 t/s 5.15.000.413 I slot print_timing: id 2 | task 5190 | n_gen = 380, tg = 21.95 t/s, tg_3s = 24.71 t/s 5.15.202.815 I slot print_timing: id 3 | task 5210 | n_gen = 366, tg = 22.68 t/s, tg_3s = 24.72 t/s 5.15.363.029 I slot print_timing: id 0 | task 5407 | n_gen = 175, tg = 24.67 t/s, tg_3s = 24.72 t/s 5.16.174.515 I slot print_timing: id 3 | task 5210 | prompt eval time = 691.85 ms / 448 tokens ( 1.54 ms per token, 647.54 tokens per second) 5.16.174.523 I slot print_timing: id 3 | task 5210 | eval time = 17065.38 ms / 390 tokens ( 43.87 ms per token, 22.79 tokens per second) 5.16.174.524 I slot print_timing: id 3 | task 5210 | total time = 17757.23 ms / 838 tokens 5.16.174.524 I slot print_timing: id 3 | task 5210 | graphs reused = 5134 5.16.174.525 I slot print_timing: id 3 | task 5210 | graph reallocs = 0 / 0 (same size) / (changed size) 5.16.174.633 I slot release: id 3 | task 5210 | stop processing: n_tokens = 1532, truncated = 0 5.16.209.703 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.916 (> 0.100 thold), f_keep = 0.697 5.16.209.735 I slot launch_slot_: id 3 | task 5605 | processing task, is_child = 0 5.16.859.320 I slot print_timing: id 1 | task 5364 | n_gen = 239, tg = 21.87 t/s, tg_3s = 20.10 t/s 5.16.969.211 I slot print_timing: id 2 | task 5190 | prompt eval time = 722.03 ms / 456 tokens ( 1.58 ms per token, 631.55 tokens per second) 5.16.969.216 I slot print_timing: id 2 | task 5190 | eval time = 19237.42 ms / 413 tokens ( 46.69 ms per token, 21.42 tokens per second) 5.16.969.216 I slot print_timing: id 2 | task 5190 | total time = 19959.46 ms / 869 tokens 5.16.969.217 I slot print_timing: id 2 | task 5190 | graphs reused = 5134 5.16.969.217 I slot print_timing: id 2 | task 5190 | graph reallocs = 0 / 0 (same size) / (changed size) 5.16.969.280 I slot release: id 2 | task 5190 | stop processing: n_tokens = 1543, truncated = 0 5.17.010.197 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.692 5.17.010.226 I slot launch_slot_: id 2 | task 5610 | processing task, is_child = 0 5.18.385.988 I slot print_timing: id 0 | task 5407 | n_gen = 218, tg = 21.54 t/s, tg_3s = 14.22 t/s 5.19.885.548 I slot print_timing: id 1 | task 5364 | n_gen = 297, tg = 21.28 t/s, tg_3s = 19.17 t/s 5.21.386.655 I slot print_timing: id 0 | task 5407 | n_gen = 292, tg = 22.25 t/s, tg_3s = 24.66 t/s 5.21.590.900 I slot print_timing: id 3 | task 5605 | n_gen = 100, tg = 21.23 t/s, tg_3s = 21.45 t/s 5.21.752.263 I slot print_timing: id 2 | task 5610 | n_gen = 100, tg = 24.65 t/s, tg_3s = 24.90 t/s 5.22.923.510 I slot print_timing: id 1 | task 5364 | n_gen = 372, tg = 21.89 t/s, tg_3s = 24.69 t/s 5.24.421.965 I slot print_timing: id 0 | task 5407 | n_gen = 367, tg = 22.72 t/s, tg_3s = 24.71 t/s 5.24.625.472 I slot print_timing: id 3 | task 5605 | n_gen = 175, tg = 22.61 t/s, tg_3s = 24.72 t/s 5.24.786.584 I slot print_timing: id 2 | task 5610 | n_gen = 175, tg = 24.68 t/s, tg_3s = 24.72 t/s 5.25.471.146 I slot print_timing: id 0 | task 5407 | prompt eval time = 713.38 ms / 480 tokens ( 1.49 ms per token, 672.86 tokens per second) 5.25.471.153 I slot print_timing: id 0 | task 5407 | eval time = 17161.09 ms / 393 tokens ( 43.78 ms per token, 22.84 tokens per second) 5.25.471.154 I slot print_timing: id 0 | task 5407 | total time = 17874.47 ms / 873 tokens 5.25.471.155 I slot print_timing: id 0 | task 5407 | graphs reused = 5323 5.25.471.156 I slot print_timing: id 0 | task 5407 | graph reallocs = 0 / 0 (same size) / (changed size) 5.25.471.251 I slot release: id 0 | task 5407 | stop processing: n_tokens = 1545, truncated = 0 5.25.507.807 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.691 5.25.507.843 I slot launch_slot_: id 0 | task 5805 | processing task, is_child = 0 5.26.155.746 I slot print_timing: id 1 | task 5364 | n_gen = 437, tg = 21.61 t/s, tg_3s = 20.11 t/s 5.27.636.535 I slot print_timing: id 3 | task 5605 | n_gen = 234, tg = 21.76 t/s, tg_3s = 19.59 t/s 5.27.798.315 I slot print_timing: id 2 | task 5610 | n_gen = 234, tg = 23.15 t/s, tg_3s = 19.59 t/s 5.29.175.116 I slot print_timing: id 1 | task 5364 | n_gen = 511, tg = 21.98 t/s, tg_3s = 24.51 t/s 5.30.227.594 I slot print_timing: id 0 | task 5805 | n_gen = 100, tg = 24.72 t/s, tg_3s = 24.96 t/s 5.30.673.895 I slot print_timing: id 3 | task 5605 | n_gen = 309, tg = 22.41 t/s, tg_3s = 24.69 t/s 5.30.834.519 I slot print_timing: id 2 | task 5610 | n_gen = 309, tg = 23.51 t/s, tg_3s = 24.70 t/s 5.32.207.631 I slot print_timing: id 1 | task 5364 | n_gen = 586, tg = 22.30 t/s, tg_3s = 24.73 t/s 5.32.368.607 I slot print_timing: id 1 | task 5364 | prompt eval time = 756.46 ms / 488 tokens ( 1.55 ms per token, 645.11 tokens per second) 5.32.368.611 I slot print_timing: id 1 | task 5364 | eval time = 26391.72 ms / 590 tokens ( 44.81 ms per token, 22.32 tokens per second) 5.32.368.612 I slot print_timing: id 1 | task 5364 | total time = 27148.18 ms / 1078 tokens 5.32.368.612 I slot print_timing: id 1 | task 5364 | graphs reused = 5475 5.32.368.613 I slot print_timing: id 1 | task 5364 | graph reallocs = 0 / 0 (same size) / (changed size) 5.32.368.711 I slot release: id 1 | task 5364 | stop processing: n_tokens = 1737, truncated = 0 5.32.412.448 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.898 (> 0.100 thold), f_keep = 0.615 5.32.412.490 I slot launch_slot_: id 1 | task 5961 | processing task, is_child = 0 5.33.234.839 I slot print_timing: id 0 | task 5805 | n_gen = 156, tg = 22.10 t/s, tg_3s = 18.62 t/s 5.33.709.060 I slot print_timing: id 3 | task 5605 | n_gen = 365, tg = 21.69 t/s, tg_3s = 18.45 t/s 5.33.867.545 I slot print_timing: id 2 | task 5610 | n_gen = 365, tg = 22.56 t/s, tg_3s = 18.46 t/s 5.36.261.848 I slot print_timing: id 0 | task 5805 | n_gen = 230, tg = 22.81 t/s, tg_3s = 24.45 t/s 5.36.709.260 I slot print_timing: id 3 | task 5605 | n_gen = 439, tg = 22.14 t/s, tg_3s = 24.67 t/s 5.36.870.339 I slot print_timing: id 2 | task 5610 | n_gen = 439, tg = 22.89 t/s, tg_3s = 24.64 t/s 5.37.315.410 I slot print_timing: id 1 | task 5961 | n_gen = 100, tg = 24.72 t/s, tg_3s = 24.97 t/s 5.39.262.135 I slot print_timing: id 0 | task 5805 | n_gen = 304, tg = 23.24 t/s, tg_3s = 24.66 t/s 5.39.710.925 I slot print_timing: id 3 | task 5605 | n_gen = 513, tg = 22.47 t/s, tg_3s = 24.65 t/s 5.39.872.475 I slot print_timing: id 2 | task 5610 | n_gen = 513, tg = 23.13 t/s, tg_3s = 24.65 t/s 5.40.320.019 I slot print_timing: id 1 | task 5961 | n_gen = 174, tg = 24.68 t/s, tg_3s = 24.63 t/s 5.42.274.275 I slot print_timing: id 0 | task 5805 | n_gen = 378, tg = 23.49 t/s, tg_3s = 24.57 t/s 5.42.724.115 I slot print_timing: id 3 | task 5605 | n_gen = 587, tg = 22.72 t/s, tg_3s = 24.56 t/s 5.42.885.627 I slot print_timing: id 2 | task 5610 | n_gen = 587, tg = 23.30 t/s, tg_3s = 24.56 t/s 5.43.331.281 I slot print_timing: id 1 | task 5961 | n_gen = 248, tg = 24.65 t/s, tg_3s = 24.57 t/s 5.45.281.905 I slot print_timing: id 0 | task 5805 | n_gen = 452, tg = 23.66 t/s, tg_3s = 24.60 t/s 5.45.729.743 I slot print_timing: id 3 | task 5605 | n_gen = 661, tg = 22.92 t/s, tg_3s = 24.62 t/s 5.45.891.402 I slot print_timing: id 2 | task 5610 | n_gen = 661, tg = 23.44 t/s, tg_3s = 24.62 t/s 5.46.336.062 I slot print_timing: id 1 | task 5961 | n_gen = 322, tg = 24.65 t/s, tg_3s = 24.63 t/s 5.48.317.119 I slot print_timing: id 0 | task 5805 | n_gen = 527, tg = 23.81 t/s, tg_3s = 24.71 t/s 5.48.440.584 I slot print_timing: id 3 | task 5605 | prompt eval time = 718.68 ms / 471 tokens ( 1.53 ms per token, 655.37 tokens per second) 5.48.440.588 I slot print_timing: id 3 | task 5605 | eval time = 31512.16 ms / 728 tokens ( 43.35 ms per token, 23.07 tokens per second) 5.48.440.589 I slot print_timing: id 3 | task 5605 | total time = 32230.84 ms / 1199 tokens 5.48.440.590 I slot print_timing: id 3 | task 5605 | graphs reused = 5845 5.48.440.590 I slot print_timing: id 3 | task 5605 | graph reallocs = 0 / 0 (same size) / (changed size) 5.48.440.688 I slot release: id 3 | task 5605 | stop processing: n_tokens = 1893, truncated = 0 5.48.475.860 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.564 5.48.475.914 I slot launch_slot_: id 3 | task 6339 | processing task, is_child = 0 5.49.132.319 I slot print_timing: id 2 | task 5610 | n_gen = 726, tg = 23.09 t/s, tg_3s = 20.06 t/s 5.49.360.968 I slot print_timing: id 1 | task 5961 | n_gen = 381, tg = 23.68 t/s, tg_3s = 19.50 t/s 5.49.400.349 I slot print_timing: id 0 | task 5805 | prompt eval time = 714.12 ms / 482 tokens ( 1.48 ms per token, 674.96 tokens per second) 5.49.400.351 I slot print_timing: id 0 | task 5805 | eval time = 23178.38 ms / 538 tokens ( 43.16 ms per token, 23.17 tokens per second) 5.49.400.351 I slot print_timing: id 0 | task 5805 | total time = 23892.50 ms / 1020 tokens 5.49.400.352 I slot print_timing: id 0 | task 5805 | graphs reused = 5849 5.49.400.353 I slot print_timing: id 0 | task 5805 | graph reallocs = 0 / 0 (same size) / (changed size) 5.49.400.416 I slot release: id 0 | task 5805 | stop processing: n_tokens = 1692, truncated = 0 5.49.434.874 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.631 5.49.434.900 I slot launch_slot_: id 0 | task 6348 | processing task, is_child = 0 5.52.146.588 I slot print_timing: id 2 | task 5610 | n_gen = 784, tg = 22.75 t/s, tg_3s = 19.24 t/s 5.52.389.131 I slot print_timing: id 1 | task 5961 | n_gen = 440, tg = 23.01 t/s, tg_3s = 19.48 t/s 5.53.850.022 I slot print_timing: id 3 | task 6339 | n_gen = 100, tg = 21.30 t/s, tg_3s = 21.51 t/s 5.54.171.839 I slot print_timing: id 0 | task 6348 | n_gen = 100, tg = 24.68 t/s, tg_3s = 24.93 t/s 5.55.187.357 I slot print_timing: id 2 | task 5610 | n_gen = 859, tg = 22.91 t/s, tg_3s = 24.66 t/s 5.55.390.080 I slot print_timing: id 1 | task 5961 | n_gen = 514, tg = 23.23 t/s, tg_3s = 24.66 t/s 5.56.853.408 I slot print_timing: id 3 | task 6339 | n_gen = 174, tg = 22.61 t/s, tg_3s = 24.64 t/s 5.57.177.037 I slot print_timing: id 0 | task 6348 | n_gen = 174, tg = 24.66 t/s, tg_3s = 24.62 t/s 5.58.202.832 I slot print_timing: id 2 | task 5610 | n_gen = 933, tg = 23.03 t/s, tg_3s = 24.54 t/s 5.58.406.743 I slot print_timing: id 1 | task 5961 | n_gen = 588, tg = 23.39 t/s, tg_3s = 24.53 t/s 5.59.880.511 I slot print_timing: id 3 | task 6339 | n_gen = 248, tg = 23.13 t/s, tg_3s = 24.45 t/s 6.00.206.516 I slot print_timing: id 0 | task 6348 | n_gen = 248, tg = 24.59 t/s, tg_3s = 24.43 t/s 6.01.228.261 I slot print_timing: id 2 | task 5610 | n_gen = 1007, tg = 23.13 t/s, tg_3s = 24.46 t/s 6.01.431.815 I slot print_timing: id 1 | task 5961 | n_gen = 662, tg = 23.51 t/s, tg_3s = 24.46 t/s 6.01.922.856 I slot print_timing: id 2 | task 5610 | prompt eval time = 725.16 ms / 462 tokens ( 1.57 ms per token, 637.10 tokens per second) 6.01.922.863 I slot print_timing: id 2 | task 5610 | eval time = 44187.46 ms / 1024 tokens ( 43.19 ms per token, 23.15 tokens per second) 6.01.922.864 I slot print_timing: id 2 | task 5610 | total time = 44912.62 ms / 1486 tokens 6.01.922.865 I slot print_timing: id 2 | task 5610 | graphs reused = 6137 6.01.922.866 I slot print_timing: id 2 | task 5610 | graph reallocs = 0 / 0 (same size) / (changed size) 6.01.922.965 I slot release: id 2 | task 5610 | stop processing: n_tokens = 2160, truncated = 0 6.01.965.848 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.494 6.01.972.088 I slot launch_slot_: id 2 | task 6641 | processing task, is_child = 0 6.02.892.820 I slot print_timing: id 3 | task 6339 | n_gen = 305, tg = 22.20 t/s, tg_3s = 18.92 t/s 6.03.215.890 I slot print_timing: id 0 | task 6348 | n_gen = 305, tg = 23.29 t/s, tg_3s = 18.94 t/s 6.04.471.987 I slot print_timing: id 1 | task 5961 | n_gen = 720, tg = 23.07 t/s, tg_3s = 19.08 t/s 6.05.930.265 I slot print_timing: id 3 | task 6339 | n_gen = 380, tg = 22.66 t/s, tg_3s = 24.69 t/s 6.06.253.375 I slot print_timing: id 0 | task 6348 | n_gen = 380, tg = 23.55 t/s, tg_3s = 24.69 t/s 6.06.742.539 I slot print_timing: id 2 | task 6641 | n_gen = 100, tg = 24.69 t/s, tg_3s = 24.94 t/s 6.07.148.676 I slot print_timing: id 1 | task 5961 | prompt eval time = 898.64 ms / 529 tokens ( 1.70 ms per token, 588.67 tokens per second) 6.07.148.683 I slot print_timing: id 1 | task 5961 | eval time = 33837.53 ms / 786 tokens ( 43.11 ms per token, 23.20 tokens per second) 6.07.148.684 I slot print_timing: id 1 | task 5961 | total time = 34736.17 ms / 1315 tokens 6.07.148.685 I slot print_timing: id 1 | task 5961 | graphs reused = 6245 6.07.148.686 I slot print_timing: id 1 | task 5961 | graph reallocs = 0 / 0 (same size) / (changed size) 6.07.148.799 I slot release: id 1 | task 5961 | stop processing: n_tokens = 1974, truncated = 0 6.07.192.670 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.541 6.07.192.713 I slot launch_slot_: id 1 | task 6754 | processing task, is_child = 0 6.08.940.175 I slot print_timing: id 3 | task 6339 | n_gen = 437, tg = 22.09 t/s, tg_3s = 18.94 t/s 6.09.264.521 I slot print_timing: id 0 | task 6348 | n_gen = 437, tg = 22.82 t/s, tg_3s = 18.93 t/s 6.09.754.168 I slot print_timing: id 2 | task 6641 | n_gen = 157, tg = 22.22 t/s, tg_3s = 18.93 t/s 6.11.945.712 I slot print_timing: id 3 | task 6339 | n_gen = 511, tg = 22.42 t/s, tg_3s = 24.62 t/s 6.11.984.778 I slot print_timing: id 1 | task 6754 | n_gen = 100, tg = 24.61 t/s, tg_3s = 24.86 t/s 6.12.267.958 I slot print_timing: id 0 | task 6348 | n_gen = 511, tg = 23.07 t/s, tg_3s = 24.64 t/s 6.12.757.516 I slot print_timing: id 2 | task 6641 | n_gen = 231, tg = 22.94 t/s, tg_3s = 24.64 t/s 6.14.946.952 I slot print_timing: id 3 | task 6339 | n_gen = 585, tg = 22.68 t/s, tg_3s = 24.66 t/s 6.14.986.236 I slot print_timing: id 1 | task 6754 | n_gen = 174, tg = 24.63 t/s, tg_3s = 24.65 t/s 6.15.269.764 I slot print_timing: id 0 | task 6348 | n_gen = 585, tg = 23.26 t/s, tg_3s = 24.65 t/s 6.15.758.621 I slot print_timing: id 2 | task 6641 | n_gen = 305, tg = 23.34 t/s, tg_3s = 24.66 t/s 6.17.959.099 I slot print_timing: id 3 | task 6339 | n_gen = 659, tg = 22.88 t/s, tg_3s = 24.57 t/s 6.17.998.696 I slot print_timing: id 1 | task 6754 | n_gen = 248, tg = 24.61 t/s, tg_3s = 24.56 t/s 6.18.283.531 I slot print_timing: id 0 | task 6348 | n_gen = 659, tg = 23.40 t/s, tg_3s = 24.55 t/s 6.18.772.676 I slot print_timing: id 2 | task 6641 | n_gen = 379, tg = 23.57 t/s, tg_3s = 24.55 t/s 6.20.962.858 I slot print_timing: id 3 | task 6339 | n_gen = 733, tg = 23.05 t/s, tg_3s = 24.64 t/s 6.21.002.044 I slot print_timing: id 1 | task 6754 | n_gen = 322, tg = 24.62 t/s, tg_3s = 24.64 t/s 6.21.285.166 I slot print_timing: id 0 | task 6348 | n_gen = 733, tg = 23.52 t/s, tg_3s = 24.65 t/s 6.21.774.017 I slot print_timing: id 2 | task 6641 | n_gen = 453, tg = 23.74 t/s, tg_3s = 24.66 t/s 6.23.967.454 I slot print_timing: id 3 | task 6339 | n_gen = 807, tg = 23.18 t/s, tg_3s = 24.63 t/s 6.24.006.273 I slot print_timing: id 0 | task 6348 | prompt eval time = 726.00 ms / 486 tokens ( 1.49 ms per token, 669.42 tokens per second) 6.24.006.276 I slot print_timing: id 0 | task 6348 | eval time = 33845.37 ms / 800 tokens ( 42.36 ms per token, 23.61 tokens per second) 6.24.006.277 I slot print_timing: id 0 | task 6348 | total time = 34571.37 ms / 1286 tokens 6.24.006.278 I slot print_timing: id 0 | task 6348 | graphs reused = 6638 6.24.006.278 I slot print_timing: id 0 | task 6348 | graph reallocs = 0 / 0 (same size) / (changed size) 6.24.006.380 I slot release: id 0 | task 6348 | stop processing: n_tokens = 1958, truncated = 0 6.24.006.846 I slot print_timing: id 1 | task 6754 | n_gen = 396, tg = 24.62 t/s, tg_3s = 24.63 t/s 6.24.043.668 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.545 6.24.043.705 I slot launch_slot_: id 0 | task 7153 | processing task, is_child = 0 6.24.788.520 I slot print_timing: id 2 | task 6641 | n_gen = 512, tg = 23.17 t/s, tg_3s = 19.57 t/s 6.27.005.960 I slot print_timing: id 3 | task 6339 | n_gen = 867, tg = 22.91 t/s, tg_3s = 19.75 t/s 6.27.045.433 I slot print_timing: id 1 | task 6754 | n_gen = 456, tg = 23.84 t/s, tg_3s = 19.75 t/s 6.27.818.661 I slot print_timing: id 2 | task 6641 | n_gen = 587, tg = 23.36 t/s, tg_3s = 24.75 t/s 6.28.755.642 I slot print_timing: id 0 | task 7153 | n_gen = 100, tg = 24.70 t/s, tg_3s = 24.95 t/s 6.28.960.554 I slot print_timing: id 3 | task 6339 | prompt eval time = 725.48 ms / 478 tokens ( 1.52 ms per token, 658.88 tokens per second) 6.28.960.558 I slot print_timing: id 3 | task 6339 | eval time = 39759.15 ms / 915 tokens ( 43.50 ms per token, 22.99 tokens per second) 6.28.960.559 I slot print_timing: id 3 | task 6339 | total time = 40484.63 ms / 1393 tokens 6.28.960.560 I slot print_timing: id 3 | task 6339 | graphs reused = 6741 6.28.960.561 I slot print_timing: id 3 | task 6339 | graph reallocs = 0 / 0 (same size) / (changed size) 6.28.960.665 I slot release: id 3 | task 6339 | stop processing: n_tokens = 2087, truncated = 0 6.28.995.846 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.512 6.28.995.902 I slot launch_slot_: id 3 | task 7261 | processing task, is_child = 0 6.30.057.031 I slot print_timing: id 1 | task 6754 | n_gen = 515, tg = 23.26 t/s, tg_3s = 19.59 t/s 6.30.826.188 I slot print_timing: id 2 | task 6641 | n_gen = 646, tg = 22.96 t/s, tg_3s = 19.62 t/s 6.31.794.250 I slot print_timing: id 0 | task 7153 | n_gen = 160, tg = 22.56 t/s, tg_3s = 19.75 t/s 6.33.091.889 I slot print_timing: id 1 | task 6754 | n_gen = 590, tg = 23.44 t/s, tg_3s = 24.71 t/s 6.33.700.856 I slot print_timing: id 3 | task 7261 | n_gen = 100, tg = 24.69 t/s, tg_3s = 24.94 t/s 6.33.862.314 I slot print_timing: id 2 | task 6641 | n_gen = 721, tg = 23.13 t/s, tg_3s = 24.70 t/s 6.34.794.634 I slot print_timing: id 0 | task 7153 | n_gen = 234, tg = 23.19 t/s, tg_3s = 24.66 t/s 6.36.095.486 I slot print_timing: id 1 | task 6754 | n_gen = 664, tg = 23.57 t/s, tg_3s = 24.64 t/s 6.36.707.525 I slot print_timing: id 3 | task 7261 | n_gen = 174, tg = 24.66 t/s, tg_3s = 24.61 t/s 6.36.870.195 I slot print_timing: id 2 | task 6641 | n_gen = 795, tg = 23.26 t/s, tg_3s = 24.60 t/s 6.37.805.109 I slot print_timing: id 0 | task 7153 | n_gen = 308, tg = 23.51 t/s, tg_3s = 24.58 t/s 6.38.777.255 I slot print_timing: id 1 | task 6754 | prompt eval time = 769.63 ms / 507 tokens ( 1.52 ms per token, 658.75 tokens per second) 6.38.777.263 I slot print_timing: id 1 | task 6754 | eval time = 30814.88 ms / 730 tokens ( 42.27 ms per token, 23.66 tokens per second) 6.38.777.264 I slot print_timing: id 1 | task 6754 | total time = 31584.52 ms / 1237 tokens 6.38.777.264 I slot print_timing: id 1 | task 6754 | graphs reused = 6963 6.38.777.265 I slot print_timing: id 1 | task 6754 | graph reallocs = 0 / 0 (same size) / (changed size) 6.38.777.388 I slot release: id 1 | task 6754 | stop processing: n_tokens = 1909, truncated = 0 6.38.821.574 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.559 6.38.821.619 I slot launch_slot_: id 1 | task 7489 | processing task, is_child = 0 6.39.718.666 I slot print_timing: id 3 | task 7261 | n_gen = 232, tg = 23.04 t/s, tg_3s = 19.26 t/s 6.39.883.502 I slot print_timing: id 2 | task 6641 | n_gen = 853, tg = 22.93 t/s, tg_3s = 19.25 t/s 6.40.815.931 I slot print_timing: id 0 | task 7153 | n_gen = 366, tg = 22.71 t/s, tg_3s = 19.26 t/s 6.42.730.389 I slot print_timing: id 3 | task 7261 | n_gen = 306, tg = 23.39 t/s, tg_3s = 24.57 t/s 6.42.892.197 I slot print_timing: id 2 | task 6641 | n_gen = 927, tg = 23.06 t/s, tg_3s = 24.60 t/s 6.43.500.142 I slot print_timing: id 3 | task 7261 | prompt eval time = 695.84 ms / 453 tokens ( 1.54 ms per token, 651.01 tokens per second) 6.43.500.147 I slot print_timing: id 3 | task 7261 | eval time = 13808.39 ms / 325 tokens ( 42.62 ms per token, 23.46 tokens per second) 6.43.500.148 I slot print_timing: id 3 | task 7261 | total time = 14504.23 ms / 778 tokens 6.43.500.149 I slot print_timing: id 3 | task 7261 | graphs reused = 7058 6.43.500.149 I slot print_timing: id 3 | task 7261 | graph reallocs = 0 / 0 (same size) / (changed size) 6.43.500.252 I slot release: id 3 | task 7261 | stop processing: n_tokens = 1472, truncated = 0 6.43.535.344 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.726 6.43.535.377 I slot launch_slot_: id 3 | task 7590 | processing task, is_child = 0 6.44.157.095 I slot print_timing: id 0 | task 7153 | n_gen = 434, tg = 22.31 t/s, tg_3s = 20.35 t/s 6.44.157.347 I slot print_timing: id 1 | task 7489 | n_gen = 100, tg = 21.50 t/s, tg_3s = 21.72 t/s 6.44.664.061 I slot print_timing: id 0 | task 7153 | prompt eval time = 703.12 ms / 466 tokens ( 1.51 ms per token, 662.76 tokens per second) 6.44.664.066 I slot print_timing: id 0 | task 7153 | eval time = 19917.23 ms / 446 tokens ( 44.76 ms per token, 22.34 tokens per second) 6.44.664.067 I slot print_timing: id 0 | task 7153 | total time = 20620.35 ms / 912 tokens 6.44.664.067 I slot print_timing: id 0 | task 7153 | graphs reused = 7068 6.44.664.068 I slot print_timing: id 0 | task 7153 | graph reallocs = 0 / 0 (same size) / (changed size) 6.44.664.125 I slot release: id 0 | task 7153 | stop processing: n_tokens = 1584, truncated = 0 6.44.698.176 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.674 6.44.698.197 I slot launch_slot_: id 0 | task 7605 | processing task, is_child = 0 6.45.894.839 I slot print_timing: id 2 | task 6641 | n_gen = 971, tg = 22.47 t/s, tg_3s = 14.65 t/s 6.47.157.600 I slot print_timing: id 1 | task 7489 | n_gen = 158, tg = 20.65 t/s, tg_3s = 19.33 t/s 6.48.056.368 I slot print_timing: id 2 | task 6641 | prompt eval time = 760.21 ms / 496 tokens ( 1.53 ms per token, 652.45 tokens per second) 6.48.056.373 I slot print_timing: id 2 | task 6641 | eval time = 45324.06 ms / 1024 tokens ( 44.31 ms per token, 22.57 tokens per second) 6.48.056.374 I slot print_timing: id 2 | task 6641 | total time = 46084.27 ms / 1520 tokens 6.48.056.375 I slot print_timing: id 2 | task 6641 | graphs reused = 7133 6.48.056.376 I slot print_timing: id 2 | task 6641 | graph reallocs = 0 / 0 (same size) / (changed size) 6.48.056.498 I slot release: id 2 | task 6641 | stop processing: n_tokens = 2194, truncated = 0 6.48.100.183 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.916 (> 0.100 thold), f_keep = 0.487 6.48.105.926 I slot launch_slot_: id 2 | task 7674 | processing task, is_child = 0 6.49.551.074 I slot print_timing: id 3 | task 7590 | n_gen = 100, tg = 18.60 t/s, tg_3s = 18.78 t/s 6.50.116.055 I slot print_timing: id 0 | task 7605 | n_gen = 100, tg = 21.04 t/s, tg_3s = 21.25 t/s 6.50.197.828 I slot print_timing: id 1 | task 7489 | n_gen = 216, tg = 20.20 t/s, tg_3s = 19.08 t/s 6.52.580.679 I slot print_timing: id 3 | task 7590 | n_gen = 175, tg = 20.83 t/s, tg_3s = 24.76 t/s 6.52.861.869 I slot print_timing: id 2 | task 7674 | n_gen = 100, tg = 24.76 t/s, tg_3s = 25.01 t/s 6.53.143.170 I slot print_timing: id 0 | task 7605 | n_gen = 175, tg = 22.50 t/s, tg_3s = 24.78 t/s 6.53.224.243 I slot print_timing: id 1 | task 7489 | n_gen = 291, tg = 21.21 t/s, tg_3s = 24.78 t/s 6.55.610.003 I slot print_timing: id 3 | task 7590 | n_gen = 250, tg = 21.87 t/s, tg_3s = 24.76 t/s 6.55.893.073 I slot print_timing: id 2 | task 7674 | n_gen = 175, tg = 24.75 t/s, tg_3s = 24.74 t/s 6.56.176.917 I slot print_timing: id 0 | task 7605 | n_gen = 250, tg = 23.13 t/s, tg_3s = 24.72 t/s 6.56.258.404 I slot print_timing: id 1 | task 7489 | n_gen = 366, tg = 21.85 t/s, tg_3s = 24.72 t/s 6.58.614.014 I slot print_timing: id 3 | task 7590 | n_gen = 324, tg = 22.45 t/s, tg_3s = 24.63 t/s 6.58.897.766 I slot print_timing: id 2 | task 7674 | n_gen = 249, tg = 24.71 t/s, tg_3s = 24.63 t/s 6.58.978.184 I slot print_timing: id 1 | task 7489 | prompt eval time = 731.80 ms / 469 tokens ( 1.56 ms per token, 640.88 tokens per second) 6.58.978.192 I slot print_timing: id 1 | task 7489 | eval time = 19424.75 ms / 433 tokens ( 44.96 ms per token, 22.24 tokens per second) 6.58.978.192 I slot print_timing: id 1 | task 7489 | total time = 20156.56 ms / 902 tokens 6.58.978.193 I slot print_timing: id 1 | task 7489 | graphs reused = 7381 6.58.978.194 I slot print_timing: id 1 | task 7489 | graph reallocs = 0 / 0 (same size) / (changed size) 6.58.978.319 I slot release: id 1 | task 7489 | stop processing: n_tokens = 1574, truncated = 0 6.59.022.641 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.916 (> 0.100 thold), f_keep = 0.679 6.59.022.687 I slot launch_slot_: id 1 | task 7928 | processing task, is_child = 0 6.59.705.940 I slot print_timing: id 0 | task 7605 | n_gen = 321, tg = 22.38 t/s, tg_3s = 20.12 t/s 7.01.649.216 I slot print_timing: id 3 | task 7590 | n_gen = 382, tg = 21.87 t/s, tg_3s = 19.11 t/s 7.01.931.563 I slot print_timing: id 2 | task 7674 | n_gen = 307, tg = 23.41 t/s, tg_3s = 19.12 t/s 7.02.742.027 I slot print_timing: id 0 | task 7605 | n_gen = 395, tg = 22.73 t/s, tg_3s = 24.37 t/s 7.03.026.070 I slot print_timing: id 3 | task 7590 | prompt eval time = 691.71 ms / 448 tokens ( 1.54 ms per token, 647.67 tokens per second) 7.03.026.075 I slot print_timing: id 3 | task 7590 | eval time = 18798.98 ms / 416 tokens ( 45.30 ms per token, 22.08 tokens per second) 7.03.026.078 I slot print_timing: id 3 | task 7590 | total time = 19490.68 ms / 864 tokens 7.03.026.078 I slot print_timing: id 3 | task 7590 | graphs reused = 7459 7.03.026.079 I slot print_timing: id 3 | task 7590 | graph reallocs = 0 / 0 (same size) / (changed size) 7.03.026.190 I slot release: id 3 | task 7590 | stop processing: n_tokens = 1558, truncated = 0 7.03.061.420 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.685 7.03.061.458 I slot launch_slot_: id 3 | task 8012 | processing task, is_child = 0 7.04.413.877 I slot print_timing: id 1 | task 7928 | n_gen = 100, tg = 21.38 t/s, tg_3s = 21.59 t/s 7.04.900.138 I slot print_timing: id 0 | task 7605 | prompt eval time = 712.12 ms / 478 tokens ( 1.49 ms per token, 671.24 tokens per second) 7.04.900.144 I slot print_timing: id 0 | task 7605 | eval time = 19489.82 ms / 433 tokens ( 45.12 ms per token, 22.17 tokens per second) 7.04.900.145 I slot print_timing: id 0 | task 7605 | total time = 20201.93 ms / 911 tokens 7.04.900.146 I slot print_timing: id 0 | task 7605 | graphs reused = 7486 7.04.900.146 I slot print_timing: id 0 | task 7605 | graph reallocs = 0 / 0 (same size) / (changed size) 7.04.900.246 I slot release: id 0 | task 7605 | stop processing: n_tokens = 1583, truncated = 0 7.04.936.301 I slot print_timing: id 2 | task 7674 | n_gen = 366, tg = 22.71 t/s, tg_3s = 19.64 t/s 7.04.936.795 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.945 (> 0.100 thold), f_keep = 0.675 7.04.936.826 I slot launch_slot_: id 0 | task 8044 | processing task, is_child = 0 7.07.418.761 I slot print_timing: id 1 | task 7928 | n_gen = 159, tg = 20.69 t/s, tg_3s = 19.63 t/s 7.07.946.115 I slot print_timing: id 2 | task 7674 | n_gen = 425, tg = 22.22 t/s, tg_3s = 19.60 t/s 7.08.390.345 I slot print_timing: id 3 | task 8012 | n_gen = 100, tg = 21.42 t/s, tg_3s = 21.64 t/s 7.09.639.238 I slot print_timing: id 0 | task 8044 | n_gen = 100, tg = 24.71 t/s, tg_3s = 24.96 t/s 7.10.448.884 I slot print_timing: id 1 | task 7928 | n_gen = 234, tg = 21.84 t/s, tg_3s = 24.75 t/s 7.10.976.270 I slot print_timing: id 2 | task 7674 | n_gen = 500, tg = 22.57 t/s, tg_3s = 24.75 t/s 7.11.422.896 I slot print_timing: id 3 | task 8012 | n_gen = 175, tg = 22.73 t/s, tg_3s = 24.73 t/s 7.12.676.444 I slot print_timing: id 0 | task 8044 | n_gen = 175, tg = 24.70 t/s, tg_3s = 24.69 t/s 7.13.487.101 I slot print_timing: id 1 | task 7928 | n_gen = 309, tg = 22.47 t/s, tg_3s = 24.69 t/s 7.14.015.894 I slot print_timing: id 2 | task 7674 | n_gen = 575, tg = 22.82 t/s, tg_3s = 24.67 t/s 7.14.462.903 I slot print_timing: id 3 | task 8012 | n_gen = 250, tg = 23.28 t/s, tg_3s = 24.67 t/s 7.15.681.076 I slot print_timing: id 0 | task 8044 | n_gen = 249, tg = 24.68 t/s, tg_3s = 24.63 t/s 7.16.497.794 I slot print_timing: id 1 | task 7928 | n_gen = 383, tg = 22.85 t/s, tg_3s = 24.58 t/s 7.17.026.211 I slot print_timing: id 2 | task 7674 | n_gen = 649, tg = 23.01 t/s, tg_3s = 24.58 t/s 7.17.473.678 I slot print_timing: id 3 | task 8012 | n_gen = 324, tg = 23.57 t/s, tg_3s = 24.58 t/s 7.17.798.424 I slot print_timing: id 2 | task 7674 | prompt eval time = 756.74 ms / 491 tokens ( 1.54 ms per token, 648.84 tokens per second) 7.17.798.432 I slot print_timing: id 2 | task 7674 | eval time = 28935.75 ms / 668 tokens ( 43.38 ms per token, 23.05 tokens per second) 7.17.798.434 I slot print_timing: id 2 | task 7674 | total time = 29692.49 ms / 1159 tokens 7.17.798.435 I slot print_timing: id 2 | task 7674 | graphs reused = 7784 7.17.798.436 I slot print_timing: id 2 | task 7674 | graph reallocs = 0 / 0 (same size) / (changed size) 7.17.798.553 I slot release: id 2 | task 7674 | stop processing: n_tokens = 1833, truncated = 0 7.17.841.792 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.583 7.17.841.826 I slot launch_slot_: id 2 | task 8348 | processing task, is_child = 0 7.18.696.066 I slot print_timing: id 0 | task 8044 | n_gen = 307, tg = 23.42 t/s, tg_3s = 19.24 t/s 7.19.509.352 I slot print_timing: id 1 | task 7928 | n_gen = 441, tg = 22.30 t/s, tg_3s = 19.26 t/s 7.20.483.983 I slot print_timing: id 3 | task 8012 | n_gen = 382, tg = 22.79 t/s, tg_3s = 19.27 t/s 7.21.697.480 I slot print_timing: id 0 | task 8044 | n_gen = 381, tg = 23.65 t/s, tg_3s = 24.66 t/s 7.22.549.655 I slot print_timing: id 1 | task 7928 | n_gen = 516, tg = 22.62 t/s, tg_3s = 24.67 t/s 7.22.590.850 I slot print_timing: id 2 | task 8348 | n_gen = 100, tg = 24.66 t/s, tg_3s = 24.91 t/s 7.23.523.105 I slot print_timing: id 3 | task 8012 | n_gen = 457, tg = 23.08 t/s, tg_3s = 24.68 t/s 7.24.735.049 I slot print_timing: id 0 | task 8044 | n_gen = 456, tg = 23.82 t/s, tg_3s = 24.69 t/s 7.25.589.190 I slot print_timing: id 1 | task 7928 | n_gen = 591, tg = 22.86 t/s, tg_3s = 24.67 t/s 7.25.630.361 I slot print_timing: id 2 | task 8348 | n_gen = 175, tg = 24.67 t/s, tg_3s = 24.68 t/s 7.26.524.361 I slot print_timing: id 3 | task 8012 | n_gen = 531, tg = 23.29 t/s, tg_3s = 24.66 t/s 7.27.741.049 I slot print_timing: id 0 | task 8044 | n_gen = 530, tg = 23.93 t/s, tg_3s = 24.62 t/s 7.28.629.497 I slot print_timing: id 1 | task 7928 | n_gen = 666, tg = 23.05 t/s, tg_3s = 24.67 t/s 7.28.670.392 I slot print_timing: id 2 | task 8348 | n_gen = 250, tg = 24.67 t/s, tg_3s = 24.67 t/s 7.28.750.649 I slot print_timing: id 0 | task 8044 | prompt eval time = 696.07 ms / 457 tokens ( 1.52 ms per token, 656.55 tokens per second) 7.28.750.653 I slot print_timing: id 0 | task 8044 | eval time = 23117.75 ms / 555 tokens ( 41.73 ms per token, 23.96 tokens per second) 7.28.750.655 I slot print_timing: id 0 | task 8044 | total time = 23813.81 ms / 1012 tokens 7.28.750.656 I slot print_timing: id 0 | task 8044 | graphs reused = 8033 7.28.750.656 I slot print_timing: id 0 | task 8044 | graph reallocs = 0 / 0 (same size) / (changed size) 7.28.750.760 I slot release: id 0 | task 8044 | stop processing: n_tokens = 1684, truncated = 0 7.28.787.112 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.634 7.28.787.149 I slot launch_slot_: id 0 | task 8603 | processing task, is_child = 0 7.29.532.219 I slot print_timing: id 3 | task 8012 | n_gen = 590, tg = 22.86 t/s, tg_3s = 19.62 t/s 7.29.769.806 I slot print_timing: id 3 | task 8012 | prompt eval time = 707.22 ms / 454 tokens ( 1.56 ms per token, 641.95 tokens per second) 7.29.769.809 I slot print_timing: id 3 | task 8012 | eval time = 26001.12 ms / 596 tokens ( 43.70 ms per token, 22.88 tokens per second) 7.29.769.809 I slot print_timing: id 3 | task 8012 | total time = 26708.34 ms / 1050 tokens 7.29.769.810 I slot print_timing: id 3 | task 8012 | graphs reused = 8040 7.29.769.810 I slot print_timing: id 3 | task 8012 | graph reallocs = 0 / 0 (same size) / (changed size) 7.29.769.874 I slot release: id 3 | task 8012 | stop processing: n_tokens = 1744, truncated = 0 7.29.802.982 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.942 (> 0.100 thold), f_keep = 0.612 7.29.803.003 I slot launch_slot_: id 3 | task 8614 | processing task, is_child = 0 7.31.663.749 I slot print_timing: id 1 | task 7928 | n_gen = 711, tg = 22.27 t/s, tg_3s = 14.83 t/s 7.31.704.903 I slot print_timing: id 2 | task 8348 | n_gen = 295, tg = 22.39 t/s, tg_3s = 14.83 t/s 7.34.095.028 I slot print_timing: id 0 | task 8603 | n_gen = 100, tg = 21.50 t/s, tg_3s = 21.72 t/s 7.34.499.902 I slot print_timing: id 3 | task 8614 | n_gen = 100, tg = 24.66 t/s, tg_3s = 24.91 t/s 7.34.700.932 I slot print_timing: id 1 | task 7928 | n_gen = 786, tg = 22.48 t/s, tg_3s = 24.69 t/s 7.34.742.149 I slot print_timing: id 2 | task 8348 | n_gen = 370, tg = 22.83 t/s, tg_3s = 24.69 t/s 7.37.131.757 I slot print_timing: id 0 | task 8603 | n_gen = 175, tg = 22.77 t/s, tg_3s = 24.70 t/s 7.37.537.747 I slot print_timing: id 3 | task 8614 | n_gen = 175, tg = 24.67 t/s, tg_3s = 24.69 t/s 7.37.739.179 I slot print_timing: id 1 | task 7928 | n_gen = 861, tg = 22.66 t/s, tg_3s = 24.69 t/s 7.37.779.947 I slot print_timing: id 2 | task 8348 | n_gen = 445, tg = 23.12 t/s, tg_3s = 24.69 t/s 7.40.139.471 I slot print_timing: id 0 | task 8603 | n_gen = 249, tg = 23.29 t/s, tg_3s = 24.60 t/s 7.40.548.513 I slot print_timing: id 3 | task 8614 | n_gen = 249, tg = 24.65 t/s, tg_3s = 24.58 t/s 7.40.751.288 I slot print_timing: id 1 | task 7928 | n_gen = 935, tg = 22.80 t/s, tg_3s = 24.57 t/s 7.40.792.482 I slot print_timing: id 2 | task 8348 | n_gen = 519, tg = 23.32 t/s, tg_3s = 24.56 t/s 7.43.154.450 I slot print_timing: id 0 | task 8603 | n_gen = 323, tg = 23.57 t/s, tg_3s = 24.54 t/s 7.43.564.674 I slot print_timing: id 3 | task 8614 | n_gen = 323, tg = 24.62 t/s, tg_3s = 24.53 t/s 7.43.767.220 I slot print_timing: id 1 | task 7928 | n_gen = 1009, tg = 22.92 t/s, tg_3s = 24.54 t/s 7.43.808.387 I slot print_timing: id 2 | task 8348 | n_gen = 593, tg = 23.46 t/s, tg_3s = 24.54 t/s 7.44.378.306 I slot print_timing: id 1 | task 7928 | prompt eval time = 760.01 ms / 493 tokens ( 1.54 ms per token, 648.67 tokens per second) 7.44.378.310 I slot print_timing: id 1 | task 7928 | eval time = 44595.60 ms / 1024 tokens ( 43.59 ms per token, 22.94 tokens per second) 7.44.378.311 I slot print_timing: id 1 | task 7928 | total time = 45355.61 ms / 1517 tokens 7.44.378.312 I slot print_timing: id 1 | task 7928 | graphs reused = 8380 7.44.378.313 I slot print_timing: id 1 | task 7928 | graph reallocs = 0 / 0 (same size) / (changed size) 7.44.378.413 I slot release: id 1 | task 7928 | stop processing: n_tokens = 2189, truncated = 0 7.44.421.955 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.488 7.44.428.154 I slot launch_slot_: id 1 | task 8960 | processing task, is_child = 0 7.46.158.170 I slot print_timing: id 0 | task 8603 | n_gen = 380, tg = 22.74 t/s, tg_3s = 18.98 t/s 7.46.568.674 I slot print_timing: id 3 | task 8614 | n_gen = 380, tg = 23.57 t/s, tg_3s = 18.97 t/s 7.46.810.819 I slot print_timing: id 2 | task 8348 | n_gen = 650, tg = 22.99 t/s, tg_3s = 18.98 t/s 7.49.041.594 I slot print_timing: id 3 | task 8614 | prompt eval time = 682.98 ms / 439 tokens ( 1.56 ms per token, 642.77 tokens per second) 7.49.041.601 I slot print_timing: id 3 | task 8614 | eval time = 18555.60 ms / 441 tokens ( 42.17 ms per token, 23.71 tokens per second) 7.49.041.602 I slot print_timing: id 3 | task 8614 | total time = 19238.58 ms / 880 tokens 7.49.041.603 I slot print_timing: id 3 | task 8614 | graphs reused = 8473 7.49.041.604 I slot print_timing: id 3 | task 8614 | graph reallocs = 0 / 0 (same size) / (changed size) 7.49.041.708 I slot release: id 3 | task 8614 | stop processing: n_tokens = 1574, truncated = 0 7.49.076.922 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.679 7.49.076.958 I slot launch_slot_: id 3 | task 9059 | processing task, is_child = 0 7.49.712.741 I slot print_timing: id 0 | task 8603 | n_gen = 453, tg = 22.35 t/s, tg_3s = 20.54 t/s 7.49.822.848 I slot print_timing: id 1 | task 8960 | n_gen = 100, tg = 21.35 t/s, tg_3s = 21.57 t/s 7.49.823.131 I slot print_timing: id 2 | task 8348 | n_gen = 709, tg = 22.66 t/s, tg_3s = 19.59 t/s 7.52.751.520 I slot print_timing: id 0 | task 8603 | n_gen = 527, tg = 22.61 t/s, tg_3s = 24.35 t/s 7.52.833.553 I slot print_timing: id 1 | task 8960 | n_gen = 174, tg = 22.62 t/s, tg_3s = 24.58 t/s 7.52.834.135 I slot print_timing: id 2 | task 8348 | n_gen = 783, tg = 22.83 t/s, tg_3s = 24.58 t/s 7.53.811.153 I slot print_timing: id 3 | task 9059 | n_gen = 100, tg = 24.57 t/s, tg_3s = 24.82 t/s 7.55.753.840 I slot print_timing: id 0 | task 8603 | n_gen = 601, tg = 22.85 t/s, tg_3s = 24.65 t/s 7.55.835.753 I slot print_timing: id 1 | task 8960 | n_gen = 248, tg = 23.19 t/s, tg_3s = 24.65 t/s 7.55.836.204 I slot print_timing: id 2 | task 8348 | n_gen = 857, tg = 22.97 t/s, tg_3s = 24.65 t/s 7.56.851.082 I slot print_timing: id 3 | task 9059 | n_gen = 175, tg = 24.62 t/s, tg_3s = 24.67 t/s 7.58.766.655 I slot print_timing: id 0 | task 8603 | n_gen = 675, tg = 23.02 t/s, tg_3s = 24.56 t/s 7.58.848.678 I slot print_timing: id 1 | task 8960 | n_gen = 322, tg = 23.49 t/s, tg_3s = 24.56 t/s 7.58.849.189 I slot print_timing: id 2 | task 8348 | n_gen = 931, tg = 23.09 t/s, tg_3s = 24.56 t/s 7.59.866.951 I slot print_timing: id 3 | task 9059 | n_gen = 249, tg = 24.59 t/s, tg_3s = 24.54 t/s 8.01.781.226 I slot print_timing: id 0 | task 8603 | n_gen = 749, tg = 23.16 t/s, tg_3s = 24.55 t/s 8.01.863.542 I slot print_timing: id 1 | task 8960 | n_gen = 396, tg = 23.68 t/s, tg_3s = 24.55 t/s 8.01.864.162 I slot print_timing: id 2 | task 8348 | n_gen = 1005, tg = 23.19 t/s, tg_3s = 24.54 t/s 8.02.639.931 I slot print_timing: id 2 | task 8348 | prompt eval time = 734.83 ms / 476 tokens ( 1.54 ms per token, 647.77 tokens per second) 8.02.639.938 I slot print_timing: id 2 | task 8348 | eval time = 44063.26 ms / 1024 tokens ( 43.07 ms per token, 23.22 tokens per second) 8.02.639.939 I slot print_timing: id 2 | task 8348 | total time = 44798.10 ms / 1500 tokens 8.02.639.940 I slot print_timing: id 2 | task 8348 | graphs reused = 8787 8.02.639.941 I slot print_timing: id 2 | task 8348 | graph reallocs = 0 / 0 (same size) / (changed size) 8.02.640.054 I slot release: id 2 | task 8348 | stop processing: n_tokens = 2174, truncated = 0 8.02.683.324 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.941 (> 0.100 thold), f_keep = 0.491 8.02.689.491 I slot launch_slot_: id 2 | task 9379 | processing task, is_child = 0 8.03.338.704 I slot print_timing: id 3 | task 9059 | n_gen = 319, tg = 23.46 t/s, tg_3s = 20.16 t/s 8.04.792.115 I slot print_timing: id 0 | task 8603 | n_gen = 807, tg = 22.83 t/s, tg_3s = 19.26 t/s 8.04.873.987 I slot print_timing: id 1 | task 8960 | n_gen = 454, tg = 23.01 t/s, tg_3s = 19.27 t/s 8.05.361.538 I slot print_timing: id 0 | task 8603 | prompt eval time = 703.34 ms / 466 tokens ( 1.51 ms per token, 662.55 tokens per second) 8.05.361.541 I slot print_timing: id 0 | task 8603 | eval time = 35871.04 ms / 821 tokens ( 43.75 ms per token, 22.86 tokens per second) 8.05.361.542 I slot print_timing: id 0 | task 8603 | total time = 36574.38 ms / 1287 tokens 8.05.361.543 I slot print_timing: id 0 | task 8603 | graphs reused = 8834 8.05.361.544 I slot print_timing: id 0 | task 8603 | graph reallocs = 0 / 0 (same size) / (changed size) 8.05.361.645 I slot release: id 0 | task 8603 | stop processing: n_tokens = 1959, truncated = 0 8.05.398.603 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.902 (> 0.100 thold), f_keep = 0.545 8.05.398.650 I slot launch_slot_: id 0 | task 9431 | processing task, is_child = 0 8.06.343.794 I slot print_timing: id 3 | task 9059 | n_gen = 376, tg = 22.64 t/s, tg_3s = 18.97 t/s 8.07.885.851 I slot print_timing: id 1 | task 8960 | n_gen = 512, tg = 22.51 t/s, tg_3s = 19.26 t/s 8.08.089.485 I slot print_timing: id 2 | task 9379 | n_gen = 100, tg = 21.18 t/s, tg_3s = 21.39 t/s 8.09.348.354 I slot print_timing: id 3 | task 9059 | n_gen = 450, tg = 22.95 t/s, tg_3s = 24.63 t/s 8.10.160.021 I slot print_timing: id 0 | task 9431 | n_gen = 100, tg = 24.64 t/s, tg_3s = 24.89 t/s 8.10.892.317 I slot print_timing: id 1 | task 8960 | n_gen = 586, tg = 22.76 t/s, tg_3s = 24.61 t/s 8.11.096.813 I slot print_timing: id 2 | task 9379 | n_gen = 174, tg = 22.52 t/s, tg_3s = 24.61 t/s 8.12.359.553 I slot print_timing: id 3 | task 9059 | n_gen = 524, tg = 23.17 t/s, tg_3s = 24.57 t/s 8.13.171.715 I slot print_timing: id 0 | task 9431 | n_gen = 174, tg = 24.61 t/s, tg_3s = 24.57 t/s 8.13.902.337 I slot print_timing: id 1 | task 8960 | n_gen = 660, tg = 22.95 t/s, tg_3s = 24.58 t/s 8.14.105.362 I slot print_timing: id 2 | task 9379 | n_gen = 248, tg = 23.10 t/s, tg_3s = 24.60 t/s 8.15.367.752 I slot print_timing: id 3 | task 9059 | n_gen = 598, tg = 23.33 t/s, tg_3s = 24.60 t/s 8.16.179.549 I slot print_timing: id 0 | task 9431 | n_gen = 248, tg = 24.61 t/s, tg_3s = 24.60 t/s 8.16.912.761 I slot print_timing: id 1 | task 8960 | n_gen = 734, tg = 23.10 t/s, tg_3s = 24.58 t/s 8.17.115.983 I slot print_timing: id 2 | task 9379 | n_gen = 322, tg = 23.43 t/s, tg_3s = 24.58 t/s 8.18.380.214 I slot print_timing: id 3 | task 9059 | n_gen = 672, tg = 23.46 t/s, tg_3s = 24.56 t/s 8.18.705.267 I slot print_timing: id 3 | task 9059 | prompt eval time = 705.62 ms / 454 tokens ( 1.55 ms per token, 643.41 tokens per second) 8.18.705.274 I slot print_timing: id 3 | task 9059 | eval time = 28922.68 ms / 680 tokens ( 42.60 ms per token, 23.48 tokens per second) 8.18.705.275 I slot print_timing: id 3 | task 9059 | total time = 29628.30 ms / 1134 tokens 8.18.705.276 I slot print_timing: id 3 | task 9059 | graphs reused = 9142 8.18.705.277 I slot print_timing: id 3 | task 9059 | graph reallocs = 0 / 0 (same size) / (changed size) 8.18.705.376 I slot release: id 3 | task 9059 | stop processing: n_tokens = 1828, truncated = 0 8.18.740.598 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.924 (> 0.100 thold), f_keep = 0.584 8.18.740.635 I slot launch_slot_: id 3 | task 9744 | processing task, is_child = 0 8.19.381.854 I slot print_timing: id 0 | task 9431 | n_gen = 312, tg = 23.49 t/s, tg_3s = 19.99 t/s 8.19.936.490 I slot print_timing: id 1 | task 8960 | n_gen = 793, tg = 22.79 t/s, tg_3s = 19.51 t/s 8.20.141.205 I slot print_timing: id 2 | task 9379 | n_gen = 381, tg = 22.72 t/s, tg_3s = 19.50 t/s 8.22.417.825 I slot print_timing: id 0 | task 9431 | n_gen = 386, tg = 23.66 t/s, tg_3s = 24.37 t/s 8.22.947.555 I slot print_timing: id 1 | task 8960 | n_gen = 867, tg = 22.93 t/s, tg_3s = 24.58 t/s 8.23.150.924 I slot print_timing: id 2 | task 9379 | n_gen = 455, tg = 23.00 t/s, tg_3s = 24.59 t/s 8.23.477.063 I slot print_timing: id 3 | task 9744 | n_gen = 100, tg = 24.59 t/s, tg_3s = 24.84 t/s 8.25.428.114 I slot print_timing: id 0 | task 9431 | n_gen = 460, tg = 23.80 t/s, tg_3s = 24.58 t/s 8.25.958.305 I slot print_timing: id 1 | task 8960 | n_gen = 941, tg = 23.05 t/s, tg_3s = 24.58 t/s 8.26.161.852 I slot print_timing: id 2 | task 9379 | n_gen = 529, tg = 23.21 t/s, tg_3s = 24.58 t/s 8.26.487.459 I slot print_timing: id 3 | task 9744 | n_gen = 174, tg = 24.59 t/s, tg_3s = 24.58 t/s 8.28.438.390 I slot print_timing: id 0 | task 9431 | n_gen = 534, tg = 23.91 t/s, tg_3s = 24.58 t/s 8.28.968.110 I slot print_timing: id 1 | task 8960 | n_gen = 1015, tg = 23.16 t/s, tg_3s = 24.59 t/s 8.29.172.154 I slot print_timing: id 2 | task 9379 | n_gen = 603, tg = 23.37 t/s, tg_3s = 24.58 t/s 8.29.334.764 I slot print_timing: id 1 | task 8960 | prompt eval time = 757.57 ms / 494 tokens ( 1.53 ms per token, 652.09 tokens per second) 8.29.334.770 I slot print_timing: id 1 | task 8960 | eval time = 44149.04 ms / 1024 tokens ( 43.16 ms per token, 23.17 tokens per second) 8.29.334.771 I slot print_timing: id 1 | task 8960 | total time = 44906.60 ms / 1518 tokens 8.29.334.771 I slot print_timing: id 1 | task 8960 | graphs reused = 9383 8.29.334.772 I slot print_timing: id 1 | task 8960 | graph reallocs = 0 / 0 (same size) / (changed size) 8.29.334.878 I slot release: id 1 | task 8960 | stop processing: n_tokens = 2190, truncated = 0 8.29.378.747 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.488 8.29.384.901 I slot launch_slot_: id 1 | task 9991 | processing task, is_child = 0 8.29.512.290 I slot print_timing: id 3 | task 9744 | n_gen = 246, tg = 24.35 t/s, tg_3s = 23.80 t/s 8.31.464.325 I slot print_timing: id 0 | task 9431 | n_gen = 589, tg = 23.22 t/s, tg_3s = 18.18 t/s 8.32.194.514 I slot print_timing: id 2 | task 9379 | n_gen = 658, tg = 22.83 t/s, tg_3s = 18.20 t/s 8.32.522.150 I slot print_timing: id 3 | task 9744 | n_gen = 303, tg = 23.11 t/s, tg_3s = 18.94 t/s 8.34.308.942 I slot print_timing: id 1 | task 9991 | n_gen = 100, tg = 24.63 t/s, tg_3s = 24.88 t/s 8.34.470.774 I slot print_timing: id 0 | task 9431 | n_gen = 663, tg = 23.37 t/s, tg_3s = 24.61 t/s 8.35.202.519 I slot print_timing: id 2 | task 9379 | n_gen = 732, tg = 23.00 t/s, tg_3s = 24.60 t/s 8.35.527.096 I slot print_timing: id 3 | task 9744 | n_gen = 377, tg = 23.39 t/s, tg_3s = 24.63 t/s 8.37.315.452 I slot print_timing: id 1 | task 9991 | n_gen = 174, tg = 24.62 t/s, tg_3s = 24.61 t/s 8.37.478.066 I slot print_timing: id 0 | task 9431 | n_gen = 737, tg = 23.49 t/s, tg_3s = 24.61 t/s 8.38.213.208 I slot print_timing: id 2 | task 9379 | n_gen = 806, tg = 23.13 t/s, tg_3s = 24.58 t/s 8.38.538.881 I slot print_timing: id 3 | task 9744 | n_gen = 451, tg = 23.58 t/s, tg_3s = 24.57 t/s 8.40.329.702 I slot print_timing: id 1 | task 9991 | n_gen = 248, tg = 24.60 t/s, tg_3s = 24.55 t/s 8.40.492.316 I slot print_timing: id 0 | task 9431 | n_gen = 811, tg = 23.58 t/s, tg_3s = 24.55 t/s 8.41.224.705 I slot print_timing: id 2 | task 9379 | n_gen = 880, tg = 23.25 t/s, tg_3s = 24.57 t/s 8.41.551.272 I slot print_timing: id 3 | task 9744 | n_gen = 525, tg = 23.71 t/s, tg_3s = 24.57 t/s 8.43.350.069 I slot print_timing: id 1 | task 9991 | n_gen = 322, tg = 24.58 t/s, tg_3s = 24.50 t/s 8.43.512.903 I slot print_timing: id 0 | task 9431 | n_gen = 885, tg = 23.66 t/s, tg_3s = 24.50 t/s 8.44.247.363 I slot print_timing: id 2 | task 9379 | n_gen = 954, tg = 23.34 t/s, tg_3s = 24.48 t/s 8.44.573.766 I slot print_timing: id 3 | task 9744 | n_gen = 599, tg = 23.80 t/s, tg_3s = 24.48 t/s 8.44.776.423 I slot print_timing: id 2 | task 9379 | prompt eval time = 724.98 ms / 460 tokens ( 1.58 ms per token, 634.50 tokens per second) 8.44.776.427 I slot print_timing: id 2 | task 9379 | eval time = 41361.94 ms / 967 tokens ( 42.82 ms per token, 23.35 tokens per second) 8.44.776.428 I slot print_timing: id 2 | task 9379 | total time = 42086.92 ms / 1427 tokens 8.44.776.429 I slot print_timing: id 2 | task 9379 | graphs reused = 9736 8.44.776.430 I slot print_timing: id 2 | task 9379 | graph reallocs = 0 / 0 (same size) / (changed size) 8.44.776.527 I slot release: id 2 | task 9379 | stop processing: n_tokens = 2101, truncated = 0 8.44.819.908 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.918 (> 0.100 thold), f_keep = 0.508 8.44.819.951 I slot launch_slot_: id 2 | task 10352 | processing task, is_child = 0 8.46.386.418 I slot print_timing: id 1 | task 9991 | n_gen = 380, tg = 23.54 t/s, tg_3s = 19.10 t/s 8.46.548.728 I slot print_timing: id 0 | task 9431 | n_gen = 943, tg = 23.31 t/s, tg_3s = 19.11 t/s 8.47.610.966 I slot print_timing: id 3 | task 9744 | n_gen = 657, tg = 23.30 t/s, tg_3s = 19.10 t/s 8.48.181.408 I slot print_timing: id 3 | task 9744 | prompt eval time = 711.00 ms / 461 tokens ( 1.54 ms per token, 648.38 tokens per second) 8.48.181.416 I slot print_timing: id 3 | task 9744 | eval time = 28729.76 ms / 671 tokens ( 42.88 ms per token, 23.32 tokens per second) 8.48.181.417 I slot print_timing: id 3 | task 9744 | total time = 29440.76 ms / 1132 tokens 8.48.181.418 I slot print_timing: id 3 | task 9744 | graphs reused = 9799 8.48.181.418 I slot print_timing: id 3 | task 9744 | graph reallocs = 0 / 0 (same size) / (changed size) 8.48.181.562 I slot release: id 3 | task 9744 | stop processing: n_tokens = 1826, truncated = 0 8.48.217.138 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.916 (> 0.100 thold), f_keep = 0.585 8.48.217.172 I slot launch_slot_: id 3 | task 10420 | processing task, is_child = 0 8.49.424.879 I slot print_timing: id 1 | task 9991 | n_gen = 439, tg = 22.89 t/s, tg_3s = 19.42 t/s 8.49.588.849 I slot print_timing: id 0 | task 9431 | n_gen = 1002, tg = 23.04 t/s, tg_3s = 19.41 t/s 8.50.244.339 I slot print_timing: id 2 | task 10352 | n_gen = 100, tg = 21.20 t/s, tg_3s = 21.42 t/s 8.50.488.192 I slot print_timing: id 0 | task 9431 | prompt eval time = 744.30 ms / 511 tokens ( 1.46 ms per token, 686.55 tokens per second) 8.50.488.196 I slot print_timing: id 0 | task 9431 | eval time = 44345.22 ms / 1024 tokens ( 43.35 ms per token, 23.07 tokens per second) 8.50.488.197 I slot print_timing: id 0 | task 9431 | total time = 45089.53 ms / 1535 tokens 8.50.488.197 I slot print_timing: id 0 | task 9431 | graphs reused = 9836 8.50.488.198 I slot print_timing: id 0 | task 9431 | graph reallocs = 0 / 0 (same size) / (changed size) 8.50.488.311 I slot release: id 0 | task 9431 | stop processing: n_tokens = 2207, truncated = 0 8.50.525.474 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.950 (> 0.100 thold), f_keep = 0.484 8.50.531.423 I slot launch_slot_: id 0 | task 10462 | processing task, is_child = 0 8.52.463.255 I slot print_timing: id 1 | task 9991 | n_gen = 499, tg = 22.46 t/s, tg_3s = 19.75 t/s 8.53.274.300 I slot print_timing: id 2 | task 10352 | n_gen = 160, tg = 20.65 t/s, tg_3s = 19.80 t/s 8.53.558.612 I slot print_timing: id 3 | task 10420 | n_gen = 100, tg = 21.41 t/s, tg_3s = 21.62 t/s 8.55.215.960 I slot print_timing: id 0 | task 10462 | n_gen = 100, tg = 24.73 t/s, tg_3s = 24.98 t/s 8.55.499.347 I slot print_timing: id 1 | task 9991 | n_gen = 574, tg = 22.73 t/s, tg_3s = 24.70 t/s 8.56.310.529 I slot print_timing: id 2 | task 10352 | n_gen = 235, tg = 21.80 t/s, tg_3s = 24.70 t/s 8.56.594.180 I slot print_timing: id 3 | task 10420 | n_gen = 175, tg = 22.71 t/s, tg_3s = 24.71 t/s 8.58.249.621 I slot print_timing: id 0 | task 10462 | n_gen = 175, tg = 24.73 t/s, tg_3s = 24.72 t/s 8.58.533.836 I slot print_timing: id 1 | task 9991 | n_gen = 649, tg = 22.94 t/s, tg_3s = 24.72 t/s 8.59.346.264 I slot print_timing: id 2 | task 10352 | n_gen = 310, tg = 22.44 t/s, tg_3s = 24.71 t/s 8.59.629.406 I slot print_timing: id 1 | task 9991 | prompt eval time = 904.25 ms / 530 tokens ( 1.71 ms per token, 586.12 tokens per second) 8.59.629.413 I slot print_timing: id 1 | task 9991 | eval time = 29340.24 ms / 676 tokens ( 43.47 ms per token, 23.01 tokens per second) 8.59.629.414 I slot print_timing: id 1 | task 9991 | total time = 30244.49 ms / 1206 tokens 8.59.629.415 I slot print_timing: id 1 | task 9991 | graphs reused = 10043 8.59.629.416 I slot print_timing: id 1 | task 9991 | graph reallocs = 0 / 0 (same size) / (changed size) 8.59.629.529 I slot release: id 1 | task 9991 | stop processing: n_tokens = 1878, truncated = 0 8.59.630.641 I slot print_timing: id 3 | task 10420 | n_gen = 250, tg = 23.28 t/s, tg_3s = 24.70 t/s 8.59.673.145 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.931 (> 0.100 thold), f_keep = 0.569 8.59.673.182 I slot launch_slot_: id 1 | task 10674 | processing task, is_child = 0 9.01.250.909 I slot print_timing: id 0 | task 10462 | n_gen = 233, tg = 23.11 t/s, tg_3s = 19.33 t/s 9.02.385.447 I slot print_timing: id 2 | task 10352 | n_gen = 369, tg = 21.89 t/s, tg_3s = 19.41 t/s 9.02.631.494 I slot print_timing: id 3 | task 10420 | n_gen = 308, tg = 22.41 t/s, tg_3s = 19.33 t/s 9.04.289.601 I slot print_timing: id 0 | task 10462 | n_gen = 308, tg = 23.48 t/s, tg_3s = 24.68 t/s 9.04.411.409 I slot print_timing: id 1 | task 10674 | n_gen = 100, tg = 24.67 t/s, tg_3s = 24.92 t/s 9.05.386.481 I slot print_timing: id 2 | task 10352 | n_gen = 443, tg = 22.31 t/s, tg_3s = 24.66 t/s 9.05.671.052 I slot print_timing: id 3 | task 10420 | n_gen = 383, tg = 22.82 t/s, tg_3s = 24.67 t/s 9.07.294.133 I slot print_timing: id 0 | task 10462 | n_gen = 382, tg = 23.69 t/s, tg_3s = 24.63 t/s 9.07.416.286 I slot print_timing: id 1 | task 10674 | n_gen = 174, tg = 24.65 t/s, tg_3s = 24.63 t/s 9.08.389.802 I slot print_timing: id 2 | task 10352 | n_gen = 517, tg = 22.62 t/s, tg_3s = 24.64 t/s 9.08.674.945 I slot print_timing: id 3 | task 10420 | n_gen = 457, tg = 23.10 t/s, tg_3s = 24.63 t/s 9.09.323.038 I slot print_timing: id 0 | task 10462 | prompt eval time = 682.08 ms / 451 tokens ( 1.51 ms per token, 661.21 tokens per second) 9.09.323.045 I slot print_timing: id 0 | task 10462 | eval time = 18109.52 ms / 432 tokens ( 42.02 ms per token, 23.80 tokens per second) 9.09.323.046 I slot print_timing: id 0 | task 10462 | total time = 18791.60 ms / 883 tokens 9.09.323.046 I slot print_timing: id 0 | task 10462 | graphs reused = 10261 9.09.323.047 I slot print_timing: id 0 | task 10462 | graph reallocs = 0 / 0 (same size) / (changed size) 9.09.323.143 I slot release: id 0 | task 10462 | stop processing: n_tokens = 1555, truncated = 0 9.09.360.129 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.916 (> 0.100 thold), f_keep = 0.687 9.09.360.170 I slot launch_slot_: id 0 | task 10898 | processing task, is_child = 0 9.10.453.569 I slot print_timing: id 1 | task 10674 | n_gen = 233, tg = 23.07 t/s, tg_3s = 19.43 t/s 9.11.395.784 I slot print_timing: id 2 | task 10352 | n_gen = 575, tg = 22.23 t/s, tg_3s = 19.29 t/s 9.11.681.261 I slot print_timing: id 3 | task 10420 | n_gen = 515, tg = 22.60 t/s, tg_3s = 19.29 t/s 9.13.305.695 I slot print_timing: id 2 | task 10352 | prompt eval time = 755.29 ms / 488 tokens ( 1.55 ms per token, 646.11 tokens per second) 9.13.305.703 I slot print_timing: id 2 | task 10352 | eval time = 27730.44 ms / 622 tokens ( 44.65 ms per token, 22.39 tokens per second) 9.13.305.704 I slot print_timing: id 2 | task 10352 | total time = 28485.73 ms / 1110 tokens 9.13.305.705 I slot print_timing: id 2 | task 10352 | graphs reused = 10340 9.13.305.705 I slot print_timing: id 2 | task 10352 | graph reallocs = 0 / 0 (same size) / (changed size) 9.13.305.828 I slot release: id 2 | task 10352 | stop processing: n_tokens = 1784, truncated = 0 9.13.348.755 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.599 9.13.348.792 I slot launch_slot_: id 2 | task 10981 | processing task, is_child = 0 9.14.004.674 I slot print_timing: id 1 | task 10674 | n_gen = 305, tg = 22.34 t/s, tg_3s = 20.28 t/s 9.14.690.413 I slot print_timing: id 3 | task 10420 | n_gen = 573, tg = 22.21 t/s, tg_3s = 19.27 t/s 9.14.769.899 I slot print_timing: id 0 | task 10898 | n_gen = 100, tg = 21.17 t/s, tg_3s = 21.39 t/s 9.17.042.355 I slot print_timing: id 1 | task 10674 | n_gen = 379, tg = 22.71 t/s, tg_3s = 24.36 t/s 9.17.692.685 I slot print_timing: id 3 | task 10420 | n_gen = 647, tg = 22.46 t/s, tg_3s = 24.65 t/s 9.17.771.917 I slot print_timing: id 0 | task 10898 | n_gen = 174, tg = 22.53 t/s, tg_3s = 24.65 t/s 9.18.097.301 I slot print_timing: id 2 | task 10981 | n_gen = 100, tg = 24.65 t/s, tg_3s = 24.90 t/s 9.20.046.703 I slot print_timing: id 1 | task 10674 | n_gen = 453, tg = 23.01 t/s, tg_3s = 24.63 t/s 9.20.370.995 I slot print_timing: id 1 | task 10674 | prompt eval time = 726.06 ms / 460 tokens ( 1.58 ms per token, 633.56 tokens per second) 9.20.371.002 I slot print_timing: id 1 | task 10674 | eval time = 19971.74 ms / 461 tokens ( 43.42 ms per token, 23.03 tokens per second) 9.20.371.003 I slot print_timing: id 1 | task 10674 | total time = 20697.80 ms / 921 tokens 9.20.371.004 I slot print_timing: id 1 | task 10674 | graphs reused = 10493 9.20.371.005 I slot print_timing: id 1 | task 10674 | graph reallocs = 0 / 0 (same size) / (changed size) 9.20.371.112 I slot release: id 1 | task 10674 | stop processing: n_tokens = 1607, truncated = 0 9.20.415.386 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.665 9.20.415.432 I slot launch_slot_: id 1 | task 11140 | processing task, is_child = 0 9.21.078.323 I slot print_timing: id 0 | task 10898 | n_gen = 240, tg = 21.76 t/s, tg_3s = 19.96 t/s 9.21.078.885 I slot print_timing: id 3 | task 10420 | n_gen = 715, tg = 22.21 t/s, tg_3s = 20.08 t/s 9.21.155.178 I slot print_timing: id 2 | task 10981 | n_gen = 159, tg = 22.33 t/s, tg_3s = 19.29 t/s 9.24.082.555 I slot print_timing: id 0 | task 10898 | n_gen = 313, tg = 22.30 t/s, tg_3s = 24.30 t/s 9.24.084.251 I slot print_timing: id 3 | task 10420 | n_gen = 788, tg = 22.39 t/s, tg_3s = 24.29 t/s 9.24.165.021 I slot print_timing: id 2 | task 10981 | n_gen = 233, tg = 23.01 t/s, tg_3s = 24.59 t/s 9.25.178.473 I slot print_timing: id 1 | task 11140 | n_gen = 100, tg = 24.61 t/s, tg_3s = 24.85 t/s 9.27.121.439 I slot print_timing: id 0 | task 10898 | n_gen = 388, tg = 22.73 t/s, tg_3s = 24.68 t/s 9.27.123.091 I slot print_timing: id 3 | task 10420 | n_gen = 863, tg = 22.57 t/s, tg_3s = 24.68 t/s 9.27.204.028 I slot print_timing: id 2 | task 10981 | n_gen = 308, tg = 23.39 t/s, tg_3s = 24.68 t/s 9.28.183.183 I slot print_timing: id 1 | task 11140 | n_gen = 174, tg = 24.61 t/s, tg_3s = 24.63 t/s 9.30.140.015 I slot print_timing: id 0 | task 10898 | n_gen = 462, tg = 23.00 t/s, tg_3s = 24.51 t/s 9.30.141.683 I slot print_timing: id 3 | task 10420 | n_gen = 937, tg = 22.71 t/s, tg_3s = 24.51 t/s 9.30.222.903 I slot print_timing: id 2 | task 10981 | n_gen = 382, tg = 23.60 t/s, tg_3s = 24.51 t/s 9.31.200.582 I slot print_timing: id 1 | task 11140 | n_gen = 248, tg = 24.59 t/s, tg_3s = 24.52 t/s 9.33.160.460 I slot print_timing: id 0 | task 10898 | n_gen = 536, tg = 23.19 t/s, tg_3s = 24.50 t/s 9.33.162.077 I slot print_timing: id 3 | task 10420 | n_gen = 1011, tg = 22.84 t/s, tg_3s = 24.50 t/s 9.33.243.173 I slot print_timing: id 2 | task 10981 | n_gen = 456, tg = 23.74 t/s, tg_3s = 24.50 t/s 9.33.690.239 I slot print_timing: id 3 | task 10420 | prompt eval time = 716.80 ms / 471 tokens ( 1.52 ms per token, 657.09 tokens per second) 9.33.690.246 I slot print_timing: id 3 | task 10420 | eval time = 44756.26 ms / 1024 tokens ( 43.75 ms per token, 22.86 tokens per second) 9.33.690.247 I slot print_timing: id 3 | task 10420 | total time = 45473.06 ms / 1495 tokens 9.33.690.248 I slot print_timing: id 3 | task 10420 | graphs reused = 10799 9.33.690.248 I slot print_timing: id 3 | task 10420 | graph reallocs = 0 / 0 (same size) / (changed size) 9.33.690.353 I slot release: id 3 | task 10420 | stop processing: n_tokens = 2189, truncated = 0 9.33.725.562 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.918 (> 0.100 thold), f_keep = 0.488 9.33.731.430 I slot launch_slot_: id 3 | task 11452 | processing task, is_child = 0 9.34.381.107 I slot print_timing: id 1 | task 11140 | n_gen = 311, tg = 23.44 t/s, tg_3s = 19.81 t/s 9.36.163.111 I slot print_timing: id 0 | task 10898 | n_gen = 594, tg = 22.75 t/s, tg_3s = 19.32 t/s 9.36.245.199 I slot print_timing: id 2 | task 10981 | n_gen = 514, tg = 23.15 t/s, tg_3s = 19.32 t/s 9.37.385.169 I slot print_timing: id 1 | task 11140 | n_gen = 384, tg = 23.60 t/s, tg_3s = 24.30 t/s 9.38.486.402 I slot print_timing: id 3 | task 11452 | n_gen = 100, tg = 24.53 t/s, tg_3s = 24.77 t/s 9.39.174.718 I slot print_timing: id 0 | task 10898 | n_gen = 668, tg = 22.94 t/s, tg_3s = 24.57 t/s 9.39.256.666 I slot print_timing: id 2 | task 10981 | n_gen = 588, tg = 23.32 t/s, tg_3s = 24.57 t/s 9.40.389.000 I slot print_timing: id 1 | task 11140 | n_gen = 458, tg = 23.76 t/s, tg_3s = 24.64 t/s 9.41.323.206 I slot print_timing: id 1 | task 11140 | prompt eval time = 739.46 ms / 478 tokens ( 1.55 ms per token, 646.42 tokens per second) 9.41.323.213 I slot print_timing: id 1 | task 11140 | eval time = 20168.30 ms / 481 tokens ( 42.02 ms per token, 23.80 tokens per second) 9.41.323.214 I slot print_timing: id 1 | task 11140 | total time = 20907.76 ms / 959 tokens 9.41.323.214 I slot print_timing: id 1 | task 11140 | graphs reused = 10966 9.41.323.215 I slot print_timing: id 1 | task 11140 | graph reallocs = 0 / 0 (same size) / (changed size) 9.41.323.327 I slot release: id 1 | task 11140 | stop processing: n_tokens = 1645, truncated = 0 9.41.367.123 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.649 9.41.367.160 I slot launch_slot_: id 1 | task 11625 | processing task, is_child = 0 9.42.019.831 I slot print_timing: id 3 | task 11452 | n_gen = 172, tg = 22.59 t/s, tg_3s = 20.38 t/s 9.42.175.858 I slot print_timing: id 0 | task 10898 | n_gen = 726, tg = 22.60 t/s, tg_3s = 19.33 t/s 9.42.295.389 I slot print_timing: id 2 | task 10981 | n_gen = 647, tg = 22.90 t/s, tg_3s = 19.42 t/s 9.42.825.637 I slot print_timing: id 0 | task 10898 | prompt eval time = 733.65 ms / 493 tokens ( 1.49 ms per token, 671.98 tokens per second) 9.42.825.641 I slot print_timing: id 0 | task 10898 | eval time = 32731.80 ms / 742 tokens ( 44.17 ms per token, 22.64 tokens per second) 9.42.825.642 I slot print_timing: id 0 | task 10898 | total time = 33465.46 ms / 1235 tokens 9.42.825.643 I slot print_timing: id 0 | task 10898 | graphs reused = 10983 9.42.825.643 I slot print_timing: id 0 | task 10898 | graph reallocs = 0 / 0 (same size) / (changed size) 9.42.825.741 I slot release: id 0 | task 10898 | stop processing: n_tokens = 1907, truncated = 0 9.42.862.413 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.560 9.42.862.450 I slot launch_slot_: id 0 | task 11647 | processing task, is_child = 0 9.45.020.224 I slot print_timing: id 3 | task 11452 | n_gen = 230, tg = 21.66 t/s, tg_3s = 19.33 t/s 9.45.303.292 I slot print_timing: id 2 | task 10981 | n_gen = 706, tg = 22.58 t/s, tg_3s = 19.62 t/s 9.46.715.888 I slot print_timing: id 1 | task 11625 | n_gen = 100, tg = 21.43 t/s, tg_3s = 21.64 t/s 9.47.562.399 I slot print_timing: id 0 | task 11647 | n_gen = 100, tg = 24.78 t/s, tg_3s = 25.03 t/s 9.48.048.333 I slot print_timing: id 3 | task 11452 | n_gen = 305, tg = 22.36 t/s, tg_3s = 24.77 t/s 9.48.331.668 I slot print_timing: id 2 | task 10981 | n_gen = 781, tg = 22.77 t/s, tg_3s = 24.77 t/s 9.49.745.318 I slot print_timing: id 1 | task 11625 | n_gen = 175, tg = 22.75 t/s, tg_3s = 24.76 t/s 9.50.595.691 I slot print_timing: id 0 | task 11647 | n_gen = 175, tg = 24.75 t/s, tg_3s = 24.73 t/s 9.51.085.502 I slot print_timing: id 3 | task 11452 | n_gen = 380, tg = 22.78 t/s, tg_3s = 24.69 t/s 9.51.369.554 I slot print_timing: id 2 | task 10981 | n_gen = 856, tg = 22.93 t/s, tg_3s = 24.69 t/s 9.52.751.826 I slot print_timing: id 1 | task 11625 | n_gen = 249, tg = 23.27 t/s, tg_3s = 24.61 t/s 9.53.606.174 I slot print_timing: id 0 | task 11647 | n_gen = 249, tg = 24.70 t/s, tg_3s = 24.58 t/s 9.54.097.756 I slot print_timing: id 3 | task 11452 | n_gen = 454, tg = 23.06 t/s, tg_3s = 24.57 t/s 9.54.383.899 I slot print_timing: id 2 | task 10981 | n_gen = 930, tg = 23.05 t/s, tg_3s = 24.55 t/s 9.55.774.116 I slot print_timing: id 1 | task 11625 | n_gen = 323, tg = 23.54 t/s, tg_3s = 24.48 t/s 9.56.629.695 I slot print_timing: id 0 | task 11647 | n_gen = 323, tg = 24.65 t/s, tg_3s = 24.47 t/s 9.57.121.399 I slot print_timing: id 3 | task 11452 | n_gen = 528, tg = 23.25 t/s, tg_3s = 24.47 t/s 9.57.407.424 I slot print_timing: id 2 | task 10981 | n_gen = 1004, tg = 23.15 t/s, tg_3s = 24.47 t/s 9.58.225.334 I slot print_timing: id 2 | task 10981 | prompt eval time = 731.86 ms / 469 tokens ( 1.56 ms per token, 640.83 tokens per second) 9.58.225.347 I slot print_timing: id 2 | task 10981 | eval time = 44144.67 ms / 1024 tokens ( 43.15 ms per token, 23.17 tokens per second) 9.58.225.348 I slot print_timing: id 2 | task 10981 | total time = 44876.53 ms / 1493 tokens 9.58.225.349 I slot print_timing: id 2 | task 10981 | graphs reused = 11343 9.58.225.350 I slot print_timing: id 2 | task 10981 | graph reallocs = 0 / 0 (same size) / (changed size) 9.58.225.461 I slot release: id 2 | task 10981 | stop processing: n_tokens = 2167, truncated = 0 9.58.268.430 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.881 (> 0.100 thold), f_keep = 0.493 9.58.274.427 I slot launch_slot_: id 2 | task 12012 | processing task, is_child = 0 9.59.137.840 I slot print_timing: id 1 | task 11625 | n_gen = 386, tg = 22.59 t/s, tg_3s = 18.73 t/s 9.59.412.706 I slot print_timing: id 3 | task 11452 | prompt eval time = 718.58 ms / 469 tokens ( 1.53 ms per token, 652.68 tokens per second) 9.59.412.709 I slot print_timing: id 3 | task 11452 | eval time = 24962.69 ms / 564 tokens ( 44.34 ms per token, 22.55 tokens per second) 9.59.412.710 I slot print_timing: id 3 | task 11452 | total time = 25681.26 ms / 1033 tokens 9.59.412.711 I slot print_timing: id 3 | task 11452 | graphs reused = 11347 9.59.412.711 I slot print_timing: id 3 | task 11452 | graph reallocs = 0 / 0 (same size) / (changed size) 9.59.412.807 I slot release: id 3 | task 11452 | stop processing: n_tokens = 1727, truncated = 0 9.59.446.467 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.941 (> 0.100 thold), f_keep = 0.618 9.59.446.493 I slot launch_slot_: id 3 | task 12022 | processing task, is_child = 0 10.00.061.948 I slot print_timing: id 0 | task 11647 | n_gen = 373, tg = 22.55 t/s, tg_3s = 14.57 t/s 10.02.152.674 I slot print_timing: id 1 | task 11625 | n_gen = 445, tg = 22.14 t/s, tg_3s = 19.57 t/s 10.03.081.543 I slot print_timing: id 0 | task 11647 | n_gen = 447, tg = 22.85 t/s, tg_3s = 24.51 t/s 10.03.810.704 I slot print_timing: id 2 | task 12012 | n_gen = 100, tg = 21.54 t/s, tg_3s = 21.75 t/s 10.04.136.290 I slot print_timing: id 3 | task 12022 | n_gen = 100, tg = 24.72 t/s, tg_3s = 24.97 t/s 10.05.189.428 I slot print_timing: id 1 | task 11625 | n_gen = 520, tg = 22.47 t/s, tg_3s = 24.70 t/s 10.06.121.583 I slot print_timing: id 0 | task 11647 | n_gen = 522, tg = 23.10 t/s, tg_3s = 24.67 t/s 10.06.812.388 I slot print_timing: id 2 | task 12012 | n_gen = 174, tg = 22.77 t/s, tg_3s = 24.65 t/s 10.07.137.455 I slot print_timing: id 3 | task 12022 | n_gen = 174, tg = 24.69 t/s, tg_3s = 24.66 t/s 10.08.192.172 I slot print_timing: id 1 | task 11625 | n_gen = 594, tg = 22.72 t/s, tg_3s = 24.64 t/s 10.09.128.007 I slot print_timing: id 0 | task 11647 | n_gen = 596, tg = 23.28 t/s, tg_3s = 24.61 t/s 10.09.575.896 I slot print_timing: id 1 | task 11625 | prompt eval time = 728.50 ms / 465 tokens ( 1.57 ms per token, 638.30 tokens per second) 10.09.575.900 I slot print_timing: id 1 | task 11625 | eval time = 27480.23 ms / 628 tokens ( 43.83 ms per token, 22.82 tokens per second) 10.09.575.901 I slot print_timing: id 1 | task 11625 | total time = 28208.72 ms / 1093 tokens 10.09.575.902 I slot print_timing: id 1 | task 11625 | graphs reused = 11579 10.09.575.903 I slot print_timing: id 1 | task 11625 | graph reallocs = 0 / 0 (same size) / (changed size) 10.09.576.010 I slot release: id 1 | task 11625 | stop processing: n_tokens = 1779, truncated = 0 10.09.619.619 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.950 (> 0.100 thold), f_keep = 0.600 10.09.619.667 I slot launch_slot_: id 1 | task 12259 | processing task, is_child = 0 10.10.241.999 I slot print_timing: id 2 | task 12012 | n_gen = 244, tg = 22.03 t/s, tg_3s = 20.41 t/s 10.10.242.292 I slot print_timing: id 3 | task 12022 | n_gen = 236, tg = 23.24 t/s, tg_3s = 19.97 t/s 10.12.147.618 I slot print_timing: id 0 | task 11647 | n_gen = 655, tg = 22.88 t/s, tg_3s = 19.54 t/s 10.13.242.046 I slot print_timing: id 2 | task 12012 | n_gen = 317, tg = 22.53 t/s, tg_3s = 24.33 t/s 10.13.242.572 I slot print_timing: id 3 | task 12022 | n_gen = 309, tg = 23.49 t/s, tg_3s = 24.33 t/s 10.14.335.315 I slot print_timing: id 1 | task 12259 | n_gen = 100, tg = 24.65 t/s, tg_3s = 24.89 t/s 10.15.185.917 I slot print_timing: id 0 | task 11647 | n_gen = 730, tg = 23.06 t/s, tg_3s = 24.68 t/s 10.16.282.736 I slot print_timing: id 2 | task 12012 | n_gen = 392, tg = 22.91 t/s, tg_3s = 24.67 t/s 10.16.283.409 I slot print_timing: id 3 | task 12022 | n_gen = 384, tg = 23.71 t/s, tg_3s = 24.66 t/s 10.17.337.020 I slot print_timing: id 1 | task 12259 | n_gen = 174, tg = 24.65 t/s, tg_3s = 24.65 t/s 10.17.903.191 I slot print_timing: id 0 | task 11647 | prompt eval time = 704.27 ms / 467 tokens ( 1.51 ms per token, 663.10 tokens per second) 10.17.903.198 I slot print_timing: id 0 | task 11647 | eval time = 34336.46 ms / 797 tokens ( 43.14 ms per token, 23.18 tokens per second) 10.17.903.199 I slot print_timing: id 0 | task 11647 | total time = 35040.73 ms / 1264 tokens 10.17.903.200 I slot print_timing: id 0 | task 11647 | graphs reused = 11764 10.17.903.200 I slot print_timing: id 0 | task 11647 | graph reallocs = 0 / 0 (same size) / (changed size) 10.17.903.301 I slot release: id 0 | task 11647 | stop processing: n_tokens = 1936, truncated = 0 10.17.940.071 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.924 (> 0.100 thold), f_keep = 0.552 10.17.940.113 I slot launch_slot_: id 0 | task 12450 | processing task, is_child = 0 10.19.061.952 I slot print_timing: id 3 | task 12022 | prompt eval time = 684.90 ms / 440 tokens ( 1.56 ms per token, 642.43 tokens per second) 10.19.061.960 I slot print_timing: id 3 | task 12022 | eval time = 18930.55 ms / 437 tokens ( 43.42 ms per token, 23.03 tokens per second) 10.19.061.961 I slot print_timing: id 3 | task 12022 | total time = 19615.45 ms / 877 tokens 10.19.061.962 I slot print_timing: id 3 | task 12022 | graphs reused = 11774 10.19.061.963 I slot print_timing: id 3 | task 12022 | graph reallocs = 0 / 0 (same size) / (changed size) 10.19.062.099 I slot release: id 3 | task 12022 | stop processing: n_tokens = 1571, truncated = 0 10.19.098.041 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.680 10.19.098.073 I slot launch_slot_: id 3 | task 12464 | processing task, is_child = 0 10.19.720.428 I slot print_timing: id 2 | task 12012 | n_gen = 447, tg = 21.75 t/s, tg_3s = 16.00 t/s 10.20.365.759 I slot print_timing: id 1 | task 12259 | n_gen = 218, tg = 21.60 t/s, tg_3s = 14.53 t/s 10.22.752.822 I slot print_timing: id 2 | task 12012 | n_gen = 521, tg = 22.09 t/s, tg_3s = 24.40 t/s 10.23.277.790 I slot print_timing: id 0 | task 12450 | n_gen = 100, tg = 21.42 t/s, tg_3s = 21.64 t/s 10.23.399.098 I slot print_timing: id 1 | task 12259 | n_gen = 293, tg = 22.32 t/s, tg_3s = 24.73 t/s 10.23.805.051 I slot print_timing: id 3 | task 12464 | n_gen = 100, tg = 24.65 t/s, tg_3s = 24.90 t/s 10.25.753.637 I slot print_timing: id 2 | task 12012 | n_gen = 595, tg = 22.38 t/s, tg_3s = 24.66 t/s 10.26.279.773 I slot print_timing: id 0 | task 12450 | n_gen = 174, tg = 22.69 t/s, tg_3s = 24.65 t/s 10.26.401.847 I slot print_timing: id 1 | task 12259 | n_gen = 367, tg = 22.76 t/s, tg_3s = 24.64 t/s 10.26.807.639 I slot print_timing: id 3 | task 12464 | n_gen = 174, tg = 24.65 t/s, tg_3s = 24.65 t/s 10.26.888.127 I slot print_timing: id 2 | task 12012 | prompt eval time = 939.13 ms / 537 tokens ( 1.75 ms per token, 571.80 tokens per second) 10.26.888.134 I slot print_timing: id 2 | task 12012 | eval time = 27674.56 ms / 623 tokens ( 44.49 ms per token, 22.48 tokens per second) 10.26.888.135 I slot print_timing: id 2 | task 12012 | total time = 28613.69 ms / 1160 tokens 10.26.888.136 I slot print_timing: id 2 | task 12012 | graphs reused = 11947 10.26.888.137 I slot print_timing: id 2 | task 12012 | graph reallocs = 0 / 0 (same size) / (changed size) 10.26.888.259 I slot release: id 2 | task 12012 | stop processing: n_tokens = 1834, truncated = 0 10.26.931.336 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.582 10.26.931.376 I slot launch_slot_: id 2 | task 12643 | processing task, is_child = 0 10.29.302.031 I slot print_timing: id 0 | task 12450 | n_gen = 233, tg = 21.79 t/s, tg_3s = 19.52 t/s 10.29.423.994 I slot print_timing: id 1 | task 12259 | n_gen = 426, tg = 22.24 t/s, tg_3s = 19.52 t/s 10.29.829.701 I slot print_timing: id 3 | task 12464 | n_gen = 233, tg = 23.11 t/s, tg_3s = 19.52 t/s 10.31.651.444 I slot print_timing: id 2 | task 12643 | n_gen = 100, tg = 24.68 t/s, tg_3s = 24.93 t/s 10.32.340.035 I slot print_timing: id 0 | task 12450 | n_gen = 308, tg = 22.44 t/s, tg_3s = 24.69 t/s 10.32.461.354 I slot print_timing: id 1 | task 12259 | n_gen = 501, tg = 22.58 t/s, tg_3s = 24.69 t/s 10.32.868.954 I slot print_timing: id 3 | task 12464 | n_gen = 308, tg = 23.47 t/s, tg_3s = 24.68 t/s 10.34.653.497 I slot print_timing: id 2 | task 12643 | n_gen = 174, tg = 24.67 t/s, tg_3s = 24.65 t/s 10.35.340.316 I slot print_timing: id 0 | task 12450 | n_gen = 382, tg = 22.84 t/s, tg_3s = 24.66 t/s 10.35.501.435 I slot print_timing: id 1 | task 12259 | n_gen = 576, tg = 22.83 t/s, tg_3s = 24.67 t/s 10.35.907.508 I slot print_timing: id 3 | task 12464 | n_gen = 383, tg = 23.70 t/s, tg_3s = 24.68 t/s 10.37.689.584 I slot print_timing: id 2 | task 12643 | n_gen = 249, tg = 24.68 t/s, tg_3s = 24.70 t/s 10.38.377.800 I slot print_timing: id 0 | task 12450 | n_gen = 457, tg = 23.12 t/s, tg_3s = 24.69 t/s 10.38.539.738 I slot print_timing: id 1 | task 12259 | n_gen = 651, tg = 23.03 t/s, tg_3s = 24.68 t/s 10.38.945.973 I slot print_timing: id 3 | task 12464 | n_gen = 458, tg = 23.86 t/s, tg_3s = 24.68 t/s 10.40.695.771 I slot print_timing: id 2 | task 12643 | n_gen = 323, tg = 24.66 t/s, tg_3s = 24.62 t/s 10.41.385.509 I slot print_timing: id 0 | task 12450 | n_gen = 531, tg = 23.32 t/s, tg_3s = 24.60 t/s 10.41.386.081 I slot print_timing: id 1 | task 12259 | prompt eval time = 698.62 ms / 437 tokens ( 1.60 ms per token, 625.52 tokens per second) 10.41.386.086 I slot print_timing: id 1 | task 12259 | eval time = 31067.78 ms / 721 tokens ( 43.15 ms per token, 23.18 tokens per second) 10.41.386.087 I slot print_timing: id 1 | task 12259 | total time = 31766.40 ms / 1158 tokens 10.41.386.088 I slot print_timing: id 1 | task 12259 | graphs reused = 12283 10.41.386.088 I slot print_timing: id 1 | task 12259 | graph reallocs = 0 / 0 (same size) / (changed size) 10.41.386.207 I slot release: id 1 | task 12259 | stop processing: n_tokens = 1844, truncated = 0 10.41.429.518 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.579 10.41.429.554 I slot launch_slot_: id 1 | task 12986 | processing task, is_child = 0 10.42.074.114 I slot print_timing: id 3 | task 12464 | n_gen = 520, tg = 23.29 t/s, tg_3s = 19.82 t/s 10.43.729.718 I slot print_timing: id 2 | task 12643 | n_gen = 382, tg = 23.68 t/s, tg_3s = 19.45 t/s 10.44.417.071 I slot print_timing: id 0 | task 12450 | n_gen = 590, tg = 22.86 t/s, tg_3s = 19.46 t/s 10.45.107.899 I slot print_timing: id 3 | task 12464 | n_gen = 594, tg = 23.42 t/s, tg_3s = 24.39 t/s 10.46.159.298 I slot print_timing: id 1 | task 12986 | n_gen = 100, tg = 24.69 t/s, tg_3s = 24.94 t/s 10.46.731.290 I slot print_timing: id 2 | task 12643 | n_gen = 456, tg = 23.83 t/s, tg_3s = 24.65 t/s 10.47.421.173 I slot print_timing: id 0 | task 12450 | n_gen = 664, tg = 23.05 t/s, tg_3s = 24.63 t/s 10.48.114.421 I slot print_timing: id 3 | task 12464 | n_gen = 668, tg = 23.55 t/s, tg_3s = 24.61 t/s 10.49.169.635 I slot print_timing: id 1 | task 12986 | n_gen = 174, tg = 24.65 t/s, tg_3s = 24.58 t/s 10.49.738.994 I slot print_timing: id 2 | task 12643 | n_gen = 530, tg = 23.94 t/s, tg_3s = 24.60 t/s 10.50.430.276 I slot print_timing: id 0 | task 12450 | n_gen = 738, tg = 23.20 t/s, tg_3s = 24.59 t/s 10.51.122.380 I slot print_timing: id 3 | task 12464 | n_gen = 742, tg = 23.65 t/s, tg_3s = 24.60 t/s 10.52.180.407 I slot print_timing: id 1 | task 12986 | n_gen = 248, tg = 24.63 t/s, tg_3s = 24.58 t/s 10.52.750.506 I slot print_timing: id 2 | task 12643 | n_gen = 604, tg = 24.01 t/s, tg_3s = 24.57 t/s 10.53.441.538 I slot print_timing: id 0 | task 12450 | n_gen = 812, tg = 23.31 t/s, tg_3s = 24.57 t/s 10.54.135.569 I slot print_timing: id 3 | task 12464 | n_gen = 816, tg = 23.73 t/s, tg_3s = 24.56 t/s 10.55.191.507 I slot print_timing: id 1 | task 12986 | n_gen = 322, tg = 24.61 t/s, tg_3s = 24.58 t/s 10.55.761.727 I slot print_timing: id 2 | task 12643 | n_gen = 678, tg = 24.07 t/s, tg_3s = 24.57 t/s 10.56.454.203 I slot print_timing: id 0 | task 12450 | n_gen = 886, tg = 23.41 t/s, tg_3s = 24.56 t/s 10.57.151.157 I slot print_timing: id 3 | task 12464 | n_gen = 890, tg = 23.79 t/s, tg_3s = 24.54 t/s 10.58.213.518 I slot print_timing: id 1 | task 12986 | n_gen = 396, tg = 24.59 t/s, tg_3s = 24.49 t/s 10.58.785.922 I slot print_timing: id 2 | task 12643 | n_gen = 752, tg = 24.11 t/s, tg_3s = 24.47 t/s 10.59.439.565 I slot print_timing: id 3 | task 12464 | prompt eval time = 691.52 ms / 447 tokens ( 1.55 ms per token, 646.41 tokens per second) 10.59.439.573 I slot print_timing: id 3 | task 12464 | eval time = 39649.97 ms / 946 tokens ( 41.96 ms per token, 23.83 tokens per second) 10.59.439.574 I slot print_timing: id 3 | task 12464 | total time = 40341.48 ms / 1393 tokens 10.59.439.575 I slot print_timing: id 3 | task 12464 | graphs reused = 12705 10.59.439.575 I slot print_timing: id 3 | task 12464 | graph reallocs = 0 / 0 (same size) / (changed size) 10.59.439.675 I slot release: id 3 | task 12464 | stop processing: n_tokens = 2087, truncated = 0 10.59.473.717 I slot print_timing: id 0 | task 12450 | n_gen = 960, tg = 23.49 t/s, tg_3s = 24.51 t/s 10.59.474.881 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.512 10.59.474.916 I slot launch_slot_: id 3 | task 13415 | processing task, is_child = 0 11.01.248.188 I slot print_timing: id 1 | task 12986 | n_gen = 455, tg = 23.77 t/s, tg_3s = 19.44 t/s 11.01.820.986 I slot print_timing: id 2 | task 12643 | n_gen = 811, tg = 23.70 t/s, tg_3s = 19.44 t/s 11.02.476.044 I slot print_timing: id 0 | task 12450 | n_gen = 1018, tg = 23.21 t/s, tg_3s = 19.32 t/s 11.02.721.583 I slot print_timing: id 0 | task 12450 | prompt eval time = 716.39 ms / 483 tokens ( 1.48 ms per token, 674.22 tokens per second) 11.02.721.590 I slot print_timing: id 0 | task 12450 | eval time = 44065.08 ms / 1024 tokens ( 43.07 ms per token, 23.22 tokens per second) 11.02.721.591 I slot print_timing: id 0 | task 12450 | total time = 44781.46 ms / 1507 tokens 11.02.721.591 I slot print_timing: id 0 | task 12450 | graphs reused = 12766 11.02.721.592 I slot print_timing: id 0 | task 12450 | graph reallocs = 0 / 0 (same size) / (changed size) 11.02.721.686 I slot release: id 0 | task 12450 | stop processing: n_tokens = 2179, truncated = 0 11.02.758.698 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.490 11.02.766.103 I slot launch_slot_: id 0 | task 13481 | processing task, is_child = 0 11.04.258.225 I slot print_timing: id 1 | task 12986 | n_gen = 513, tg = 23.16 t/s, tg_3s = 19.27 t/s 11.04.828.026 I slot print_timing: id 2 | task 12643 | n_gen = 869, tg = 23.34 t/s, tg_3s = 19.29 t/s 11.04.869.174 I slot print_timing: id 3 | task 13415 | n_gen = 100, tg = 21.14 t/s, tg_3s = 21.35 t/s 11.07.273.775 I slot print_timing: id 1 | task 12986 | n_gen = 587, tg = 23.32 t/s, tg_3s = 24.54 t/s 11.07.517.186 I slot print_timing: id 0 | task 13481 | n_gen = 100, tg = 24.55 t/s, tg_3s = 24.79 t/s 11.07.842.397 I slot print_timing: id 2 | task 12643 | n_gen = 943, tg = 23.43 t/s, tg_3s = 24.55 t/s 11.07.883.438 I slot print_timing: id 3 | task 13415 | n_gen = 174, tg = 22.48 t/s, tg_3s = 24.55 t/s 11.10.281.445 I slot print_timing: id 1 | task 12986 | n_gen = 661, tg = 23.46 t/s, tg_3s = 24.60 t/s 11.10.525.107 I slot print_timing: id 0 | task 13481 | n_gen = 174, tg = 24.57 t/s, tg_3s = 24.60 t/s 11.10.851.842 I slot print_timing: id 2 | task 12643 | n_gen = 1017, tg = 23.51 t/s, tg_3s = 24.59 t/s 11.10.892.852 I slot print_timing: id 3 | task 13415 | n_gen = 248, tg = 23.07 t/s, tg_3s = 24.59 t/s 11.11.136.134 I slot print_timing: id 2 | task 12643 | prompt eval time = 709.15 ms / 453 tokens ( 1.57 ms per token, 638.79 tokens per second) 11.11.136.139 I slot print_timing: id 2 | task 12643 | eval time = 43495.60 ms / 1024 tokens ( 42.52 ms per token, 23.52 tokens per second) 11.11.136.140 I slot print_timing: id 2 | task 12643 | total time = 44204.75 ms / 1477 tokens 11.11.136.140 I slot print_timing: id 2 | task 12643 | graphs reused = 12953 11.11.136.141 I slot print_timing: id 2 | task 12643 | graph reallocs = 0 / 0 (same size) / (changed size) 11.11.136.254 I slot release: id 2 | task 12643 | stop processing: n_tokens = 2172, truncated = 0 11.11.179.014 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.492 11.11.181.558 I slot launch_slot_: id 2 | task 13673 | processing task, is_child = 0 11.12.324.013 I slot print_timing: id 1 | task 12986 | prompt eval time = 720.79 ms / 454 tokens ( 1.59 ms per token, 629.86 tokens per second) 11.12.324.021 I slot print_timing: id 1 | task 12986 | eval time = 30173.66 ms / 695 tokens ( 43.48 ms per token, 23.00 tokens per second) 11.12.324.022 I slot print_timing: id 1 | task 12986 | total time = 30894.45 ms / 1149 tokens 11.12.324.023 I slot print_timing: id 1 | task 12986 | graphs reused = 12962 11.12.324.024 I slot print_timing: id 1 | task 12986 | graph reallocs = 0 / 0 (same size) / (changed size) 11.12.324.148 I slot release: id 1 | task 12986 | stop processing: n_tokens = 1835, truncated = 0 11.12.368.371 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.582 11.12.368.415 I slot launch_slot_: id 1 | task 13687 | processing task, is_child = 0 11.13.540.618 I slot print_timing: id 0 | task 13481 | n_gen = 216, tg = 21.38 t/s, tg_3s = 13.93 t/s 11.13.907.524 I slot print_timing: id 3 | task 13415 | n_gen = 290, tg = 21.06 t/s, tg_3s = 13.93 t/s 11.16.579.126 I slot print_timing: id 0 | task 13481 | n_gen = 291, tg = 22.15 t/s, tg_3s = 24.68 t/s 11.16.580.206 I slot print_timing: id 2 | task 13673 | n_gen = 100, tg = 21.25 t/s, tg_3s = 21.47 t/s 11.16.944.520 I slot print_timing: id 3 | task 13415 | n_gen = 365, tg = 21.72 t/s, tg_3s = 24.70 t/s 11.17.105.358 I slot print_timing: id 1 | task 13687 | n_gen = 100, tg = 24.72 t/s, tg_3s = 24.97 t/s 11.19.612.584 I slot print_timing: id 0 | task 13481 | n_gen = 366, tg = 22.63 t/s, tg_3s = 24.72 t/s 11.19.613.657 I slot print_timing: id 2 | task 13673 | n_gen = 175, tg = 22.62 t/s, tg_3s = 24.72 t/s 11.19.979.040 I slot print_timing: id 3 | task 13415 | n_gen = 440, tg = 22.18 t/s, tg_3s = 24.72 t/s 11.20.140.235 I slot print_timing: id 1 | task 13687 | n_gen = 175, tg = 24.71 t/s, tg_3s = 24.71 t/s 11.22.616.426 I slot print_timing: id 0 | task 13481 | n_gen = 440, tg = 22.95 t/s, tg_3s = 24.64 t/s 11.22.617.528 I slot print_timing: id 2 | task 13673 | n_gen = 249, tg = 23.19 t/s, tg_3s = 24.63 t/s 11.22.982.205 I slot print_timing: id 3 | task 13415 | n_gen = 514, tg = 22.50 t/s, tg_3s = 24.64 t/s 11.23.142.744 I slot print_timing: id 1 | task 13687 | n_gen = 249, tg = 24.69 t/s, tg_3s = 24.65 t/s 11.25.655.856 I slot print_timing: id 0 | task 13481 | n_gen = 515, tg = 23.18 t/s, tg_3s = 24.68 t/s 11.25.656.986 I slot print_timing: id 2 | task 13673 | n_gen = 324, tg = 23.52 t/s, tg_3s = 24.68 t/s 11.25.982.619 I slot print_timing: id 3 | task 13415 | n_gen = 588, tg = 22.76 t/s, tg_3s = 24.66 t/s 11.26.143.604 I slot print_timing: id 1 | task 13687 | n_gen = 323, tg = 24.69 t/s, tg_3s = 24.66 t/s 11.26.913.331 I slot print_timing: id 3 | task 13415 | prompt eval time = 711.45 ms / 460 tokens ( 1.55 ms per token, 646.57 tokens per second) 11.26.913.338 I slot print_timing: id 3 | task 13415 | eval time = 26726.95 ms / 611 tokens ( 43.81 ms per token, 22.82 tokens per second) 11.26.913.339 I slot print_timing: id 3 | task 13415 | total time = 27438.40 ms / 1071 tokens 11.26.913.340 I slot print_timing: id 3 | task 13415 | graphs reused = 13301 11.26.913.341 I slot print_timing: id 3 | task 13415 | graph reallocs = 0 / 0 (same size) / (changed size) 11.26.913.442 I slot release: id 3 | task 13415 | stop processing: n_tokens = 1765, truncated = 0 11.26.948.623 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.605 11.26.948.657 I slot launch_slot_: id 3 | task 14032 | processing task, is_child = 0 11.28.669.996 I slot print_timing: id 0 | task 13481 | n_gen = 574, tg = 22.75 t/s, tg_3s = 19.57 t/s 11.28.671.088 I slot print_timing: id 2 | task 13673 | n_gen = 383, tg = 22.81 t/s, tg_3s = 19.57 t/s 11.29.158.044 I slot print_timing: id 1 | task 13687 | n_gen = 382, tg = 23.73 t/s, tg_3s = 19.57 t/s 11.30.213.447 I slot print_timing: id 0 | task 13481 | prompt eval time = 717.99 ms / 483 tokens ( 1.49 ms per token, 672.72 tokens per second) 11.30.213.451 I slot print_timing: id 0 | task 13481 | eval time = 26729.34 ms / 612 tokens ( 43.75 ms per token, 22.86 tokens per second) 11.30.213.452 I slot print_timing: id 0 | task 13481 | total time = 27447.33 ms / 1095 tokens 11.30.213.453 I slot print_timing: id 0 | task 13481 | graphs reused = 13363 11.30.213.454 I slot print_timing: id 0 | task 13481 | graph reallocs = 0 / 0 (same size) / (changed size) 11.30.213.554 I slot release: id 0 | task 13481 | stop processing: n_tokens = 1769, truncated = 0 11.30.250.465 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.604 11.30.250.502 I slot launch_slot_: id 0 | task 14099 | processing task, is_child = 0 11.31.678.798 I slot print_timing: id 2 | task 13673 | n_gen = 442, tg = 22.32 t/s, tg_3s = 19.62 t/s 11.32.165.778 I slot print_timing: id 1 | task 13687 | n_gen = 441, tg = 23.08 t/s, tg_3s = 19.62 t/s 11.32.288.258 I slot print_timing: id 3 | task 14032 | n_gen = 100, tg = 21.38 t/s, tg_3s = 21.60 t/s 11.34.707.100 I slot print_timing: id 2 | task 13673 | n_gen = 517, tg = 22.65 t/s, tg_3s = 24.77 t/s 11.34.948.395 I slot print_timing: id 0 | task 14099 | n_gen = 100, tg = 24.79 t/s, tg_3s = 25.04 t/s 11.35.190.375 I slot print_timing: id 1 | task 13687 | n_gen = 516, tg = 23.31 t/s, tg_3s = 24.80 t/s 11.35.312.584 I slot print_timing: id 3 | task 14032 | n_gen = 175, tg = 22.73 t/s, tg_3s = 24.80 t/s 11.35.392.898 I slot print_timing: id 2 | task 13673 | prompt eval time = 740.18 ms / 482 tokens ( 1.54 ms per token, 651.19 tokens per second) 11.35.392.906 I slot print_timing: id 2 | task 13673 | eval time = 23471.15 ms / 534 tokens ( 44.04 ms per token, 22.71 tokens per second) 11.35.392.906 I slot print_timing: id 2 | task 13673 | total time = 24211.33 ms / 1016 tokens 11.35.392.907 I slot print_timing: id 2 | task 13673 | graphs reused = 13473 11.35.392.908 I slot print_timing: id 2 | task 13673 | graph reallocs = 0 / 0 (same size) / (changed size) 11.35.393.037 I slot release: id 2 | task 13673 | stop processing: n_tokens = 1711, truncated = 0 11.35.436.273 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.624 11.35.436.308 I slot launch_slot_: id 2 | task 14213 | processing task, is_child = 0 11.37.952.701 I slot print_timing: id 0 | task 14099 | n_gen = 159, tg = 22.58 t/s, tg_3s = 19.64 t/s 11.38.195.838 I slot print_timing: id 1 | task 13687 | n_gen = 575, tg = 22.87 t/s, tg_3s = 19.63 t/s 11.38.318.703 I slot print_timing: id 3 | task 14032 | n_gen = 234, tg = 21.86 t/s, tg_3s = 19.63 t/s 11.40.142.586 I slot print_timing: id 2 | task 14213 | n_gen = 100, tg = 24.71 t/s, tg_3s = 24.96 t/s 11.40.955.920 I slot print_timing: id 0 | task 14099 | n_gen = 233, tg = 23.20 t/s, tg_3s = 24.64 t/s 11.41.200.836 I slot print_timing: id 1 | task 13687 | n_gen = 649, tg = 23.06 t/s, tg_3s = 24.63 t/s 11.41.324.140 I slot print_timing: id 3 | task 14032 | n_gen = 308, tg = 22.46 t/s, tg_3s = 24.62 t/s 11.43.148.861 I slot print_timing: id 2 | task 14213 | n_gen = 174, tg = 24.67 t/s, tg_3s = 24.62 t/s 11.43.960.307 I slot print_timing: id 0 | task 14099 | n_gen = 307, tg = 23.53 t/s, tg_3s = 24.63 t/s 11.44.205.304 I slot print_timing: id 1 | task 13687 | n_gen = 723, tg = 23.21 t/s, tg_3s = 24.63 t/s 11.44.328.766 I slot print_timing: id 3 | task 14032 | n_gen = 382, tg = 22.85 t/s, tg_3s = 24.63 t/s 11.46.157.716 I slot print_timing: id 2 | task 14213 | n_gen = 248, tg = 24.65 t/s, tg_3s = 24.59 t/s 11.46.969.522 I slot print_timing: id 0 | task 14099 | n_gen = 381, tg = 23.73 t/s, tg_3s = 24.59 t/s 11.47.213.661 I slot print_timing: id 1 | task 13687 | n_gen = 797, tg = 23.33 t/s, tg_3s = 24.60 t/s 11.47.336.656 I slot print_timing: id 3 | task 14032 | n_gen = 456, tg = 23.12 t/s, tg_3s = 24.60 t/s 11.49.165.683 I slot print_timing: id 2 | task 14213 | n_gen = 322, tg = 24.64 t/s, tg_3s = 24.60 t/s 11.49.979.018 I slot print_timing: id 0 | task 14099 | n_gen = 455, tg = 23.87 t/s, tg_3s = 24.59 t/s 11.50.223.747 I slot print_timing: id 1 | task 13687 | n_gen = 871, tg = 23.44 t/s, tg_3s = 24.58 t/s 11.50.347.078 I slot print_timing: id 3 | task 14032 | n_gen = 530, tg = 23.32 t/s, tg_3s = 24.58 t/s 11.52.181.096 I slot print_timing: id 2 | task 14213 | n_gen = 396, tg = 24.62 t/s, tg_3s = 24.54 t/s 11.52.670.276 I slot print_timing: id 1 | task 13687 | prompt eval time = 731.37 ms / 471 tokens ( 1.55 ms per token, 643.99 tokens per second) 11.52.670.283 I slot print_timing: id 1 | task 13687 | eval time = 39570.48 ms / 931 tokens ( 42.55 ms per token, 23.50 tokens per second) 11.52.670.284 I slot print_timing: id 1 | task 13687 | total time = 40301.85 ms / 1402 tokens 11.52.670.285 I slot print_timing: id 1 | task 13687 | graphs reused = 13877 11.52.670.285 I slot print_timing: id 1 | task 13687 | graph reallocs = 0 / 0 (same size) / (changed size) 11.52.670.393 I slot release: id 1 | task 13687 | stop processing: n_tokens = 2088, truncated = 0 11.52.713.989 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.511 11.52.714.029 I slot launch_slot_: id 1 | task 14624 | processing task, is_child = 0 11.53.377.588 I slot print_timing: id 0 | task 14099 | n_gen = 523, tg = 23.28 t/s, tg_3s = 20.01 t/s 11.53.378.099 I slot print_timing: id 3 | task 14032 | n_gen = 589, tg = 22.86 t/s, tg_3s = 19.47 t/s 11.53.653.834 I slot print_timing: id 3 | task 14032 | prompt eval time = 709.47 ms / 457 tokens ( 1.55 ms per token, 644.14 tokens per second) 11.53.653.837 I slot print_timing: id 3 | task 14032 | eval time = 25995.70 ms / 595 tokens ( 43.76 ms per token, 22.85 tokens per second) 11.53.653.838 I slot print_timing: id 3 | task 14032 | total time = 26705.17 ms / 1052 tokens 11.53.653.839 I slot print_timing: id 3 | task 14032 | graphs reused = 13881 11.53.653.839 I slot print_timing: id 3 | task 14032 | graph reallocs = 0 / 0 (same size) / (changed size) 11.53.653.906 I slot release: id 3 | task 14032 | stop processing: n_tokens = 1746, truncated = 0 11.53.687.564 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.883 (> 0.100 thold), f_keep = 0.612 11.53.687.589 I slot launch_slot_: id 3 | task 14633 | processing task, is_child = 0 11.55.218.933 I slot print_timing: id 2 | task 14213 | n_gen = 438, tg = 22.90 t/s, tg_3s = 13.83 t/s 11.56.391.875 I slot print_timing: id 0 | task 14099 | n_gen = 580, tg = 22.76 t/s, tg_3s = 18.91 t/s 11.56.756.859 I slot print_timing: id 0 | task 14099 | prompt eval time = 704.93 ms / 467 tokens ( 1.51 ms per token, 662.48 tokens per second) 11.56.756.863 I slot print_timing: id 0 | task 14099 | eval time = 25801.42 ms / 589 tokens ( 43.88 ms per token, 22.79 tokens per second) 11.56.756.864 I slot print_timing: id 0 | task 14099 | total time = 26506.35 ms / 1056 tokens 11.56.756.865 I slot print_timing: id 0 | task 14099 | graphs reused = 13937 11.56.756.866 I slot print_timing: id 0 | task 14099 | graph reallocs = 0 / 0 (same size) / (changed size) 11.56.756.965 I slot release: id 0 | task 14099 | stop processing: n_tokens = 1730, truncated = 0 11.56.793.559 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.617 11.56.793.596 I slot launch_slot_: id 0 | task 14694 | processing task, is_child = 0 11.58.224.807 I slot print_timing: id 2 | task 14213 | n_gen = 497, tg = 22.46 t/s, tg_3s = 19.63 t/s 11.58.758.267 I slot print_timing: id 1 | task 14624 | n_gen = 100, tg = 18.66 t/s, tg_3s = 18.85 t/s 11.59.084.319 I slot print_timing: id 3 | task 14633 | n_gen = 100, tg = 21.34 t/s, tg_3s = 21.56 t/s 12.01.232.581 I slot print_timing: id 2 | task 14213 | n_gen = 571, tg = 22.71 t/s, tg_3s = 24.60 t/s 12.01.514.851 I slot print_timing: id 0 | task 14694 | n_gen = 100, tg = 24.71 t/s, tg_3s = 24.96 t/s 12.01.798.321 I slot print_timing: id 1 | task 14624 | n_gen = 175, tg = 20.85 t/s, tg_3s = 24.67 t/s 12.02.122.101 I slot print_timing: id 3 | task 14633 | n_gen = 175, tg = 22.67 t/s, tg_3s = 24.69 t/s 12.04.262.035 I slot print_timing: id 2 | task 14213 | n_gen = 646, tg = 22.93 t/s, tg_3s = 24.76 t/s 12.04.544.173 I slot print_timing: id 0 | task 14694 | n_gen = 175, tg = 24.73 t/s, tg_3s = 24.76 t/s 12.04.830.898 I slot print_timing: id 1 | task 14624 | n_gen = 250, tg = 21.89 t/s, tg_3s = 24.73 t/s 12.05.156.269 I slot print_timing: id 3 | task 14633 | n_gen = 250, tg = 23.25 t/s, tg_3s = 24.72 t/s 12.07.265.046 I slot print_timing: id 2 | task 14213 | n_gen = 720, tg = 23.10 t/s, tg_3s = 24.64 t/s 12.07.547.471 I slot print_timing: id 0 | task 14694 | n_gen = 249, tg = 24.70 t/s, tg_3s = 24.64 t/s 12.07.831.408 I slot print_timing: id 1 | task 14624 | n_gen = 324, tg = 22.47 t/s, tg_3s = 24.66 t/s 12.08.157.310 I slot print_timing: id 3 | task 14633 | n_gen = 324, tg = 23.56 t/s, tg_3s = 24.66 t/s 12.10.268.080 I slot print_timing: id 2 | task 14213 | n_gen = 794, tg = 23.23 t/s, tg_3s = 24.64 t/s 12.10.551.085 I slot print_timing: id 0 | task 14694 | n_gen = 323, tg = 24.69 t/s, tg_3s = 24.64 t/s 12.10.836.935 I slot print_timing: id 1 | task 14624 | n_gen = 398, tg = 22.84 t/s, tg_3s = 24.62 t/s 12.11.164.914 I slot print_timing: id 3 | task 14633 | n_gen = 398, tg = 23.74 t/s, tg_3s = 24.60 t/s 12.13.276.395 I slot print_timing: id 2 | task 14213 | n_gen = 868, tg = 23.34 t/s, tg_3s = 24.60 t/s 12.13.559.509 I slot print_timing: id 0 | task 14694 | n_gen = 397, tg = 24.67 t/s, tg_3s = 24.60 t/s 12.13.844.036 I slot print_timing: id 1 | task 14624 | n_gen = 472, tg = 23.10 t/s, tg_3s = 24.61 t/s 12.14.170.440 I slot print_timing: id 3 | task 14633 | n_gen = 472, tg = 23.88 t/s, tg_3s = 24.62 t/s 12.16.289.783 I slot print_timing: id 2 | task 14213 | n_gen = 942, tg = 23.44 t/s, tg_3s = 24.56 t/s 12.16.575.094 I slot print_timing: id 0 | task 14694 | n_gen = 471, tg = 24.65 t/s, tg_3s = 24.54 t/s 12.16.861.522 I slot print_timing: id 1 | task 14624 | n_gen = 546, tg = 23.28 t/s, tg_3s = 24.52 t/s 12.17.190.272 I slot print_timing: id 3 | task 14633 | n_gen = 546, tg = 23.96 t/s, tg_3s = 24.50 t/s 12.19.308.964 I slot print_timing: id 2 | task 14213 | n_gen = 1016, tg = 23.51 t/s, tg_3s = 24.51 t/s 12.19.593.330 I slot print_timing: id 0 | task 14694 | n_gen = 545, tg = 24.63 t/s, tg_3s = 24.52 t/s 12.19.635.222 I slot print_timing: id 2 | task 14213 | prompt eval time = 700.11 ms / 442 tokens ( 1.58 ms per token, 631.33 tokens per second) 12.19.635.226 I slot print_timing: id 2 | task 14213 | eval time = 43498.80 ms / 1024 tokens ( 42.52 ms per token, 23.52 tokens per second) 12.19.635.227 I slot print_timing: id 2 | task 14213 | total time = 44198.91 ms / 1466 tokens 12.19.635.228 I slot print_timing: id 2 | task 14213 | graphs reused = 14480 12.19.635.229 I slot print_timing: id 2 | task 14213 | graph reallocs = 0 / 0 (same size) / (changed size) 12.19.635.332 I slot release: id 2 | task 14213 | stop processing: n_tokens = 2161, truncated = 0 12.19.679.288 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.494 12.19.685.139 I slot launch_slot_: id 2 | task 15243 | processing task, is_child = 0 12.20.317.208 I slot print_timing: id 1 | task 14624 | n_gen = 616, tg = 22.89 t/s, tg_3s = 20.26 t/s 12.20.317.474 I slot print_timing: id 3 | task 14633 | n_gen = 608, tg = 23.46 t/s, tg_3s = 19.83 t/s 12.22.632.445 I slot print_timing: id 0 | task 14694 | n_gen = 604, tg = 24.00 t/s, tg_3s = 19.41 t/s 12.23.324.360 I slot print_timing: id 1 | task 14624 | n_gen = 689, tg = 23.03 t/s, tg_3s = 24.28 t/s 12.23.325.405 I slot print_timing: id 3 | task 14633 | n_gen = 681, tg = 23.55 t/s, tg_3s = 24.27 t/s 12.24.424.379 I slot print_timing: id 2 | task 15243 | n_gen = 100, tg = 24.56 t/s, tg_3s = 24.81 t/s 12.25.643.783 I slot print_timing: id 0 | task 14694 | n_gen = 678, tg = 24.06 t/s, tg_3s = 24.57 t/s 12.26.336.113 I slot print_timing: id 1 | task 14624 | n_gen = 763, tg = 23.17 t/s, tg_3s = 24.57 t/s 12.26.337.305 I slot print_timing: id 3 | task 14633 | n_gen = 755, tg = 23.64 t/s, tg_3s = 24.57 t/s 12.27.437.219 I slot print_timing: id 2 | task 15243 | n_gen = 174, tg = 24.56 t/s, tg_3s = 24.56 t/s 12.28.657.136 I slot print_timing: id 0 | task 14694 | n_gen = 752, tg = 24.11 t/s, tg_3s = 24.56 t/s 12.29.349.242 I slot print_timing: id 1 | task 14624 | n_gen = 837, tg = 23.29 t/s, tg_3s = 24.56 t/s 12.29.350.405 I slot print_timing: id 3 | task 14633 | n_gen = 829, tg = 23.72 t/s, tg_3s = 24.56 t/s 12.29.922.192 I slot print_timing: id 1 | task 14624 | prompt eval time = 740.17 ms / 480 tokens ( 1.54 ms per token, 648.50 tokens per second) 12.29.922.200 I slot print_timing: id 1 | task 14624 | eval time = 36467.98 ms / 851 tokens ( 42.90 ms per token, 23.31 tokens per second) 12.29.922.201 I slot print_timing: id 1 | task 14624 | total time = 37208.15 ms / 1331 tokens 12.29.922.201 I slot print_timing: id 1 | task 14624 | graphs reused = 14712 12.29.922.202 I slot print_timing: id 1 | task 14624 | graph reallocs = 0 / 0 (same size) / (changed size) 12.29.922.316 I slot release: id 1 | task 14624 | stop processing: n_tokens = 2017, truncated = 0 12.29.965.949 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.529 12.29.965.992 I slot launch_slot_: id 1 | task 15481 | processing task, is_child = 0 12.30.618.439 I slot print_timing: id 2 | task 15243 | n_gen = 237, tg = 23.08 t/s, tg_3s = 19.80 t/s 12.31.663.788 I slot print_timing: id 0 | task 14694 | n_gen = 810, tg = 23.69 t/s, tg_3s = 19.29 t/s 12.32.360.056 I slot print_timing: id 3 | task 14633 | n_gen = 887, tg = 23.37 t/s, tg_3s = 19.27 t/s 12.33.621.935 I slot print_timing: id 2 | task 15243 | n_gen = 310, tg = 23.36 t/s, tg_3s = 24.31 t/s 12.34.677.226 I slot print_timing: id 0 | task 14694 | n_gen = 884, tg = 23.76 t/s, tg_3s = 24.56 t/s 12.34.718.225 I slot print_timing: id 1 | task 15481 | n_gen = 100, tg = 24.61 t/s, tg_3s = 24.85 t/s 12.35.370.460 I slot print_timing: id 3 | task 14633 | n_gen = 961, tg = 23.46 t/s, tg_3s = 24.58 t/s 12.35.613.022 I slot print_timing: id 0 | task 14694 | prompt eval time = 714.64 ms / 483 tokens ( 1.48 ms per token, 675.87 tokens per second) 12.35.613.026 I slot print_timing: id 0 | task 14694 | eval time = 38104.78 ms / 907 tokens ( 42.06 ms per token, 23.78 tokens per second) 12.35.613.027 I slot print_timing: id 0 | task 14694 | total time = 38819.42 ms / 1390 tokens 12.35.613.028 I slot print_timing: id 0 | task 14694 | graphs reused = 14832 12.35.613.029 I slot print_timing: id 0 | task 14694 | graph reallocs = 0 / 0 (same size) / (changed size) 12.35.613.127 I slot release: id 0 | task 14694 | stop processing: n_tokens = 2064, truncated = 0 12.35.649.823 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.517 12.35.649.856 I slot launch_slot_: id 0 | task 15606 | processing task, is_child = 0 12.36.629.757 I slot print_timing: id 2 | task 15243 | n_gen = 368, tg = 22.60 t/s, tg_3s = 19.28 t/s 12.37.733.769 I slot print_timing: id 1 | task 15481 | n_gen = 158, tg = 22.30 t/s, tg_3s = 19.23 t/s 12.38.388.809 I slot print_timing: id 3 | task 14633 | n_gen = 1019, tg = 23.17 t/s, tg_3s = 19.22 t/s 12.38.551.891 I slot print_timing: id 2 | task 15243 | prompt eval time = 708.22 ms / 448 tokens ( 1.58 ms per token, 632.57 tokens per second) 12.38.551.895 I slot print_timing: id 2 | task 15243 | eval time = 18158.51 ms / 415 tokens ( 43.86 ms per token, 22.80 tokens per second) 12.38.551.896 I slot print_timing: id 2 | task 15243 | total time = 18866.73 ms / 863 tokens 12.38.551.897 I slot print_timing: id 2 | task 15243 | graphs reused = 14885 12.38.551.898 I slot print_timing: id 2 | task 15243 | graph reallocs = 0 / 0 (same size) / (changed size) 12.38.552.042 I slot release: id 2 | task 15243 | stop processing: n_tokens = 1558, truncated = 0 12.38.595.621 I slot print_timing: id 3 | task 14633 | prompt eval time = 757.89 ms / 514 tokens ( 1.47 ms per token, 678.20 tokens per second) 12.38.595.628 I slot print_timing: id 3 | task 14633 | eval time = 44150.13 ms / 1024 tokens ( 43.16 ms per token, 23.17 tokens per second) 12.38.595.629 I slot print_timing: id 3 | task 14633 | total time = 44908.03 ms / 1538 tokens 12.38.595.630 I slot print_timing: id 3 | task 14633 | graphs reused = 14885 12.38.595.631 I slot print_timing: id 3 | task 14633 | graph reallocs = 0 / 0 (same size) / (changed size) 12.38.595.726 I slot release: id 3 | task 14633 | stop processing: n_tokens = 2232, truncated = 0 12.38.595.736 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.685 12.38.595.776 I slot launch_slot_: id 2 | task 15663 | processing task, is_child = 0 12.39.234.108 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.478 12.39.234.241 I slot launch_slot_: id 3 | task 15665 | processing task, is_child = 0 12.40.762.053 I slot print_timing: id 1 | task 15481 | n_gen = 201, tg = 19.87 t/s, tg_3s = 14.20 t/s 12.41.690.566 I slot print_timing: id 0 | task 15606 | n_gen = 100, tg = 18.67 t/s, tg_3s = 18.86 t/s 12.43.794.239 I slot print_timing: id 1 | task 15481 | n_gen = 276, tg = 20.99 t/s, tg_3s = 24.73 t/s 12.43.955.916 I slot print_timing: id 2 | task 15663 | n_gen = 100, tg = 24.54 t/s, tg_3s = 24.79 t/s 12.43.996.666 I slot print_timing: id 3 | task 15665 | n_gen = 100, tg = 24.71 t/s, tg_3s = 24.96 t/s 12.44.720.595 I slot print_timing: id 0 | task 15606 | n_gen = 175, tg = 20.88 t/s, tg_3s = 24.75 t/s 12.46.822.390 I slot print_timing: id 1 | task 15481 | n_gen = 351, tg = 21.70 t/s, tg_3s = 24.77 t/s 12.46.985.073 I slot print_timing: id 2 | task 15663 | n_gen = 175, tg = 24.63 t/s, tg_3s = 24.76 t/s 12.47.026.005 I slot print_timing: id 3 | task 15665 | n_gen = 175, tg = 24.73 t/s, tg_3s = 24.76 t/s 12.47.754.927 I slot print_timing: id 0 | task 15606 | n_gen = 250, tg = 21.91 t/s, tg_3s = 24.72 t/s 12.49.824.455 I slot print_timing: id 1 | task 15481 | n_gen = 425, tg = 22.16 t/s, tg_3s = 24.65 t/s 12.49.986.873 I slot print_timing: id 2 | task 15663 | n_gen = 249, tg = 24.64 t/s, tg_3s = 24.65 t/s 12.50.027.848 I slot print_timing: id 3 | task 15665 | n_gen = 249, tg = 24.71 t/s, tg_3s = 24.65 t/s 12.50.756.787 I slot print_timing: id 0 | task 15606 | n_gen = 324, tg = 22.48 t/s, tg_3s = 24.65 t/s 12.52.829.747 I slot print_timing: id 1 | task 15481 | n_gen = 499, tg = 22.50 t/s, tg_3s = 24.62 t/s 12.52.992.164 I slot print_timing: id 2 | task 15663 | n_gen = 323, tg = 24.63 t/s, tg_3s = 24.62 t/s 12.53.033.202 I slot print_timing: id 3 | task 15665 | n_gen = 323, tg = 24.69 t/s, tg_3s = 24.62 t/s 12.53.763.084 I slot print_timing: id 0 | task 15606 | n_gen = 398, tg = 22.85 t/s, tg_3s = 24.61 t/s 12.55.835.940 I slot print_timing: id 1 | task 15481 | n_gen = 573, tg = 22.75 t/s, tg_3s = 24.62 t/s 12.55.998.561 I slot print_timing: id 2 | task 15663 | n_gen = 397, tg = 24.63 t/s, tg_3s = 24.61 t/s 12.56.039.862 I slot print_timing: id 3 | task 15665 | n_gen = 397, tg = 24.67 t/s, tg_3s = 24.61 t/s 12.56.768.879 I slot print_timing: id 0 | task 15606 | n_gen = 472, tg = 23.11 t/s, tg_3s = 24.62 t/s 12.58.840.917 I slot print_timing: id 1 | task 15481 | n_gen = 647, tg = 22.95 t/s, tg_3s = 24.63 t/s 12.59.003.279 I slot print_timing: id 2 | task 15663 | n_gen = 471, tg = 24.63 t/s, tg_3s = 24.63 t/s 12.59.044.491 I slot print_timing: id 3 | task 15665 | n_gen = 471, tg = 24.67 t/s, tg_3s = 24.63 t/s 12.59.528.345 I slot print_timing: id 2 | task 15663 | prompt eval time = 1319.34 ms / 454 tokens ( 2.91 ms per token, 344.11 tokens per second) 12.59.528.353 I slot print_timing: id 2 | task 15663 | eval time = 19607.03 ms / 484 tokens ( 40.59 ms per token, 24.63 tokens per second) 12.59.528.354 I slot print_timing: id 2 | task 15663 | total time = 20926.36 ms / 938 tokens 12.59.528.355 I slot print_timing: id 2 | task 15663 | graphs reused = 15364 12.59.528.355 I slot print_timing: id 2 | task 15663 | graph reallocs = 0 / 0 (same size) / (changed size) 12.59.528.457 I slot release: id 2 | task 15663 | stop processing: n_tokens = 1633, truncated = 0 12.59.571.274 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.654 12.59.571.307 I slot launch_slot_: id 2 | task 16151 | processing task, is_child = 0 13.00.223.978 I slot print_timing: id 0 | task 15606 | n_gen = 542, tg = 22.70 t/s, tg_3s = 20.26 t/s 13.01.853.358 I slot print_timing: id 1 | task 15481 | n_gen = 705, tg = 22.59 t/s, tg_3s = 19.25 t/s 13.02.057.272 I slot print_timing: id 3 | task 15665 | n_gen = 529, tg = 23.93 t/s, tg_3s = 19.25 t/s 13.03.232.972 I slot print_timing: id 0 | task 15606 | n_gen = 615, tg = 22.87 t/s, tg_3s = 24.26 t/s 13.04.329.089 I slot print_timing: id 2 | task 16151 | n_gen = 100, tg = 24.57 t/s, tg_3s = 24.82 t/s 13.04.370.065 I slot print_timing: id 3 | task 15665 | prompt eval time = 755.80 ms / 465 tokens ( 1.63 ms per token, 615.25 tokens per second) 13.04.370.069 I slot print_timing: id 3 | task 15665 | eval time = 24379.85 ms / 586 tokens ( 41.67 ms per token, 24.00 tokens per second) 13.04.370.070 I slot print_timing: id 3 | task 15665 | total time = 25135.64 ms / 1051 tokens 13.04.370.071 I slot print_timing: id 3 | task 15665 | graphs reused = 15463 13.04.370.072 I slot print_timing: id 3 | task 15665 | graph reallocs = 0 / 0 (same size) / (changed size) 13.04.370.187 I slot release: id 3 | task 15665 | stop processing: n_tokens = 1745, truncated = 0 13.04.405.475 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.612 13.04.405.512 I slot launch_slot_: id 3 | task 16255 | processing task, is_child = 0 13.05.052.190 I slot print_timing: id 1 | task 15481 | n_gen = 769, tg = 22.35 t/s, tg_3s = 20.01 t/s 13.06.250.755 I slot print_timing: id 0 | task 15606 | n_gen = 674, tg = 22.54 t/s, tg_3s = 19.55 t/s 13.07.343.241 I slot print_timing: id 2 | task 16151 | n_gen = 159, tg = 22.43 t/s, tg_3s = 19.57 t/s 13.08.072.225 I slot print_timing: id 1 | task 15481 | n_gen = 843, tg = 22.53 t/s, tg_3s = 24.50 t/s 13.08.274.689 I slot print_timing: id 1 | task 15481 | prompt eval time = 728.74 ms / 463 tokens ( 1.57 ms per token, 635.34 tokens per second) 13.08.274.693 I slot print_timing: id 1 | task 15481 | eval time = 37579.95 ms / 848 tokens ( 44.37 ms per token, 22.54 tokens per second) 13.08.274.694 I slot print_timing: id 1 | task 15481 | total time = 38308.69 ms / 1311 tokens 13.08.274.695 I slot print_timing: id 1 | task 15481 | graphs reused = 15540 13.08.274.695 I slot print_timing: id 1 | task 15481 | graph reallocs = 0 / 0 (same size) / (changed size) 13.08.274.800 I slot release: id 1 | task 15481 | stop processing: n_tokens = 1997, truncated = 0 13.08.318.432 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.535 13.08.318.471 I slot launch_slot_: id 1 | task 16337 | processing task, is_child = 0 13.09.281.128 I slot print_timing: id 0 | task 15606 | n_gen = 733, tg = 22.25 t/s, tg_3s = 19.47 t/s 13.09.770.973 I slot print_timing: id 3 | task 16255 | n_gen = 100, tg = 21.29 t/s, tg_3s = 21.51 t/s 13.10.379.199 I slot print_timing: id 2 | task 16151 | n_gen = 218, tg = 21.53 t/s, tg_3s = 19.43 t/s 13.12.284.715 I slot print_timing: id 0 | task 15606 | n_gen = 807, tg = 22.45 t/s, tg_3s = 24.64 t/s 13.12.773.975 I slot print_timing: id 3 | task 16255 | n_gen = 174, tg = 22.61 t/s, tg_3s = 24.64 t/s 13.13.056.691 I slot print_timing: id 1 | task 16337 | n_gen = 100, tg = 24.66 t/s, tg_3s = 24.91 t/s 13.13.381.212 I slot print_timing: id 2 | task 16151 | n_gen = 292, tg = 22.25 t/s, tg_3s = 24.65 t/s 13.15.293.149 I slot print_timing: id 0 | task 15606 | n_gen = 881, tg = 22.62 t/s, tg_3s = 24.60 t/s 13.15.786.375 I slot print_timing: id 3 | task 16255 | n_gen = 248, tg = 23.16 t/s, tg_3s = 24.57 t/s 13.16.071.970 I slot print_timing: id 1 | task 16337 | n_gen = 174, tg = 24.61 t/s, tg_3s = 24.54 t/s 13.16.398.755 I slot print_timing: id 2 | task 16151 | n_gen = 366, tg = 22.67 t/s, tg_3s = 24.52 t/s 13.18.319.652 I slot print_timing: id 0 | task 15606 | n_gen = 955, tg = 22.75 t/s, tg_3s = 24.45 t/s 13.18.810.683 I slot print_timing: id 3 | task 16255 | n_gen = 322, tg = 23.45 t/s, tg_3s = 24.47 t/s 13.19.094.902 I slot print_timing: id 1 | task 16337 | n_gen = 248, tg = 24.57 t/s, tg_3s = 24.48 t/s 13.19.421.907 I slot print_timing: id 2 | task 16151 | n_gen = 440, tg = 22.96 t/s, tg_3s = 24.48 t/s 13.21.130.217 I slot print_timing: id 0 | task 15606 | prompt eval time = 738.71 ms / 504 tokens ( 1.47 ms per token, 682.27 tokens per second) 13.21.130.224 I slot print_timing: id 0 | task 15606 | eval time = 44741.65 ms / 1024 tokens ( 43.74 ms per token, 22.86 tokens per second) 13.21.130.225 I slot print_timing: id 0 | task 15606 | total time = 45480.35 ms / 1528 tokens 13.21.130.226 I slot print_timing: id 0 | task 15606 | graphs reused = 15835 13.21.130.227 I slot print_timing: id 0 | task 15606 | graph reallocs = 0 / 0 (same size) / (changed size) 13.21.130.326 I slot release: id 0 | task 15606 | stop processing: n_tokens = 2202, truncated = 0 13.21.167.251 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.485 13.21.172.814 I slot launch_slot_: id 0 | task 16638 | processing task, is_child = 0 13.21.835.642 I slot print_timing: id 3 | task 16255 | n_gen = 381, tg = 22.73 t/s, tg_3s = 19.50 t/s 13.22.101.753 I slot print_timing: id 1 | task 16337 | n_gen = 306, tg = 23.36 t/s, tg_3s = 19.29 t/s 13.22.423.121 I slot print_timing: id 2 | task 16151 | n_gen = 498, tg = 22.47 t/s, tg_3s = 19.33 t/s 13.24.858.484 I slot print_timing: id 3 | task 16255 | n_gen = 455, tg = 23.00 t/s, tg_3s = 24.48 t/s 13.25.102.391 I slot print_timing: id 1 | task 16337 | n_gen = 380, tg = 23.60 t/s, tg_3s = 24.66 t/s 13.25.428.546 I slot print_timing: id 2 | task 16151 | n_gen = 572, tg = 22.72 t/s, tg_3s = 24.62 t/s 13.25.915.700 I slot print_timing: id 0 | task 16638 | n_gen = 100, tg = 24.66 t/s, tg_3s = 24.91 t/s 13.27.869.289 I slot print_timing: id 3 | task 16255 | n_gen = 529, tg = 23.21 t/s, tg_3s = 24.58 t/s 13.28.111.451 I slot print_timing: id 1 | task 16337 | n_gen = 454, tg = 23.76 t/s, tg_3s = 24.59 t/s 13.28.435.991 I slot print_timing: id 2 | task 16151 | n_gen = 646, tg = 22.92 t/s, tg_3s = 24.61 t/s 13.28.920.775 I slot print_timing: id 0 | task 16638 | n_gen = 174, tg = 24.65 t/s, tg_3s = 24.62 t/s 13.30.462.847 I slot print_timing: id 2 | task 16151 | prompt eval time = 729.10 ms / 466 tokens ( 1.56 ms per token, 639.14 tokens per second) 13.30.462.860 I slot print_timing: id 2 | task 16151 | eval time = 30162.43 ms / 696 tokens ( 43.40 ms per token, 23.04 tokens per second) 13.30.462.860 I slot print_timing: id 2 | task 16151 | total time = 30891.53 ms / 1162 tokens 13.30.462.861 I slot print_timing: id 2 | task 16151 | graphs reused = 16045 13.30.462.864 I slot print_timing: id 2 | task 16151 | graph reallocs = 0 / 0 (same size) / (changed size) 13.30.462.968 I slot release: id 2 | task 16151 | stop processing: n_tokens = 1857, truncated = 0 13.30.506.357 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.575 13.30.506.401 I slot launch_slot_: id 2 | task 16853 | processing task, is_child = 0 13.31.152.898 I slot print_timing: id 1 | task 16337 | n_gen = 514, tg = 23.20 t/s, tg_3s = 19.73 t/s 13.31.153.195 I slot print_timing: id 3 | task 16255 | n_gen = 595, tg = 22.82 t/s, tg_3s = 20.10 t/s 13.31.957.526 I slot print_timing: id 0 | task 16638 | n_gen = 233, tg = 23.07 t/s, tg_3s = 19.43 t/s 13.34.153.127 I slot print_timing: id 1 | task 16337 | n_gen = 587, tg = 23.34 t/s, tg_3s = 24.33 t/s 13.34.154.082 I slot print_timing: id 3 | task 16255 | n_gen = 668, tg = 22.97 t/s, tg_3s = 24.33 t/s 13.34.962.693 I slot print_timing: id 0 | task 16638 | n_gen = 307, tg = 23.43 t/s, tg_3s = 24.62 t/s 13.35.247.065 I slot print_timing: id 2 | task 16853 | n_gen = 100, tg = 24.64 t/s, tg_3s = 24.89 t/s 13.37.193.145 I slot print_timing: id 1 | task 16337 | n_gen = 662, tg = 23.48 t/s, tg_3s = 24.67 t/s 13.37.194.194 I slot print_timing: id 3 | task 16255 | n_gen = 743, tg = 23.13 t/s, tg_3s = 24.67 t/s 13.37.966.455 I slot print_timing: id 0 | task 16638 | n_gen = 381, tg = 23.65 t/s, tg_3s = 24.64 t/s 13.38.252.744 I slot print_timing: id 2 | task 16853 | n_gen = 174, tg = 24.63 t/s, tg_3s = 24.62 t/s 13.40.206.332 I slot print_timing: id 1 | task 16337 | n_gen = 736, tg = 23.59 t/s, tg_3s = 24.56 t/s 13.40.207.448 I slot print_timing: id 3 | task 16255 | n_gen = 817, tg = 23.26 t/s, tg_3s = 24.56 t/s 13.40.979.241 I slot print_timing: id 0 | task 16638 | n_gen = 455, tg = 23.80 t/s, tg_3s = 24.56 t/s 13.41.265.020 I slot print_timing: id 2 | task 16853 | n_gen = 248, tg = 24.61 t/s, tg_3s = 24.57 t/s 13.43.222.148 I slot print_timing: id 1 | task 16337 | n_gen = 810, tg = 23.67 t/s, tg_3s = 24.54 t/s 13.43.223.311 I slot print_timing: id 3 | task 16255 | n_gen = 891, tg = 23.36 t/s, tg_3s = 24.54 t/s 13.43.999.439 I slot print_timing: id 0 | task 16638 | n_gen = 529, tg = 23.89 t/s, tg_3s = 24.50 t/s 13.44.287.241 I slot print_timing: id 2 | task 16853 | n_gen = 322, tg = 24.58 t/s, tg_3s = 24.49 t/s 13.46.242.018 I slot print_timing: id 1 | task 16337 | n_gen = 884, tg = 23.74 t/s, tg_3s = 24.50 t/s 13.46.243.089 I slot print_timing: id 3 | task 16255 | n_gen = 965, tg = 23.44 t/s, tg_3s = 24.51 t/s 13.46.283.303 I slot print_timing: id 2 | task 16853 | prompt eval time = 722.55 ms / 456 tokens ( 1.58 ms per token, 631.10 tokens per second) 13.46.283.311 I slot print_timing: id 2 | task 16853 | eval time = 15054.35 ms / 371 tokens ( 40.69 ms per token, 24.58 tokens per second) 13.46.283.313 I slot print_timing: id 2 | task 16853 | total time = 15776.90 ms / 827 tokens 13.46.283.314 I slot print_timing: id 2 | task 16853 | graphs reused = 16412 13.46.283.315 I slot print_timing: id 2 | task 16853 | graph reallocs = 0 / 0 (same size) / (changed size) 13.46.283.427 I slot release: id 2 | task 16853 | stop processing: n_tokens = 1522, truncated = 0 13.46.326.692 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.702 13.46.326.731 I slot launch_slot_: id 2 | task 17227 | processing task, is_child = 0 13.47.032.100 I slot print_timing: id 0 | task 16638 | n_gen = 588, tg = 23.36 t/s, tg_3s = 19.45 t/s 13.48.182.559 I slot print_timing: id 3 | task 16255 | prompt eval time = 715.79 ms / 467 tokens ( 1.53 ms per token, 652.42 tokens per second) 13.48.182.567 I slot print_timing: id 3 | task 16255 | eval time = 43061.24 ms / 997 tokens ( 43.23 ms per token, 23.13 tokens per second) 13.48.182.568 I slot print_timing: id 3 | task 16255 | total time = 43777.04 ms / 1464 tokens 13.48.182.569 I slot print_timing: id 3 | task 16255 | graphs reused = 16439 13.48.182.570 I slot print_timing: id 3 | task 16255 | graph reallocs = 0 / 0 (same size) / (changed size) 13.48.182.685 I slot release: id 3 | task 16255 | stop processing: n_tokens = 2158, truncated = 0 13.48.218.567 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.495 13.48.224.024 I slot launch_slot_: id 3 | task 17259 | processing task, is_child = 0 13.49.273.308 I slot print_timing: id 1 | task 16337 | n_gen = 928, tg = 23.04 t/s, tg_3s = 14.52 t/s 13.50.051.054 I slot print_timing: id 0 | task 16638 | n_gen = 647, tg = 22.95 t/s, tg_3s = 19.54 t/s 13.51.685.841 I slot print_timing: id 2 | task 17227 | n_gen = 100, tg = 21.28 t/s, tg_3s = 21.49 t/s 13.52.295.329 I slot print_timing: id 1 | task 16337 | n_gen = 1002, tg = 23.14 t/s, tg_3s = 24.49 t/s 13.52.947.547 I slot print_timing: id 3 | task 17259 | n_gen = 100, tg = 24.54 t/s, tg_3s = 24.79 t/s 13.53.068.070 I slot print_timing: id 0 | task 16638 | n_gen = 721, tg = 23.10 t/s, tg_3s = 24.53 t/s 13.53.190.175 I slot print_timing: id 1 | task 16337 | prompt eval time = 724.27 ms / 458 tokens ( 1.58 ms per token, 632.36 tokens per second) 13.53.190.182 I slot print_timing: id 1 | task 16337 | eval time = 44147.43 ms / 1024 tokens ( 43.15 ms per token, 23.17 tokens per second) 13.53.190.183 I slot print_timing: id 1 | task 16337 | total time = 44871.70 ms / 1482 tokens 13.53.190.183 I slot print_timing: id 1 | task 16337 | graphs reused = 16543 13.53.190.184 I slot print_timing: id 1 | task 16337 | graph reallocs = 0 / 0 (same size) / (changed size) 13.53.190.285 I slot release: id 1 | task 16337 | stop processing: n_tokens = 2168, truncated = 0 13.53.233.784 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.887 (> 0.100 thold), f_keep = 0.493 13.53.239.944 I slot launch_slot_: id 1 | task 17368 | processing task, is_child = 0 13.54.708.483 I slot print_timing: id 2 | task 17227 | n_gen = 157, tg = 20.32 t/s, tg_3s = 18.86 t/s 13.55.719.927 I slot print_timing: id 0 | task 16638 | prompt eval time = 729.03 ms / 487 tokens ( 1.50 ms per token, 668.01 tokens per second) 13.55.719.934 I slot print_timing: id 0 | task 16638 | eval time = 33818.07 ms / 769 tokens ( 44.03 ms per token, 22.71 tokens per second) 13.55.719.935 I slot print_timing: id 0 | task 16638 | total time = 34547.10 ms / 1256 tokens 13.55.719.936 I slot print_timing: id 0 | task 16638 | graphs reused = 16583 13.55.719.937 I slot print_timing: id 0 | task 16638 | graph reallocs = 0 / 0 (same size) / (changed size) 13.55.720.040 I slot release: id 0 | task 16638 | stop processing: n_tokens = 1930, truncated = 0 13.55.756.810 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.553 13.55.756.850 I slot launch_slot_: id 0 | task 17414 | processing task, is_child = 0 13.56.405.521 I slot print_timing: id 3 | task 17259 | n_gen = 153, tg = 20.29 t/s, tg_3s = 15.33 t/s 13.57.725.834 I slot print_timing: id 2 | task 17227 | n_gen = 216, tg = 20.11 t/s, tg_3s = 19.55 t/s 13.58.695.410 I slot print_timing: id 1 | task 17368 | n_gen = 100, tg = 21.39 t/s, tg_3s = 21.60 t/s 13.59.424.333 I slot print_timing: id 3 | task 17259 | n_gen = 227, tg = 21.50 t/s, tg_3s = 24.51 t/s 14.00.474.920 I slot print_timing: id 0 | task 17414 | n_gen = 100, tg = 24.73 t/s, tg_3s = 24.98 t/s 14.00.758.823 I slot print_timing: id 2 | task 17227 | n_gen = 291, tg = 21.13 t/s, tg_3s = 24.73 t/s 14.01.730.200 I slot print_timing: id 1 | task 17368 | n_gen = 175, tg = 22.70 t/s, tg_3s = 24.71 t/s 14.02.461.773 I slot print_timing: id 3 | task 17259 | n_gen = 302, tg = 22.22 t/s, tg_3s = 24.69 t/s 14.03.511.148 I slot print_timing: id 0 | task 17414 | n_gen = 175, tg = 24.72 t/s, tg_3s = 24.70 t/s 14.03.795.046 I slot print_timing: id 2 | task 17227 | n_gen = 366, tg = 21.78 t/s, tg_3s = 24.70 t/s 14.04.766.220 I slot print_timing: id 1 | task 17368 | n_gen = 250, tg = 23.27 t/s, tg_3s = 24.70 t/s 14.05.498.090 I slot print_timing: id 3 | task 17259 | n_gen = 377, tg = 22.67 t/s, tg_3s = 24.70 t/s 14.06.546.455 I slot print_timing: id 0 | task 17414 | n_gen = 250, tg = 24.72 t/s, tg_3s = 24.71 t/s 14.06.709.427 I slot print_timing: id 2 | task 17227 | prompt eval time = 706.01 ms / 446 tokens ( 1.58 ms per token, 631.72 tokens per second) 14.06.709.435 I slot print_timing: id 2 | task 17227 | eval time = 19676.67 ms / 438 tokens ( 45.03 ms per token, 22.21 tokens per second) 14.06.709.436 I slot print_timing: id 2 | task 17227 | total time = 20382.69 ms / 884 tokens 14.06.709.437 I slot print_timing: id 2 | task 17227 | graphs reused = 16835 14.06.709.438 I slot print_timing: id 2 | task 17227 | graph reallocs = 0 / 0 (same size) / (changed size) 14.06.709.567 I slot release: id 2 | task 17227 | stop processing: n_tokens = 1579, truncated = 0 14.06.752.748 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.676 14.06.752.785 I slot launch_slot_: id 2 | task 17671 | processing task, is_child = 0 14.07.802.583 I slot print_timing: id 1 | task 17368 | n_gen = 309, tg = 22.42 t/s, tg_3s = 19.43 t/s 14.08.533.571 I slot print_timing: id 3 | task 17259 | n_gen = 436, tg = 22.17 t/s, tg_3s = 19.44 t/s 14.08.937.151 I slot print_timing: id 3 | task 17259 | prompt eval time = 689.28 ms / 444 tokens ( 1.55 ms per token, 644.15 tokens per second) 14.08.937.156 I slot print_timing: id 3 | task 17259 | eval time = 20023.83 ms / 446 tokens ( 45.00 ms per token, 22.22 tokens per second) 14.08.937.156 I slot print_timing: id 3 | task 17259 | total time = 20713.11 ms / 890 tokens 14.08.937.157 I slot print_timing: id 3 | task 17259 | graphs reused = 16870 14.08.937.158 I slot print_timing: id 3 | task 17259 | graph reallocs = 0 / 0 (same size) / (changed size) 14.08.937.251 I slot release: id 3 | task 17259 | stop processing: n_tokens = 1584, truncated = 0 14.08.971.879 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.931 (> 0.100 thold), f_keep = 0.674 14.08.971.919 I slot launch_slot_: id 3 | task 17711 | processing task, is_child = 0 14.09.596.848 I slot print_timing: id 0 | task 17414 | n_gen = 295, tg = 22.40 t/s, tg_3s = 14.75 t/s 14.10.839.020 I slot print_timing: id 1 | task 17368 | n_gen = 369, tg = 21.94 t/s, tg_3s = 19.76 t/s 14.12.092.437 I slot print_timing: id 2 | task 17671 | n_gen = 100, tg = 21.47 t/s, tg_3s = 21.68 t/s 14.12.616.557 I slot print_timing: id 0 | task 17414 | n_gen = 369, tg = 22.79 t/s, tg_3s = 24.51 t/s 14.13.671.562 I slot print_timing: id 3 | task 17711 | n_gen = 100, tg = 24.72 t/s, tg_3s = 24.97 t/s 14.13.873.016 I slot print_timing: id 1 | task 17368 | n_gen = 444, tg = 22.37 t/s, tg_3s = 24.72 t/s 14.15.131.152 I slot print_timing: id 2 | task 17671 | n_gen = 175, tg = 22.74 t/s, tg_3s = 24.68 t/s 14.15.656.366 I slot print_timing: id 0 | task 17414 | n_gen = 444, tg = 23.09 t/s, tg_3s = 24.67 t/s 14.16.673.037 I slot print_timing: id 3 | task 17711 | n_gen = 174, tg = 24.69 t/s, tg_3s = 24.65 t/s 14.16.875.223 I slot print_timing: id 1 | task 17368 | n_gen = 518, tg = 22.67 t/s, tg_3s = 24.65 t/s 14.18.135.367 I slot print_timing: id 2 | task 17671 | n_gen = 249, tg = 23.28 t/s, tg_3s = 24.63 t/s 14.18.663.046 I slot print_timing: id 0 | task 17414 | n_gen = 518, tg = 23.30 t/s, tg_3s = 24.61 t/s 14.19.684.918 I slot print_timing: id 3 | task 17711 | n_gen = 248, tg = 24.65 t/s, tg_3s = 24.57 t/s 14.19.890.012 I slot print_timing: id 1 | task 17368 | n_gen = 592, tg = 22.89 t/s, tg_3s = 24.55 t/s 14.21.152.131 I slot print_timing: id 2 | task 17671 | n_gen = 323, tg = 23.55 t/s, tg_3s = 24.53 t/s 14.21.681.437 I slot print_timing: id 0 | task 17414 | n_gen = 592, tg = 23.44 t/s, tg_3s = 24.52 t/s 14.22.699.552 I slot print_timing: id 3 | task 17711 | n_gen = 322, tg = 24.63 t/s, tg_3s = 24.55 t/s 14.22.901.748 I slot print_timing: id 1 | task 17368 | n_gen = 666, tg = 23.06 t/s, tg_3s = 24.57 t/s 14.23.555.198 I slot print_timing: id 3 | task 17711 | prompt eval time = 694.37 ms / 452 tokens ( 1.54 ms per token, 650.95 tokens per second) 14.23.555.206 I slot print_timing: id 3 | task 17711 | eval time = 13888.90 ms / 343 tokens ( 40.61 ms per token, 24.62 tokens per second) 14.23.555.207 I slot print_timing: id 3 | task 17711 | total time = 14583.27 ms / 795 tokens 14.23.555.207 I slot print_timing: id 3 | task 17711 | graphs reused = 17210 14.23.555.208 I slot print_timing: id 3 | task 17711 | graph reallocs = 0 / 0 (same size) / (changed size) 14.23.555.311 I slot release: id 3 | task 17711 | stop processing: n_tokens = 1489, truncated = 0 14.23.590.773 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.717 14.23.590.816 I slot launch_slot_: id 3 | task 18057 | processing task, is_child = 0 14.24.235.827 I slot print_timing: id 2 | task 17671 | n_gen = 384, tg = 22.86 t/s, tg_3s = 19.78 t/s 14.24.705.045 I slot print_timing: id 0 | task 17414 | n_gen = 651, tg = 23.02 t/s, tg_3s = 19.51 t/s 14.25.933.488 I slot print_timing: id 1 | task 17368 | n_gen = 725, tg = 22.72 t/s, tg_3s = 19.46 t/s 14.27.237.236 I slot print_timing: id 2 | task 17671 | n_gen = 457, tg = 23.08 t/s, tg_3s = 24.32 t/s 14.27.723.683 I slot print_timing: id 0 | task 17414 | n_gen = 725, tg = 23.17 t/s, tg_3s = 24.51 t/s 14.28.335.509 I slot print_timing: id 3 | task 18057 | n_gen = 100, tg = 24.56 t/s, tg_3s = 24.81 t/s 14.28.944.511 I slot print_timing: id 1 | task 17368 | n_gen = 799, tg = 22.88 t/s, tg_3s = 24.58 t/s 14.30.247.225 I slot print_timing: id 2 | task 17671 | n_gen = 531, tg = 23.28 t/s, tg_3s = 24.58 t/s 14.30.735.146 I slot print_timing: id 0 | task 17414 | n_gen = 799, tg = 23.29 t/s, tg_3s = 24.57 t/s 14.31.352.562 I slot print_timing: id 3 | task 18057 | n_gen = 174, tg = 24.55 t/s, tg_3s = 24.53 t/s 14.31.965.880 I slot print_timing: id 1 | task 17368 | n_gen = 873, tg = 23.01 t/s, tg_3s = 24.49 t/s 14.33.275.570 I slot print_timing: id 2 | task 17671 | n_gen = 605, tg = 23.42 t/s, tg_3s = 24.44 t/s 14.33.765.219 I slot print_timing: id 0 | task 17414 | n_gen = 873, tg = 23.38 t/s, tg_3s = 24.42 t/s 14.34.379.306 I slot print_timing: id 3 | task 18057 | n_gen = 248, tg = 24.52 t/s, tg_3s = 24.45 t/s 14.34.989.634 I slot print_timing: id 1 | task 17368 | n_gen = 947, tg = 23.12 t/s, tg_3s = 24.47 t/s 14.36.297.103 I slot print_timing: id 2 | task 17671 | n_gen = 679, tg = 23.53 t/s, tg_3s = 24.49 t/s 14.36.785.901 I slot print_timing: id 0 | task 17414 | n_gen = 947, tg = 23.47 t/s, tg_3s = 24.50 t/s 14.37.400.143 I slot print_timing: id 3 | task 18057 | n_gen = 322, tg = 24.51 t/s, tg_3s = 24.50 t/s 14.38.012.859 I slot print_timing: id 1 | task 17368 | n_gen = 1021, tg = 23.21 t/s, tg_3s = 24.48 t/s 14.38.135.776 I slot print_timing: id 1 | task 17368 | prompt eval time = 826.59 ms / 517 tokens ( 1.60 ms per token, 625.47 tokens per second) 14.38.135.783 I slot print_timing: id 1 | task 17368 | eval time = 44069.24 ms / 1024 tokens ( 43.08 ms per token, 23.21 tokens per second) 14.38.135.784 I slot print_timing: id 1 | task 17368 | total time = 44895.82 ms / 1541 tokens 14.38.135.785 I slot print_timing: id 1 | task 17368 | graphs reused = 17547 14.38.135.785 I slot print_timing: id 1 | task 17368 | graph reallocs = 0 / 0 (same size) / (changed size) 14.38.135.888 I slot release: id 1 | task 17368 | stop processing: n_tokens = 2227, truncated = 0 14.38.179.980 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.480 14.38.186.627 I slot launch_slot_: id 1 | task 18400 | processing task, is_child = 0 14.39.305.540 I slot print_timing: id 2 | task 17671 | n_gen = 737, tg = 23.13 t/s, tg_3s = 19.28 t/s 14.39.795.187 I slot print_timing: id 0 | task 17414 | n_gen = 1005, tg = 23.17 t/s, tg_3s = 19.27 t/s 14.40.409.532 I slot print_timing: id 3 | task 18057 | n_gen = 380, tg = 23.53 t/s, tg_3s = 19.27 t/s 14.40.571.224 I slot print_timing: id 0 | task 17414 | prompt eval time = 714.79 ms / 483 tokens ( 1.48 ms per token, 675.72 tokens per second) 14.40.571.231 I slot print_timing: id 0 | task 17414 | eval time = 44099.58 ms / 1024 tokens ( 43.11 ms per token, 23.20 tokens per second) 14.40.571.232 I slot print_timing: id 0 | task 17414 | total time = 44814.37 ms / 1507 tokens 14.40.571.232 I slot print_timing: id 0 | task 17414 | graphs reused = 17587 14.40.571.233 I slot print_timing: id 0 | task 17414 | graph reallocs = 0 / 0 (same size) / (changed size) 14.40.571.331 I slot release: id 0 | task 17414 | stop processing: n_tokens = 2181, truncated = 0 14.40.607.907 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.490 14.40.615.317 I slot launch_slot_: id 0 | task 18445 | processing task, is_child = 0 14.42.328.487 I slot print_timing: id 2 | task 17671 | n_gen = 796, tg = 22.81 t/s, tg_3s = 19.52 t/s 14.42.369.207 I slot print_timing: id 3 | task 18057 | prompt eval time = 714.27 ms / 465 tokens ( 1.54 ms per token, 651.02 tokens per second) 14.42.369.210 I slot print_timing: id 3 | task 18057 | eval time = 18064.12 ms / 413 tokens ( 43.84 ms per token, 22.81 tokens per second) 14.42.369.211 I slot print_timing: id 3 | task 18057 | total time = 18778.38 ms / 878 tokens 14.42.369.212 I slot print_timing: id 3 | task 18057 | graphs reused = 17613 14.42.369.213 I slot print_timing: id 3 | task 18057 | graph reallocs = 0 / 0 (same size) / (changed size) 14.42.369.310 I slot release: id 3 | task 18057 | stop processing: n_tokens = 1572, truncated = 0 14.42.404.496 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.944 (> 0.100 thold), f_keep = 0.679 14.42.404.529 I slot launch_slot_: id 3 | task 18475 | processing task, is_child = 0 14.44.140.432 I slot print_timing: id 1 | task 18400 | n_gen = 100, tg = 18.85 t/s, tg_3s = 19.04 t/s 14.45.358.913 I slot print_timing: id 2 | task 17671 | n_gen = 856, tg = 22.57 t/s, tg_3s = 19.80 t/s 14.45.928.424 I slot print_timing: id 0 | task 18445 | n_gen = 100, tg = 21.50 t/s, tg_3s = 21.72 t/s 14.47.112.446 I slot print_timing: id 3 | task 18475 | n_gen = 100, tg = 24.60 t/s, tg_3s = 24.85 t/s 14.47.151.891 I slot print_timing: id 1 | task 18400 | n_gen = 174, tg = 20.94 t/s, tg_3s = 24.57 t/s 14.48.372.150 I slot print_timing: id 2 | task 17671 | n_gen = 930, tg = 22.72 t/s, tg_3s = 24.56 t/s 14.48.616.339 I slot print_timing: id 2 | task 17671 | prompt eval time = 727.57 ms / 463 tokens ( 1.57 ms per token, 636.37 tokens per second) 14.48.616.343 I slot print_timing: id 2 | task 17671 | eval time = 41135.98 ms / 936 tokens ( 44.00 ms per token, 22.73 tokens per second) 14.48.616.344 I slot print_timing: id 2 | task 17671 | total time = 41863.54 ms / 1399 tokens 14.48.616.345 I slot print_timing: id 2 | task 17671 | graphs reused = 17747 14.48.616.346 I slot print_timing: id 2 | task 17671 | graph reallocs = 0 / 0 (same size) / (changed size) 14.48.616.447 I slot release: id 2 | task 17671 | stop processing: n_tokens = 2094, truncated = 0 14.48.659.531 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.891 (> 0.100 thold), f_keep = 0.510 14.48.659.566 I slot launch_slot_: id 2 | task 18615 | processing task, is_child = 0 14.49.347.545 I slot print_timing: id 0 | task 18445 | n_gen = 168, tg = 20.81 t/s, tg_3s = 19.89 t/s 14.50.118.915 I slot print_timing: id 3 | task 18475 | n_gen = 157, tg = 22.19 t/s, tg_3s = 18.96 t/s 14.50.158.053 I slot print_timing: id 1 | task 18400 | n_gen = 231, tg = 20.41 t/s, tg_3s = 18.96 t/s 14.52.348.976 I slot print_timing: id 0 | task 18445 | n_gen = 241, tg = 21.77 t/s, tg_3s = 24.32 t/s 14.53.122.543 I slot print_timing: id 3 | task 18475 | n_gen = 231, tg = 22.92 t/s, tg_3s = 24.64 t/s 14.53.161.951 I slot print_timing: id 1 | task 18400 | n_gen = 305, tg = 21.30 t/s, tg_3s = 24.63 t/s 14.53.445.756 I slot print_timing: id 2 | task 18615 | n_gen = 100, tg = 24.62 t/s, tg_3s = 24.87 t/s 14.55.386.140 I slot print_timing: id 0 | task 18445 | n_gen = 316, tg = 22.40 t/s, tg_3s = 24.69 t/s 14.55.508.063 I slot print_timing: id 1 | task 18400 | prompt eval time = 702.27 ms / 441 tokens ( 1.59 ms per token, 627.97 tokens per second) 14.55.508.071 I slot print_timing: id 1 | task 18400 | eval time = 16619.15 ms / 363 tokens ( 45.91 ms per token, 21.78 tokens per second) 14.55.508.072 I slot print_timing: id 1 | task 18400 | total time = 17321.42 ms / 804 tokens 14.55.508.073 I slot print_timing: id 1 | task 18400 | graphs reused = 17896 14.55.508.074 I slot print_timing: id 1 | task 18400 | graph reallocs = 0 / 0 (same size) / (changed size) 14.55.508.178 I slot release: id 1 | task 18400 | stop processing: n_tokens = 1491, truncated = 0 14.55.551.487 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.716 14.55.551.526 I slot launch_slot_: id 1 | task 18769 | processing task, is_child = 0 14.56.208.568 I slot print_timing: id 3 | task 18475 | n_gen = 292, tg = 22.18 t/s, tg_3s = 19.77 t/s 14.56.483.461 I slot print_timing: id 2 | task 18615 | n_gen = 159, tg = 22.38 t/s, tg_3s = 19.42 t/s 14.58.390.910 I slot print_timing: id 0 | task 18445 | n_gen = 374, tg = 21.86 t/s, tg_3s = 19.30 t/s 14.59.242.372 I slot print_timing: id 3 | task 18475 | n_gen = 366, tg = 22.60 t/s, tg_3s = 24.39 t/s 14.59.484.820 I slot print_timing: id 2 | task 18615 | n_gen = 233, tg = 23.06 t/s, tg_3s = 24.66 t/s 15.00.297.066 I slot print_timing: id 1 | task 18769 | n_gen = 100, tg = 24.67 t/s, tg_3s = 24.92 t/s 15.01.392.523 I slot print_timing: id 0 | task 18445 | n_gen = 448, tg = 22.27 t/s, tg_3s = 24.65 t/s 15.02.246.858 I slot print_timing: id 3 | task 18475 | n_gen = 440, tg = 22.91 t/s, tg_3s = 24.63 t/s 15.02.490.019 I slot print_timing: id 2 | task 18615 | n_gen = 307, tg = 23.42 t/s, tg_3s = 24.62 t/s 15.03.301.543 I slot print_timing: id 1 | task 18769 | n_gen = 174, tg = 24.65 t/s, tg_3s = 24.63 t/s 15.04.395.646 I slot print_timing: id 0 | task 18445 | n_gen = 522, tg = 22.58 t/s, tg_3s = 24.64 t/s 15.05.251.704 I slot print_timing: id 3 | task 18475 | n_gen = 514, tg = 23.15 t/s, tg_3s = 24.63 t/s 15.05.495.272 I slot print_timing: id 2 | task 18615 | n_gen = 381, tg = 23.64 t/s, tg_3s = 24.62 t/s 15.06.306.591 I slot print_timing: id 1 | task 18769 | n_gen = 248, tg = 24.65 t/s, tg_3s = 24.63 t/s 15.07.404.700 I slot print_timing: id 0 | task 18445 | n_gen = 596, tg = 22.81 t/s, tg_3s = 24.59 t/s 15.08.259.334 I slot print_timing: id 3 | task 18475 | n_gen = 588, tg = 23.32 t/s, tg_3s = 24.60 t/s 15.08.505.513 I slot print_timing: id 2 | task 18615 | n_gen = 455, tg = 23.79 t/s, tg_3s = 24.58 t/s 15.09.314.879 I slot print_timing: id 1 | task 18769 | n_gen = 322, tg = 24.63 t/s, tg_3s = 24.60 t/s 15.10.407.652 I slot print_timing: id 0 | task 18445 | n_gen = 670, tg = 23.00 t/s, tg_3s = 24.64 t/s 15.11.262.674 I slot print_timing: id 3 | task 18475 | n_gen = 662, tg = 23.46 t/s, tg_3s = 24.64 t/s 15.11.506.447 I slot print_timing: id 2 | task 18615 | n_gen = 529, tg = 23.91 t/s, tg_3s = 24.66 t/s 15.12.319.243 I slot print_timing: id 1 | task 18769 | n_gen = 396, tg = 24.63 t/s, tg_3s = 24.63 t/s 15.13.418.667 I slot print_timing: id 0 | task 18445 | n_gen = 744, tg = 23.15 t/s, tg_3s = 24.58 t/s 15.14.275.026 I slot print_timing: id 3 | task 18475 | n_gen = 736, tg = 23.57 t/s, tg_3s = 24.57 t/s 15.14.519.228 I slot print_timing: id 2 | task 18615 | n_gen = 603, tg = 23.99 t/s, tg_3s = 24.56 t/s 15.15.334.377 I slot print_timing: id 1 | task 18769 | n_gen = 470, tg = 24.62 t/s, tg_3s = 24.54 t/s 15.16.432.791 I slot print_timing: id 0 | task 18445 | n_gen = 818, tg = 23.27 t/s, tg_3s = 24.55 t/s 15.17.081.335 I slot print_timing: id 1 | task 18769 | prompt eval time = 732.76 ms / 472 tokens ( 1.55 ms per token, 644.14 tokens per second) 15.17.081.341 I slot print_timing: id 1 | task 18769 | eval time = 20797.03 ms / 513 tokens ( 40.62 ms per token, 24.62 tokens per second) 15.17.081.342 I slot print_timing: id 1 | task 18769 | total time = 21529.79 ms / 985 tokens 15.17.081.343 I slot print_timing: id 1 | task 18769 | graphs reused = 18405 15.17.081.344 I slot print_timing: id 1 | task 18769 | graph reallocs = 0 / 0 (same size) / (changed size) 15.17.081.455 I slot release: id 1 | task 18769 | stop processing: n_tokens = 1672, truncated = 0 15.17.125.455 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.639 15.17.125.499 I slot launch_slot_: id 1 | task 19285 | processing task, is_child = 0 15.17.779.196 I slot print_timing: id 2 | task 18615 | n_gen = 668, tg = 23.52 t/s, tg_3s = 19.94 t/s 15.17.779.488 I slot print_timing: id 3 | task 18475 | n_gen = 807, tg = 23.23 t/s, tg_3s = 20.26 t/s 15.17.975.874 I slot print_timing: id 2 | task 18615 | prompt eval time = 764.64 ms / 502 tokens ( 1.52 ms per token, 656.52 tokens per second) 15.17.975.880 I slot print_timing: id 2 | task 18615 | eval time = 28551.66 ms / 672 tokens ( 42.55 ms per token, 23.50 tokens per second) 15.17.975.881 I slot print_timing: id 2 | task 18615 | total time = 29316.30 ms / 1174 tokens 15.17.975.881 I slot print_timing: id 2 | task 18615 | graphs reused = 18407 15.17.975.882 I slot print_timing: id 2 | task 18615 | graph reallocs = 0 / 0 (same size) / (changed size) 15.17.975.956 I slot release: id 2 | task 18615 | stop processing: n_tokens = 1869, truncated = 0 15.18.018.631 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.571 15.18.018.658 I slot launch_slot_: id 2 | task 19292 | processing task, is_child = 0 15.19.328.912 I slot print_timing: id 3 | task 18475 | prompt eval time = 683.97 ms / 436 tokens ( 1.57 ms per token, 637.46 tokens per second) 15.19.328.917 I slot print_timing: id 3 | task 18475 | eval time = 36240.41 ms / 828 tokens ( 43.82 ms per token, 22.82 tokens per second) 15.19.328.918 I slot print_timing: id 3 | task 18475 | total time = 36924.37 ms / 1264 tokens 15.19.328.918 I slot print_timing: id 3 | task 18475 | graphs reused = 18420 15.19.328.919 I slot print_timing: id 3 | task 18475 | graph reallocs = 0 / 0 (same size) / (changed size) 15.19.329.018 I slot release: id 3 | task 18475 | stop processing: n_tokens = 1958, truncated = 0 15.19.364.134 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.942 (> 0.100 thold), f_keep = 0.545 15.19.364.188 I slot launch_slot_: id 3 | task 19310 | processing task, is_child = 0 15.19.980.202 I slot print_timing: id 0 | task 18445 | n_gen = 859, tg = 22.20 t/s, tg_3s = 11.56 t/s 15.23.020.289 I slot print_timing: id 0 | task 18445 | n_gen = 933, tg = 22.35 t/s, tg_3s = 24.34 t/s 15.23.142.537 I slot print_timing: id 1 | task 19285 | n_gen = 100, tg = 18.73 t/s, tg_3s = 18.91 t/s 15.23.386.089 I slot print_timing: id 2 | task 19292 | n_gen = 100, tg = 21.40 t/s, tg_3s = 21.61 t/s 15.24.077.441 I slot print_timing: id 3 | task 19310 | n_gen = 100, tg = 24.58 t/s, tg_3s = 24.83 t/s 15.26.025.796 I slot print_timing: id 0 | task 18445 | n_gen = 1007, tg = 22.50 t/s, tg_3s = 24.62 t/s 15.26.148.058 I slot print_timing: id 1 | task 19285 | n_gen = 174, tg = 20.86 t/s, tg_3s = 24.62 t/s 15.26.393.834 I slot print_timing: id 2 | task 19292 | n_gen = 174, tg = 22.66 t/s, tg_3s = 24.60 t/s 15.26.718.363 I slot print_timing: id 0 | task 18445 | prompt eval time = 708.76 ms / 475 tokens ( 1.49 ms per token, 670.18 tokens per second) 15.26.718.373 I slot print_timing: id 0 | task 18445 | eval time = 45394.27 ms / 1024 tokens ( 44.37 ms per token, 22.54 tokens per second) 15.26.718.375 I slot print_timing: id 0 | task 18445 | total time = 46103.04 ms / 1499 tokens 15.26.718.375 I slot print_timing: id 0 | task 18445 | graphs reused = 18582 15.26.718.376 I slot print_timing: id 0 | task 18445 | graph reallocs = 0 / 0 (same size) / (changed size) 15.26.718.480 I slot release: id 0 | task 18445 | stop processing: n_tokens = 2194, truncated = 0 15.26.755.049 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.487 15.26.760.797 I slot launch_slot_: id 0 | task 19478 | processing task, is_child = 0 15.27.399.326 I slot print_timing: id 3 | task 19310 | n_gen = 167, tg = 22.59 t/s, tg_3s = 20.17 t/s 15.29.153.031 I slot print_timing: id 1 | task 19285 | n_gen = 233, tg = 20.54 t/s, tg_3s = 19.63 t/s 15.29.395.361 I slot print_timing: id 2 | task 19292 | n_gen = 233, tg = 21.81 t/s, tg_3s = 19.66 t/s 15.30.405.737 I slot print_timing: id 3 | task 19310 | n_gen = 241, tg = 23.17 t/s, tg_3s = 24.61 t/s 15.31.452.905 I slot print_timing: id 0 | task 19478 | n_gen = 100, tg = 24.83 t/s, tg_3s = 25.08 t/s 15.32.182.512 I slot print_timing: id 1 | task 19285 | n_gen = 308, tg = 21.43 t/s, tg_3s = 24.76 t/s 15.32.426.091 I slot print_timing: id 2 | task 19292 | n_gen = 308, tg = 22.46 t/s, tg_3s = 24.75 t/s 15.33.439.223 I slot print_timing: id 3 | task 19310 | n_gen = 316, tg = 23.53 t/s, tg_3s = 24.72 t/s 15.34.492.910 I slot print_timing: id 0 | task 19478 | n_gen = 175, tg = 24.76 t/s, tg_3s = 24.67 t/s 15.35.187.650 I slot print_timing: id 1 | task 19285 | n_gen = 382, tg = 21.98 t/s, tg_3s = 24.62 t/s 15.35.431.755 I slot print_timing: id 2 | task 19292 | n_gen = 382, tg = 22.85 t/s, tg_3s = 24.62 t/s 15.36.448.822 I slot print_timing: id 3 | task 19310 | n_gen = 390, tg = 23.72 t/s, tg_3s = 24.59 t/s 15.37.496.481 I slot print_timing: id 0 | task 19478 | n_gen = 249, tg = 24.72 t/s, tg_3s = 24.64 t/s 15.38.225.260 I slot print_timing: id 1 | task 19285 | n_gen = 457, tg = 22.39 t/s, tg_3s = 24.69 t/s 15.38.226.282 I slot print_timing: id 3 | task 19310 | prompt eval time = 685.52 ms / 439 tokens ( 1.56 ms per token, 640.39 tokens per second) 15.38.226.285 I slot print_timing: id 3 | task 19310 | eval time = 18176.57 ms / 434 tokens ( 41.98 ms per token, 23.82 tokens per second) 15.38.226.286 I slot print_timing: id 3 | task 19310 | total time = 18862.09 ms / 873 tokens 15.38.226.287 I slot print_timing: id 3 | task 19310 | graphs reused = 18847 15.38.226.287 I slot print_timing: id 3 | task 19310 | graph reallocs = 0 / 0 (same size) / (changed size) 15.38.226.386 I slot release: id 3 | task 19310 | stop processing: n_tokens = 1567, truncated = 0 15.38.261.471 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.909 (> 0.100 thold), f_keep = 0.682 15.38.261.507 I slot launch_slot_: id 3 | task 19748 | processing task, is_child = 0 15.38.917.035 I slot print_timing: id 2 | task 19292 | n_gen = 453, tg = 22.42 t/s, tg_3s = 20.37 t/s 15.40.528.553 I slot print_timing: id 0 | task 19478 | n_gen = 308, tg = 23.50 t/s, tg_3s = 19.46 t/s 15.41.260.307 I slot print_timing: id 1 | task 19285 | n_gen = 516, tg = 22.00 t/s, tg_3s = 19.44 t/s 15.41.952.215 I slot print_timing: id 2 | task 19292 | n_gen = 527, tg = 22.68 t/s, tg_3s = 24.38 t/s 15.43.008.288 I slot print_timing: id 3 | task 19748 | n_gen = 100, tg = 24.61 t/s, tg_3s = 24.86 t/s 15.43.535.283 I slot print_timing: id 0 | task 19478 | n_gen = 382, tg = 23.71 t/s, tg_3s = 24.61 t/s 15.44.268.149 I slot print_timing: id 1 | task 19285 | n_gen = 590, tg = 22.30 t/s, tg_3s = 24.60 t/s 15.44.959.842 I slot print_timing: id 2 | task 19292 | n_gen = 601, tg = 22.90 t/s, tg_3s = 24.60 t/s 15.46.018.653 I slot print_timing: id 3 | task 19748 | n_gen = 174, tg = 24.60 t/s, tg_3s = 24.58 t/s 15.46.546.007 I slot print_timing: id 0 | task 19478 | n_gen = 456, tg = 23.85 t/s, tg_3s = 24.58 t/s 15.47.033.966 I slot print_timing: id 1 | task 19285 | prompt eval time = 730.18 ms / 464 tokens ( 1.57 ms per token, 635.46 tokens per second) 15.47.033.985 I slot print_timing: id 1 | task 19285 | eval time = 29178.28 ms / 658 tokens ( 44.41 ms per token, 22.52 tokens per second) 15.47.033.986 I slot print_timing: id 1 | task 19285 | total time = 29908.46 ms / 1122 tokens 15.47.033.988 I slot print_timing: id 1 | task 19285 | graphs reused = 19043 15.47.033.988 I slot print_timing: id 1 | task 19285 | graph reallocs = 0 / 0 (same size) / (changed size) 15.47.034.092 I slot release: id 1 | task 19285 | stop processing: n_tokens = 1809, truncated = 0 15.47.077.839 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.940 (> 0.100 thold), f_keep = 0.590 15.47.077.877 I slot launch_slot_: id 1 | task 19950 | processing task, is_child = 0 15.47.984.690 I slot print_timing: id 2 | task 19292 | n_gen = 660, tg = 22.55 t/s, tg_3s = 19.51 t/s 15.49.047.997 I slot print_timing: id 3 | task 19748 | n_gen = 233, tg = 23.06 t/s, tg_3s = 19.48 t/s 15.49.573.535 I slot print_timing: id 0 | task 19478 | n_gen = 515, tg = 23.25 t/s, tg_3s = 19.49 t/s 15.50.992.987 I slot print_timing: id 2 | task 19292 | n_gen = 734, tg = 22.74 t/s, tg_3s = 24.60 t/s 15.51.806.309 I slot print_timing: id 1 | task 19950 | n_gen = 100, tg = 24.62 t/s, tg_3s = 24.87 t/s 15.52.050.669 I slot print_timing: id 3 | task 19748 | n_gen = 307, tg = 23.42 t/s, tg_3s = 24.64 t/s 15.52.578.272 I slot print_timing: id 0 | task 19478 | n_gen = 589, tg = 23.41 t/s, tg_3s = 24.63 t/s 15.53.993.050 I slot print_timing: id 2 | task 19292 | n_gen = 808, tg = 22.90 t/s, tg_3s = 24.67 t/s 15.54.845.042 I slot print_timing: id 1 | task 19950 | n_gen = 175, tg = 24.65 t/s, tg_3s = 24.68 t/s 15.55.090.561 I slot print_timing: id 3 | task 19748 | n_gen = 382, tg = 23.66 t/s, tg_3s = 24.67 t/s 15.55.615.834 I slot print_timing: id 0 | task 19478 | n_gen = 664, tg = 23.55 t/s, tg_3s = 24.69 t/s 15.57.006.613 I slot print_timing: id 2 | task 19292 | n_gen = 882, tg = 23.03 t/s, tg_3s = 24.56 t/s 15.57.862.055 I slot print_timing: id 1 | task 19950 | n_gen = 249, tg = 24.61 t/s, tg_3s = 24.53 t/s 15.58.108.661 I slot print_timing: id 3 | task 19748 | n_gen = 456, tg = 23.79 t/s, tg_3s = 24.52 t/s 15.58.637.154 I slot print_timing: id 0 | task 19478 | n_gen = 738, tg = 23.64 t/s, tg_3s = 24.49 t/s 15.59.045.035 I slot print_timing: id 0 | task 19478 | prompt eval time = 704.79 ms / 469 tokens ( 1.50 ms per token, 665.45 tokens per second) 15.59.045.041 I slot print_timing: id 0 | task 19478 | eval time = 31579.44 ms / 748 tokens ( 42.28 ms per token, 23.65 tokens per second) 15.59.045.042 I slot print_timing: id 0 | task 19478 | total time = 32284.23 ms / 1217 tokens 15.59.045.043 I slot print_timing: id 0 | task 19478 | graphs reused = 19318 15.59.045.043 I slot print_timing: id 0 | task 19478 | graph reallocs = 0 / 0 (same size) / (changed size) 15.59.045.143 I slot release: id 0 | task 19478 | stop processing: n_tokens = 1912, truncated = 0 15.59.082.241 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.559 15.59.082.270 I slot launch_slot_: id 0 | task 20231 | processing task, is_child = 0 16.00.041.219 I slot print_timing: id 2 | task 19292 | n_gen = 942, tg = 22.79 t/s, tg_3s = 19.77 t/s 16.00.865.032 I slot print_timing: id 1 | task 19950 | n_gen = 308, tg = 23.47 t/s, tg_3s = 19.65 t/s 16.01.112.093 I slot print_timing: id 3 | task 19748 | n_gen = 515, tg = 23.23 t/s, tg_3s = 19.64 t/s 16.03.072.522 I slot print_timing: id 2 | task 19292 | n_gen = 1016, tg = 22.91 t/s, tg_3s = 24.41 t/s 16.03.398.901 I slot print_timing: id 2 | task 19292 | prompt eval time = 740.99 ms / 482 tokens ( 1.54 ms per token, 650.48 tokens per second) 16.03.398.909 I slot print_timing: id 2 | task 19292 | eval time = 44639.25 ms / 1024 tokens ( 43.64 ms per token, 22.92 tokens per second) 16.03.398.910 I slot print_timing: id 2 | task 19292 | total time = 45380.23 ms / 1506 tokens 16.03.398.911 I slot print_timing: id 2 | task 19292 | graphs reused = 19407 16.03.398.912 I slot print_timing: id 2 | task 19292 | graph reallocs = 0 / 0 (same size) / (changed size) 16.03.399.038 I slot release: id 2 | task 19292 | stop processing: n_tokens = 2201, truncated = 0 16.03.442.642 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.485 16.03.448.734 I slot launch_slot_: id 2 | task 20324 | processing task, is_child = 0 16.04.100.376 I slot print_timing: id 1 | task 19950 | n_gen = 372, tg = 22.74 t/s, tg_3s = 19.78 t/s 16.04.176.655 I slot print_timing: id 3 | task 19748 | n_gen = 574, tg = 22.75 t/s, tg_3s = 19.25 t/s 16.04.456.616 I slot print_timing: id 0 | task 20231 | n_gen = 100, tg = 21.08 t/s, tg_3s = 21.29 t/s 16.07.109.054 I slot print_timing: id 1 | task 19950 | n_gen = 445, tg = 22.98 t/s, tg_3s = 24.26 t/s 16.07.191.305 I slot print_timing: id 3 | task 19748 | n_gen = 648, tg = 22.94 t/s, tg_3s = 24.55 t/s 16.07.473.477 I slot print_timing: id 0 | task 20231 | n_gen = 174, tg = 22.43 t/s, tg_3s = 24.53 t/s 16.08.204.291 I slot print_timing: id 2 | task 20324 | n_gen = 100, tg = 24.58 t/s, tg_3s = 24.83 t/s 16.10.109.236 I slot print_timing: id 1 | task 19950 | n_gen = 519, tg = 23.20 t/s, tg_3s = 24.67 t/s 16.10.191.493 I slot print_timing: id 3 | task 19748 | n_gen = 722, tg = 23.10 t/s, tg_3s = 24.67 t/s 16.10.474.215 I slot print_timing: id 0 | task 20231 | n_gen = 248, tg = 23.05 t/s, tg_3s = 24.66 t/s 16.11.207.717 I slot print_timing: id 2 | task 20324 | n_gen = 174, tg = 24.60 t/s, tg_3s = 24.64 t/s 16.13.119.302 I slot print_timing: id 1 | task 19950 | n_gen = 593, tg = 23.37 t/s, tg_3s = 24.58 t/s 16.13.202.139 I slot print_timing: id 3 | task 19748 | n_gen = 796, tg = 23.23 t/s, tg_3s = 24.58 t/s 16.13.485.990 I slot print_timing: id 0 | task 20231 | n_gen = 322, tg = 23.39 t/s, tg_3s = 24.57 t/s 16.14.221.229 I slot print_timing: id 2 | task 20324 | n_gen = 248, tg = 24.59 t/s, tg_3s = 24.56 t/s 16.16.129.227 I slot print_timing: id 1 | task 19950 | n_gen = 667, tg = 23.50 t/s, tg_3s = 24.59 t/s 16.16.211.690 I slot print_timing: id 3 | task 19748 | n_gen = 870, tg = 23.34 t/s, tg_3s = 24.59 t/s 16.16.498.460 I slot print_timing: id 0 | task 20231 | n_gen = 396, tg = 23.60 t/s, tg_3s = 24.56 t/s 16.17.235.546 I slot print_timing: id 2 | task 20324 | n_gen = 322, tg = 24.58 t/s, tg_3s = 24.55 t/s 16.18.867.613 I slot print_timing: id 1 | task 19950 | prompt eval time = 707.31 ms / 448 tokens ( 1.58 ms per token, 633.38 tokens per second) 16.18.867.618 I slot print_timing: id 1 | task 19950 | eval time = 31082.41 ms / 734 tokens ( 42.40 ms per token, 23.58 tokens per second) 16.18.867.619 I slot print_timing: id 1 | task 19950 | total time = 31789.73 ms / 1182 tokens 16.18.867.620 I slot print_timing: id 1 | task 19950 | graphs reused = 19765 16.18.867.621 I slot print_timing: id 1 | task 19950 | graph reallocs = 0 / 0 (same size) / (changed size) 16.18.867.726 I slot release: id 1 | task 19950 | stop processing: n_tokens = 1869, truncated = 0 16.18.911.668 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.571 16.18.911.706 I slot launch_slot_: id 1 | task 20689 | processing task, is_child = 0 16.19.574.039 I slot print_timing: id 0 | task 20231 | n_gen = 456, tg = 22.96 t/s, tg_3s = 19.51 t/s 16.19.574.612 I slot print_timing: id 3 | task 19748 | n_gen = 937, tg = 23.06 t/s, tg_3s = 19.92 t/s 16.20.262.775 I slot print_timing: id 2 | task 20324 | n_gen = 380, tg = 23.56 t/s, tg_3s = 19.16 t/s 16.22.264.234 I slot print_timing: id 0 | task 20231 | prompt eval time = 677.28 ms / 443 tokens ( 1.53 ms per token, 654.09 tokens per second) 16.22.264.240 I slot print_timing: id 0 | task 20231 | eval time = 22504.68 ms / 521 tokens ( 43.28 ms per token, 23.11 tokens per second) 16.22.264.241 I slot print_timing: id 0 | task 20231 | total time = 23181.96 ms / 964 tokens 16.22.264.242 I slot print_timing: id 0 | task 20231 | graphs reused = 19828 16.22.264.243 I slot print_timing: id 0 | task 20231 | graph reallocs = 0 / 0 (same size) / (changed size) 16.22.264.336 I slot release: id 0 | task 20231 | stop processing: n_tokens = 1659, truncated = 0 16.22.301.443 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.644 16.22.301.483 I slot launch_slot_: id 0 | task 20757 | processing task, is_child = 0 16.22.915.698 I slot print_timing: id 3 | task 19748 | n_gen = 1004, tg = 22.83 t/s, tg_3s = 20.05 t/s 16.23.263.038 I slot print_timing: id 2 | task 20324 | n_gen = 439, tg = 22.95 t/s, tg_3s = 19.66 t/s 16.23.757.167 I slot print_timing: id 3 | task 19748 | prompt eval time = 723.97 ms / 480 tokens ( 1.51 ms per token, 663.01 tokens per second) 16.23.757.172 I slot print_timing: id 3 | task 19748 | eval time = 44771.68 ms / 1024 tokens ( 43.77 ms per token, 22.85 tokens per second) 16.23.757.173 I slot print_timing: id 3 | task 19748 | total time = 45495.65 ms / 1504 tokens 16.23.757.174 I slot print_timing: id 3 | task 19748 | graphs reused = 19847 16.23.757.174 I slot print_timing: id 3 | task 19748 | graph reallocs = 0 / 0 (same size) / (changed size) 16.23.757.300 I slot release: id 3 | task 19748 | stop processing: n_tokens = 2198, truncated = 0 16.23.792.489 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.486 16.23.798.280 I slot launch_slot_: id 3 | task 20780 | processing task, is_child = 0 16.24.922.014 I slot print_timing: id 1 | task 20689 | n_gen = 100, tg = 18.78 t/s, tg_3s = 18.97 t/s 16.26.302.685 I slot print_timing: id 2 | task 20324 | n_gen = 498, tg = 22.46 t/s, tg_3s = 19.41 t/s 16.27.635.357 I slot print_timing: id 0 | task 20757 | n_gen = 100, tg = 21.27 t/s, tg_3s = 21.49 t/s 16.27.958.151 I slot print_timing: id 1 | task 20689 | n_gen = 175, tg = 20.95 t/s, tg_3s = 24.70 t/s 16.28.525.282 I slot print_timing: id 3 | task 20780 | n_gen = 100, tg = 24.69 t/s, tg_3s = 24.94 t/s 16.29.333.083 I slot print_timing: id 2 | task 20324 | n_gen = 573, tg = 22.74 t/s, tg_3s = 24.75 t/s 16.30.667.165 I slot print_timing: id 0 | task 20757 | n_gen = 175, tg = 22.64 t/s, tg_3s = 24.74 t/s 16.30.992.032 I slot print_timing: id 1 | task 20689 | n_gen = 250, tg = 21.96 t/s, tg_3s = 24.72 t/s 16.31.561.485 I slot print_timing: id 3 | task 20780 | n_gen = 175, tg = 24.69 t/s, tg_3s = 24.70 t/s 16.32.337.928 I slot print_timing: id 2 | task 20324 | n_gen = 647, tg = 22.94 t/s, tg_3s = 24.63 t/s 16.33.675.909 I slot print_timing: id 0 | task 20757 | n_gen = 249, tg = 23.19 t/s, tg_3s = 24.59 t/s 16.34.000.336 I slot print_timing: id 1 | task 20689 | n_gen = 324, tg = 22.51 t/s, tg_3s = 24.60 t/s 16.34.569.316 I slot print_timing: id 3 | task 20780 | n_gen = 249, tg = 24.67 t/s, tg_3s = 24.60 t/s 16.35.342.678 I slot print_timing: id 2 | task 20324 | n_gen = 721, tg = 23.10 t/s, tg_3s = 24.63 t/s 16.36.683.203 I slot print_timing: id 0 | task 20757 | n_gen = 323, tg = 23.50 t/s, tg_3s = 24.61 t/s 16.37.007.645 I slot print_timing: id 1 | task 20689 | n_gen = 398, tg = 22.87 t/s, tg_3s = 24.61 t/s 16.37.574.894 I slot print_timing: id 3 | task 20780 | n_gen = 323, tg = 24.66 t/s, tg_3s = 24.62 t/s 16.38.383.159 I slot print_timing: id 2 | task 20324 | n_gen = 796, tg = 23.24 t/s, tg_3s = 24.67 t/s 16.39.720.421 I slot print_timing: id 0 | task 20757 | n_gen = 398, tg = 23.72 t/s, tg_3s = 24.69 t/s 16.40.046.960 I slot print_timing: id 1 | task 20689 | n_gen = 473, tg = 23.14 t/s, tg_3s = 24.68 t/s 16.40.576.756 I slot print_timing: id 3 | task 20780 | n_gen = 397, tg = 24.66 t/s, tg_3s = 24.65 t/s 16.41.388.846 I slot print_timing: id 2 | task 20324 | n_gen = 870, tg = 23.35 t/s, tg_3s = 24.62 t/s 16.42.739.084 I slot print_timing: id 0 | task 20757 | n_gen = 472, tg = 23.84 t/s, tg_3s = 24.51 t/s 16.43.065.284 I slot print_timing: id 1 | task 20689 | n_gen = 547, tg = 23.32 t/s, tg_3s = 24.52 t/s 16.43.595.607 I slot print_timing: id 3 | task 20780 | n_gen = 471, tg = 24.63 t/s, tg_3s = 24.51 t/s 16.44.409.366 I slot print_timing: id 2 | task 20324 | n_gen = 944, tg = 23.44 t/s, tg_3s = 24.50 t/s 16.45.182.015 I slot print_timing: id 0 | task 20757 | prompt eval time = 680.24 ms / 448 tokens ( 1.52 ms per token, 658.59 tokens per second) 16.45.182.022 I slot print_timing: id 0 | task 20757 | eval time = 22200.28 ms / 532 tokens ( 41.81 ms per token, 23.92 tokens per second) 16.45.182.024 I slot print_timing: id 0 | task 20757 | total time = 22880.52 ms / 980 tokens 16.45.182.025 I slot print_timing: id 0 | task 20757 | graphs reused = 20353 16.45.182.025 I slot print_timing: id 0 | task 20757 | graph reallocs = 0 / 0 (same size) / (changed size) 16.45.182.119 I slot release: id 0 | task 20757 | stop processing: n_tokens = 1675, truncated = 0 16.45.219.134 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.909 (> 0.100 thold), f_keep = 0.638 16.45.219.175 I slot launch_slot_: id 0 | task 21293 | processing task, is_child = 0 16.46.093.551 I slot print_timing: id 1 | task 20689 | n_gen = 606, tg = 22.88 t/s, tg_3s = 19.48 t/s 16.46.623.013 I slot print_timing: id 3 | task 20780 | n_gen = 530, tg = 23.93 t/s, tg_3s = 19.49 t/s 16.47.440.061 I slot print_timing: id 2 | task 20324 | n_gen = 1003, tg = 23.16 t/s, tg_3s = 19.47 t/s 16.48.299.315 I slot print_timing: id 2 | task 20324 | prompt eval time = 727.61 ms / 464 tokens ( 1.57 ms per token, 637.71 tokens per second) 16.48.299.323 I slot print_timing: id 2 | task 20324 | eval time = 44122.96 ms / 1024 tokens ( 43.13 ms per token, 23.19 tokens per second) 16.48.299.324 I slot print_timing: id 2 | task 20324 | total time = 44850.57 ms / 1488 tokens 16.48.299.325 I slot print_timing: id 2 | task 20324 | graphs reused = 20411 16.48.299.325 I slot print_timing: id 2 | task 20324 | graph reallocs = 0 / 0 (same size) / (changed size) 16.48.299.443 I slot release: id 2 | task 20324 | stop processing: n_tokens = 2183, truncated = 0 16.48.342.953 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.489 16.48.349.116 I slot launch_slot_: id 2 | task 21355 | processing task, is_child = 0 16.49.122.456 I slot print_timing: id 1 | task 20689 | n_gen = 664, tg = 22.50 t/s, tg_3s = 19.15 t/s 16.49.655.210 I slot print_timing: id 3 | task 20780 | n_gen = 588, tg = 23.35 t/s, tg_3s = 19.13 t/s 16.50.628.353 I slot print_timing: id 0 | task 21293 | n_gen = 100, tg = 21.09 t/s, tg_3s = 21.30 t/s 16.52.131.720 I slot print_timing: id 1 | task 20689 | n_gen = 738, tg = 22.69 t/s, tg_3s = 24.59 t/s 16.52.661.340 I slot print_timing: id 3 | task 20780 | n_gen = 662, tg = 23.48 t/s, tg_3s = 24.62 t/s 16.53.108.072 I slot print_timing: id 2 | task 21355 | n_gen = 100, tg = 24.59 t/s, tg_3s = 24.84 t/s 16.53.635.119 I slot print_timing: id 0 | task 21293 | n_gen = 174, tg = 22.46 t/s, tg_3s = 24.61 t/s 16.55.137.654 I slot print_timing: id 1 | task 20689 | n_gen = 812, tg = 22.85 t/s, tg_3s = 24.62 t/s 16.55.666.555 I slot print_timing: id 3 | task 20780 | n_gen = 736, tg = 23.59 t/s, tg_3s = 24.62 t/s 16.56.112.955 I slot print_timing: id 2 | task 21355 | n_gen = 174, tg = 24.60 t/s, tg_3s = 24.63 t/s 16.56.639.128 I slot print_timing: id 0 | task 21293 | n_gen = 248, tg = 23.07 t/s, tg_3s = 24.63 t/s 16.58.149.800 I slot print_timing: id 1 | task 20689 | n_gen = 886, tg = 22.99 t/s, tg_3s = 24.57 t/s 16.58.681.915 I slot print_timing: id 3 | task 20780 | n_gen = 810, tg = 23.68 t/s, tg_3s = 24.54 t/s 16.59.130.023 I slot print_timing: id 2 | task 21355 | n_gen = 248, tg = 24.58 t/s, tg_3s = 24.53 t/s 16.59.661.715 I slot print_timing: id 0 | task 21293 | n_gen = 322, tg = 23.38 t/s, tg_3s = 24.48 t/s 17.01.171.235 I slot print_timing: id 1 | task 20689 | n_gen = 960, tg = 23.10 t/s, tg_3s = 24.49 t/s 17.01.660.912 I slot print_timing: id 1 | task 20689 | prompt eval time = 739.63 ms / 481 tokens ( 1.54 ms per token, 650.32 tokens per second) 17.01.660.916 I slot print_timing: id 1 | task 20689 | eval time = 42009.56 ms / 972 tokens ( 43.26 ms per token, 23.11 tokens per second) 17.01.660.917 I slot print_timing: id 1 | task 20689 | total time = 42749.19 ms / 1453 tokens 17.01.660.918 I slot print_timing: id 1 | task 20689 | graphs reused = 20718 17.01.660.919 I slot print_timing: id 1 | task 20689 | graph reallocs = 0 / 0 (same size) / (changed size) 17.01.661.022 I slot release: id 1 | task 20689 | stop processing: n_tokens = 2140, truncated = 0 17.01.705.001 I slot print_timing: id 3 | task 20780 | n_gen = 884, tg = 23.74 t/s, tg_3s = 24.48 t/s 17.01.705.012 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.499 17.01.707.809 I slot launch_slot_: id 1 | task 21668 | processing task, is_child = 0 17.02.365.674 I slot print_timing: id 2 | task 21355 | n_gen = 312, tg = 23.41 t/s, tg_3s = 19.78 t/s 17.02.682.682 I slot print_timing: id 0 | task 21293 | n_gen = 380, tg = 22.63 t/s, tg_3s = 19.20 t/s 17.04.722.650 I slot print_timing: id 3 | task 20780 | n_gen = 942, tg = 23.40 t/s, tg_3s = 19.22 t/s 17.05.372.366 I slot print_timing: id 2 | task 21355 | n_gen = 385, tg = 23.57 t/s, tg_3s = 24.28 t/s 17.05.697.309 I slot print_timing: id 0 | task 21293 | n_gen = 454, tg = 22.92 t/s, tg_3s = 24.55 t/s 17.06.470.269 I slot print_timing: id 1 | task 21668 | n_gen = 100, tg = 24.58 t/s, tg_3s = 24.83 t/s 17.07.730.095 I slot print_timing: id 3 | task 20780 | n_gen = 1016, tg = 23.49 t/s, tg_3s = 24.61 t/s 17.08.055.395 I slot print_timing: id 3 | task 20780 | prompt eval time = 717.08 ms / 466 tokens ( 1.54 ms per token, 649.85 tokens per second) 17.08.055.404 I slot print_timing: id 3 | task 20780 | eval time = 43540.02 ms / 1024 tokens ( 42.56 ms per token, 23.50 tokens per second) 17.08.055.417 I slot print_timing: id 3 | task 20780 | total time = 44257.10 ms / 1490 tokens 17.08.055.423 I slot print_timing: id 3 | task 20780 | graphs reused = 20854 17.08.055.424 I slot print_timing: id 3 | task 20780 | graph reallocs = 0 / 0 (same size) / (changed size) 17.08.055.540 I slot release: id 3 | task 20780 | stop processing: n_tokens = 2184, truncated = 0 17.08.090.907 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.489 17.08.096.980 I slot launch_slot_: id 3 | task 21810 | processing task, is_child = 0 17.08.720.170 I slot print_timing: id 0 | task 21293 | n_gen = 514, tg = 22.51 t/s, tg_3s = 19.85 t/s 17.08.720.744 I slot print_timing: id 2 | task 21355 | n_gen = 453, tg = 23.02 t/s, tg_3s = 20.31 t/s 17.09.477.692 I slot print_timing: id 1 | task 21668 | n_gen = 159, tg = 22.46 t/s, tg_3s = 19.62 t/s 17.11.753.210 I slot print_timing: id 0 | task 21293 | n_gen = 588, tg = 22.73 t/s, tg_3s = 24.40 t/s 17.11.754.338 I slot print_timing: id 2 | task 21355 | n_gen = 527, tg = 23.20 t/s, tg_3s = 24.39 t/s 17.12.484.070 I slot print_timing: id 1 | task 21668 | n_gen = 233, tg = 23.10 t/s, tg_3s = 24.61 t/s 17.12.809.616 I slot print_timing: id 3 | task 21810 | n_gen = 100, tg = 24.63 t/s, tg_3s = 24.87 t/s 17.14.591.012 I slot print_timing: id 2 | task 21355 | prompt eval time = 732.57 ms / 471 tokens ( 1.56 ms per token, 642.94 tokens per second) 17.14.591.019 I slot print_timing: id 2 | task 21355 | eval time = 25509.31 ms / 597 tokens ( 42.80 ms per token, 23.36 tokens per second) 17.14.591.020 I slot print_timing: id 2 | task 21355 | total time = 26241.88 ms / 1068 tokens 17.14.591.021 I slot print_timing: id 2 | task 21355 | graphs reused = 20995 17.14.591.022 I slot print_timing: id 2 | task 21355 | graph reallocs = 0 / 0 (same size) / (changed size) 17.14.591.141 I slot release: id 2 | task 21355 | stop processing: n_tokens = 1763, truncated = 0 17.14.634.423 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.606 17.14.634.471 I slot launch_slot_: id 2 | task 21957 | processing task, is_child = 0 17.15.259.360 I slot print_timing: id 0 | task 21293 | n_gen = 660, tg = 22.47 t/s, tg_3s = 20.54 t/s 17.15.495.617 I slot print_timing: id 1 | task 21668 | n_gen = 292, tg = 22.29 t/s, tg_3s = 19.59 t/s 17.15.823.275 I slot print_timing: id 3 | task 21810 | n_gen = 159, tg = 22.46 t/s, tg_3s = 19.58 t/s 17.18.261.033 I slot print_timing: id 0 | task 21293 | n_gen = 733, tg = 22.64 t/s, tg_3s = 24.32 t/s 17.18.505.410 I slot print_timing: id 1 | task 21668 | n_gen = 366, tg = 22.72 t/s, tg_3s = 24.59 t/s 17.18.832.172 I slot print_timing: id 3 | task 21810 | n_gen = 233, tg = 23.10 t/s, tg_3s = 24.59 t/s 17.19.360.216 I slot print_timing: id 2 | task 21957 | n_gen = 100, tg = 24.60 t/s, tg_3s = 24.85 t/s 17.21.263.713 I slot print_timing: id 0 | task 21293 | n_gen = 807, tg = 22.81 t/s, tg_3s = 24.64 t/s 17.21.506.222 I slot print_timing: id 1 | task 21668 | n_gen = 440, tg = 23.03 t/s, tg_3s = 24.66 t/s 17.21.870.814 I slot print_timing: id 3 | task 21810 | n_gen = 308, tg = 23.47 t/s, tg_3s = 24.68 t/s 17.22.395.930 I slot print_timing: id 2 | task 21957 | n_gen = 175, tg = 24.65 t/s, tg_3s = 24.71 t/s 17.24.303.808 I slot print_timing: id 0 | task 21293 | n_gen = 882, tg = 22.96 t/s, tg_3s = 24.67 t/s 17.24.507.729 I slot print_timing: id 1 | task 21668 | n_gen = 514, tg = 23.25 t/s, tg_3s = 24.65 t/s 17.24.874.515 I slot print_timing: id 3 | task 21810 | n_gen = 382, tg = 23.69 t/s, tg_3s = 24.64 t/s 17.25.405.198 I slot print_timing: id 2 | task 21957 | n_gen = 249, tg = 24.63 t/s, tg_3s = 24.59 t/s 17.27.323.444 I slot print_timing: id 0 | task 21293 | n_gen = 956, tg = 23.07 t/s, tg_3s = 24.51 t/s 17.27.528.085 I slot print_timing: id 1 | task 21668 | n_gen = 588, tg = 23.40 t/s, tg_3s = 24.50 t/s 17.27.896.987 I slot print_timing: id 3 | task 21810 | n_gen = 456, tg = 23.81 t/s, tg_3s = 24.48 t/s 17.28.425.912 I slot print_timing: id 2 | task 21957 | n_gen = 323, tg = 24.60 t/s, tg_3s = 24.50 t/s 17.29.564.095 I slot print_timing: id 3 | task 21810 | prompt eval time = 692.49 ms / 449 tokens ( 1.54 ms per token, 648.38 tokens per second) 17.29.564.102 I slot print_timing: id 3 | task 21810 | eval time = 20774.61 ms / 497 tokens ( 41.88 ms per token, 23.88 tokens per second) 17.29.564.103 I slot print_timing: id 3 | task 21810 | total time = 21467.10 ms / 946 tokens 17.29.564.104 I slot print_timing: id 3 | task 21810 | graphs reused = 21343 17.29.564.105 I slot print_timing: id 3 | task 21810 | graph reallocs = 0 / 0 (same size) / (changed size) 17.29.564.216 I slot release: id 3 | task 21810 | stop processing: n_tokens = 1640, truncated = 0 17.29.599.682 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.896 (> 0.100 thold), f_keep = 0.651 17.29.599.722 I slot launch_slot_: id 3 | task 22311 | processing task, is_child = 0 17.30.348.994 I slot print_timing: id 0 | task 21293 | n_gen = 1014, tg = 22.81 t/s, tg_3s = 19.17 t/s 17.30.550.002 I slot print_timing: id 1 | task 21668 | n_gen = 646, tg = 22.95 t/s, tg_3s = 19.19 t/s 17.30.749.955 I slot print_timing: id 0 | task 21293 | prompt eval time = 713.97 ms / 479 tokens ( 1.49 ms per token, 670.89 tokens per second) 17.30.749.962 I slot print_timing: id 0 | task 21293 | eval time = 44816.80 ms / 1024 tokens ( 43.81 ms per token, 22.83 tokens per second) 17.30.749.963 I slot print_timing: id 0 | task 21293 | total time = 45530.77 ms / 1503 tokens 17.30.749.964 I slot print_timing: id 0 | task 21293 | graphs reused = 21352 17.30.749.965 I slot print_timing: id 0 | task 21293 | graph reallocs = 0 / 0 (same size) / (changed size) 17.30.750.060 I slot release: id 0 | task 21293 | stop processing: n_tokens = 2198, truncated = 0 17.30.788.886 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.945 (> 0.100 thold), f_keep = 0.486 17.30.796.039 I slot launch_slot_: id 0 | task 22325 | processing task, is_child = 0 17.31.467.962 I slot print_timing: id 2 | task 21957 | n_gen = 367, tg = 22.69 t/s, tg_3s = 14.46 t/s 17.33.572.341 I slot print_timing: id 1 | task 21668 | n_gen = 706, tg = 22.65 t/s, tg_3s = 19.85 t/s 17.34.500.150 I slot print_timing: id 2 | task 21957 | n_gen = 442, tg = 23.01 t/s, tg_3s = 24.73 t/s 17.34.945.924 I slot print_timing: id 3 | task 22311 | n_gen = 100, tg = 21.54 t/s, tg_3s = 21.76 t/s 17.35.470.988 I slot print_timing: id 0 | task 22325 | n_gen = 100, tg = 24.73 t/s, tg_3s = 24.98 t/s 17.36.611.684 I slot print_timing: id 1 | task 21668 | n_gen = 781, tg = 22.83 t/s, tg_3s = 24.68 t/s 17.37.506.289 I slot print_timing: id 2 | task 21957 | n_gen = 516, tg = 23.23 t/s, tg_3s = 24.62 t/s 17.37.952.173 I slot print_timing: id 3 | task 22311 | n_gen = 174, tg = 22.76 t/s, tg_3s = 24.62 t/s 17.38.476.243 I slot print_timing: id 0 | task 22325 | n_gen = 174, tg = 24.68 t/s, tg_3s = 24.62 t/s 17.39.651.125 I slot print_timing: id 1 | task 21668 | n_gen = 856, tg = 22.98 t/s, tg_3s = 24.68 t/s 17.40.542.778 I slot print_timing: id 2 | task 21957 | n_gen = 591, tg = 23.41 t/s, tg_3s = 24.70 t/s 17.40.989.356 I slot print_timing: id 3 | task 22311 | n_gen = 249, tg = 23.31 t/s, tg_3s = 24.69 t/s 17.41.275.371 I slot print_timing: id 1 | task 21668 | prompt eval time = 734.44 ms / 471 tokens ( 1.56 ms per token, 641.31 tokens per second) 17.41.275.375 I slot print_timing: id 1 | task 21668 | eval time = 38833.11 ms / 896 tokens ( 43.39 ms per token, 23.05 tokens per second) 17.41.275.376 I slot print_timing: id 1 | task 21668 | total time = 39567.55 ms / 1367 tokens 17.41.275.377 I slot print_timing: id 1 | task 21668 | graphs reused = 21593 17.41.275.378 I slot print_timing: id 1 | task 21668 | graph reallocs = 0 / 0 (same size) / (changed size) 17.41.275.490 I slot release: id 1 | task 21668 | stop processing: n_tokens = 2054, truncated = 0 17.41.319.143 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.520 17.41.319.181 I slot launch_slot_: id 1 | task 22571 | processing task, is_child = 0 17.41.966.251 I slot print_timing: id 0 | task 22325 | n_gen = 245, tg = 23.24 t/s, tg_3s = 20.34 t/s 17.43.576.513 I slot print_timing: id 2 | task 21957 | n_gen = 650, tg = 22.98 t/s, tg_3s = 19.45 t/s 17.44.025.118 I slot print_timing: id 3 | task 22311 | n_gen = 308, tg = 22.45 t/s, tg_3s = 19.43 t/s 17.44.996.920 I slot print_timing: id 0 | task 22325 | n_gen = 319, tg = 23.50 t/s, tg_3s = 24.42 t/s 17.45.241.926 I slot print_timing: id 2 | task 21957 | prompt eval time = 701.45 ms / 442 tokens ( 1.59 ms per token, 630.12 tokens per second) 17.45.241.932 I slot print_timing: id 2 | task 21957 | eval time = 29905.99 ms / 691 tokens ( 43.34 ms per token, 23.07 tokens per second) 17.45.241.933 I slot print_timing: id 2 | task 21957 | total time = 30607.44 ms / 1133 tokens 17.45.241.934 I slot print_timing: id 2 | task 21957 | graphs reused = 21670 17.45.241.935 I slot print_timing: id 2 | task 21957 | graph reallocs = 0 / 0 (same size) / (changed size) 17.45.242.042 I slot release: id 2 | task 21957 | stop processing: n_tokens = 1828, truncated = 0 17.45.285.187 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.584 17.45.285.220 I slot launch_slot_: id 2 | task 22654 | processing task, is_child = 0 17.46.673.409 I slot print_timing: id 1 | task 22571 | n_gen = 100, tg = 21.38 t/s, tg_3s = 21.59 t/s 17.47.039.953 I slot print_timing: id 3 | task 22311 | n_gen = 367, tg = 21.93 t/s, tg_3s = 19.57 t/s 17.48.013.468 I slot print_timing: id 0 | task 22325 | n_gen = 378, tg = 22.78 t/s, tg_3s = 19.56 t/s 17.49.675.294 I slot print_timing: id 1 | task 22571 | n_gen = 174, tg = 22.67 t/s, tg_3s = 24.65 t/s 17.50.000.153 I slot print_timing: id 2 | task 22654 | n_gen = 100, tg = 24.67 t/s, tg_3s = 24.92 t/s 17.50.041.160 I slot print_timing: id 3 | task 22311 | n_gen = 441, tg = 22.34 t/s, tg_3s = 24.66 t/s 17.51.053.278 I slot print_timing: id 0 | task 22325 | n_gen = 453, tg = 23.08 t/s, tg_3s = 24.67 t/s 17.52.679.498 I slot print_timing: id 1 | task 22571 | n_gen = 248, tg = 23.22 t/s, tg_3s = 24.63 t/s 17.53.005.726 I slot print_timing: id 2 | task 22654 | n_gen = 174, tg = 24.65 t/s, tg_3s = 24.62 t/s 17.53.046.911 I slot print_timing: id 3 | task 22311 | n_gen = 515, tg = 22.65 t/s, tg_3s = 24.62 t/s 17.54.061.689 I slot print_timing: id 0 | task 22325 | n_gen = 527, tg = 23.28 t/s, tg_3s = 24.60 t/s 17.55.691.967 I slot print_timing: id 1 | task 22571 | n_gen = 322, tg = 23.52 t/s, tg_3s = 24.56 t/s 17.56.018.194 I slot print_timing: id 2 | task 22654 | n_gen = 248, tg = 24.62 t/s, tg_3s = 24.56 t/s 17.56.059.439 I slot print_timing: id 3 | task 22311 | n_gen = 589, tg = 22.87 t/s, tg_3s = 24.56 t/s 17.56.913.826 I slot print_timing: id 0 | task 22325 | prompt eval time = 671.38 ms / 434 tokens ( 1.55 ms per token, 646.43 tokens per second) 17.56.913.834 I slot print_timing: id 0 | task 22325 | eval time = 25446.40 ms / 597 tokens ( 42.70 ms per token, 23.42 tokens per second) 17.56.913.835 I slot print_timing: id 0 | task 22325 | total time = 26117.77 ms / 1031 tokens 17.56.913.836 I slot print_timing: id 0 | task 22325 | graphs reused = 21936 17.56.913.837 I slot print_timing: id 0 | task 22325 | graph reallocs = 0 / 0 (same size) / (changed size) 17.56.913.935 I slot release: id 0 | task 22325 | stop processing: n_tokens = 1726, truncated = 0 17.56.950.856 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.619 17.56.950.892 I slot launch_slot_: id 0 | task 22927 | processing task, is_child = 0 17.58.703.703 I slot print_timing: id 1 | task 22571 | n_gen = 381, tg = 22.81 t/s, tg_3s = 19.59 t/s 17.59.029.097 I slot print_timing: id 2 | task 22654 | n_gen = 307, tg = 23.46 t/s, tg_3s = 19.60 t/s 17.59.070.118 I slot print_timing: id 3 | task 22311 | n_gen = 648, tg = 22.53 t/s, tg_3s = 19.60 t/s 18.01.661.050 I slot print_timing: id 0 | task 22927 | n_gen = 100, tg = 24.69 t/s, tg_3s = 24.94 t/s 18.01.742.513 I slot print_timing: id 1 | task 22571 | n_gen = 456, tg = 23.10 t/s, tg_3s = 24.68 t/s 18.02.026.169 I slot print_timing: id 2 | task 22654 | prompt eval time = 701.29 ms / 442 tokens ( 1.59 ms per token, 630.27 tokens per second) 18.02.026.176 I slot print_timing: id 2 | task 22654 | eval time = 16039.66 ms / 381 tokens ( 42.21 ms per token, 23.69 tokens per second) 18.02.026.177 I slot print_timing: id 2 | task 22654 | total time = 16740.94 ms / 823 tokens 18.02.026.178 I slot print_timing: id 2 | task 22654 | graphs reused = 22044 18.02.026.179 I slot print_timing: id 2 | task 22654 | graph reallocs = 0 / 0 (same size) / (changed size) 18.02.026.286 I slot release: id 2 | task 22654 | stop processing: n_tokens = 1518, truncated = 0 18.02.069.435 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.704 18.02.069.484 I slot launch_slot_: id 2 | task 23039 | processing task, is_child = 0 18.02.723.192 I slot print_timing: id 3 | task 22311 | n_gen = 723, tg = 22.30 t/s, tg_3s = 20.53 t/s 18.04.699.407 I slot print_timing: id 0 | task 22927 | n_gen = 159, tg = 22.42 t/s, tg_3s = 19.42 t/s 18.04.781.348 I slot print_timing: id 1 | task 22571 | n_gen = 515, tg = 22.60 t/s, tg_3s = 19.42 t/s 18.05.757.259 I slot print_timing: id 3 | task 22311 | n_gen = 797, tg = 22.48 t/s, tg_3s = 24.39 t/s 18.06.811.939 I slot print_timing: id 2 | task 23039 | n_gen = 100, tg = 24.67 t/s, tg_3s = 24.92 t/s 18.07.703.786 I slot print_timing: id 0 | task 22927 | n_gen = 233, tg = 23.08 t/s, tg_3s = 24.63 t/s 18.07.785.456 I slot print_timing: id 1 | task 22571 | n_gen = 589, tg = 22.84 t/s, tg_3s = 24.63 t/s 18.08.767.234 I slot print_timing: id 3 | task 22311 | n_gen = 871, tg = 22.65 t/s, tg_3s = 24.58 t/s 18.09.825.529 I slot print_timing: id 2 | task 23039 | n_gen = 174, tg = 24.62 t/s, tg_3s = 24.56 t/s 18.10.720.341 I slot print_timing: id 0 | task 22927 | n_gen = 307, tg = 23.41 t/s, tg_3s = 24.53 t/s 18.10.802.338 I slot print_timing: id 1 | task 22571 | n_gen = 663, tg = 23.02 t/s, tg_3s = 24.53 t/s 18.11.780.841 I slot print_timing: id 3 | task 22311 | n_gen = 945, tg = 22.78 t/s, tg_3s = 24.56 t/s 18.12.842.740 I slot print_timing: id 2 | task 23039 | n_gen = 248, tg = 24.59 t/s, tg_3s = 24.53 t/s 18.13.739.898 I slot print_timing: id 0 | task 22927 | n_gen = 381, tg = 23.62 t/s, tg_3s = 24.51 t/s 18.13.822.089 I slot print_timing: id 1 | task 22571 | n_gen = 737, tg = 23.16 t/s, tg_3s = 24.51 t/s 18.14.799.908 I slot print_timing: id 3 | task 22311 | n_gen = 1019, tg = 22.90 t/s, tg_3s = 24.51 t/s 18.15.003.428 I slot print_timing: id 3 | task 22311 | prompt eval time = 750.17 ms / 497 tokens ( 1.51 ms per token, 662.52 tokens per second) 18.15.003.436 I slot print_timing: id 3 | task 22311 | eval time = 44653.53 ms / 1024 tokens ( 43.65 ms per token, 22.91 tokens per second) 18.15.003.437 I slot print_timing: id 3 | task 22311 | total time = 45403.70 ms / 1521 tokens 18.15.003.438 I slot print_timing: id 3 | task 22311 | graphs reused = 22342 18.15.003.439 I slot print_timing: id 3 | task 22311 | graph reallocs = 0 / 0 (same size) / (changed size) 18.15.003.550 I slot release: id 3 | task 22311 | stop processing: n_tokens = 2215, truncated = 0 18.15.038.627 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.942 (> 0.100 thold), f_keep = 0.482 18.15.044.553 I slot launch_slot_: id 3 | task 23343 | processing task, is_child = 0 18.15.849.075 I slot print_timing: id 2 | task 23039 | n_gen = 307, tg = 23.45 t/s, tg_3s = 19.63 t/s 18.16.741.513 I slot print_timing: id 0 | task 22927 | n_gen = 440, tg = 23.00 t/s, tg_3s = 19.66 t/s 18.16.823.408 I slot print_timing: id 1 | task 22571 | n_gen = 796, tg = 22.86 t/s, tg_3s = 19.66 t/s 18.18.856.342 I slot print_timing: id 2 | task 23039 | n_gen = 381, tg = 23.67 t/s, tg_3s = 24.61 t/s 18.19.747.598 I slot print_timing: id 0 | task 22927 | n_gen = 514, tg = 23.22 t/s, tg_3s = 24.62 t/s 18.19.749.230 I slot print_timing: id 3 | task 23343 | n_gen = 100, tg = 24.63 t/s, tg_3s = 24.88 t/s 18.19.829.147 I slot print_timing: id 1 | task 22571 | n_gen = 870, tg = 23.00 t/s, tg_3s = 24.62 t/s 18.21.863.826 I slot print_timing: id 2 | task 23039 | n_gen = 455, tg = 23.81 t/s, tg_3s = 24.61 t/s 18.22.760.749 I slot print_timing: id 0 | task 22927 | n_gen = 588, tg = 23.38 t/s, tg_3s = 24.56 t/s 18.22.762.428 I slot print_timing: id 3 | task 23343 | n_gen = 174, tg = 24.60 t/s, tg_3s = 24.56 t/s 18.22.842.577 I slot print_timing: id 1 | task 22571 | n_gen = 944, tg = 23.11 t/s, tg_3s = 24.56 t/s 18.24.880.473 I slot print_timing: id 2 | task 23039 | n_gen = 529, tg = 23.91 t/s, tg_3s = 24.53 t/s 18.25.775.719 I slot print_timing: id 0 | task 22927 | n_gen = 662, tg = 23.50 t/s, tg_3s = 24.54 t/s 18.25.777.391 I slot print_timing: id 3 | task 23343 | n_gen = 248, tg = 24.58 t/s, tg_3s = 24.54 t/s 18.25.857.888 I slot print_timing: id 1 | task 22571 | n_gen = 1018, tg = 23.21 t/s, tg_3s = 24.54 t/s 18.26.102.684 I slot print_timing: id 1 | task 22571 | prompt eval time = 723.44 ms / 455 tokens ( 1.59 ms per token, 628.94 tokens per second) 18.26.102.691 I slot print_timing: id 1 | task 22571 | eval time = 44060.05 ms / 1024 tokens ( 43.07 ms per token, 23.22 tokens per second) 18.26.102.693 I slot print_timing: id 1 | task 22571 | total time = 44783.50 ms / 1479 tokens 18.26.102.694 I slot print_timing: id 1 | task 22571 | graphs reused = 22595 18.26.102.695 I slot print_timing: id 1 | task 22571 | graph reallocs = 0 / 0 (same size) / (changed size) 18.26.102.797 I slot release: id 1 | task 22571 | stop processing: n_tokens = 2166, truncated = 0 18.26.146.409 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.880 (> 0.100 thold), f_keep = 0.493 18.26.152.636 I slot launch_slot_: id 1 | task 23602 | processing task, is_child = 0 18.27.893.436 I slot print_timing: id 2 | task 23039 | n_gen = 584, tg = 23.23 t/s, tg_3s = 18.25 t/s 18.28.785.176 I slot print_timing: id 0 | task 22927 | n_gen = 717, tg = 23.00 t/s, tg_3s = 18.28 t/s 18.28.786.856 I slot print_timing: id 3 | task 23343 | n_gen = 303, tg = 23.13 t/s, tg_3s = 18.28 t/s 18.30.856.302 I slot print_timing: id 2 | task 23039 | prompt eval time = 729.55 ms / 469 tokens ( 1.56 ms per token, 642.86 tokens per second) 18.30.856.307 I slot print_timing: id 2 | task 23039 | eval time = 28057.25 ms / 657 tokens ( 42.77 ms per token, 23.38 tokens per second) 18.30.856.309 I slot print_timing: id 2 | task 23039 | total time = 28786.81 ms / 1126 tokens 18.30.856.309 I slot print_timing: id 2 | task 23039 | graphs reused = 22688 18.30.856.310 I slot print_timing: id 2 | task 23039 | graph reallocs = 0 / 0 (same size) / (changed size) 18.30.856.431 I slot release: id 2 | task 23039 | stop processing: n_tokens = 1821, truncated = 0 18.30.899.724 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.586 18.30.899.763 I slot launch_slot_: id 2 | task 23701 | processing task, is_child = 0 18.31.703.594 I slot print_timing: id 1 | task 23602 | n_gen = 100, tg = 21.22 t/s, tg_3s = 21.43 t/s 18.31.821.884 I slot print_timing: id 0 | task 22927 | n_gen = 776, tg = 22.68 t/s, tg_3s = 19.43 t/s 18.31.822.726 I slot print_timing: id 3 | task 23343 | n_gen = 362, tg = 22.43 t/s, tg_3s = 19.43 t/s 18.34.743.995 I slot print_timing: id 1 | task 23602 | n_gen = 175, tg = 22.58 t/s, tg_3s = 24.67 t/s 18.34.824.902 I slot print_timing: id 0 | task 22927 | n_gen = 850, tg = 22.84 t/s, tg_3s = 24.64 t/s 18.34.826.621 I slot print_timing: id 3 | task 23343 | n_gen = 436, tg = 22.78 t/s, tg_3s = 24.63 t/s 18.35.641.672 I slot print_timing: id 2 | task 23701 | n_gen = 100, tg = 24.64 t/s, tg_3s = 24.89 t/s 18.36.006.949 I slot print_timing: id 0 | task 22927 | prompt eval time = 700.75 ms / 461 tokens ( 1.52 ms per token, 657.87 tokens per second) 18.36.006.953 I slot print_timing: id 0 | task 22927 | eval time = 38355.30 ms / 879 tokens ( 43.68 ms per token, 22.89 tokens per second) 18.36.006.954 I slot print_timing: id 0 | task 22927 | total time = 39056.05 ms / 1340 tokens 18.36.006.955 I slot print_timing: id 0 | task 22927 | graphs reused = 22795 18.36.006.955 I slot print_timing: id 0 | task 22927 | graph reallocs = 0 / 0 (same size) / (changed size) 18.36.007.052 I slot release: id 0 | task 22927 | stop processing: n_tokens = 2035, truncated = 0 18.36.043.904 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.896 (> 0.100 thold), f_keep = 0.525 18.36.043.948 I slot launch_slot_: id 0 | task 23813 | processing task, is_child = 0 18.37.746.619 I slot print_timing: id 1 | task 23602 | n_gen = 233, tg = 21.66 t/s, tg_3s = 19.32 t/s 18.37.828.724 I slot print_timing: id 3 | task 23343 | n_gen = 494, tg = 22.31 t/s, tg_3s = 19.32 t/s 18.38.680.103 I slot print_timing: id 2 | task 23701 | n_gen = 159, tg = 22.39 t/s, tg_3s = 19.42 t/s 18.40.746.753 I slot print_timing: id 1 | task 23602 | n_gen = 307, tg = 22.32 t/s, tg_3s = 24.67 t/s 18.40.786.587 I slot print_timing: id 0 | task 23813 | n_gen = 100, tg = 24.70 t/s, tg_3s = 24.95 t/s 18.40.869.148 I slot print_timing: id 3 | task 23343 | n_gen = 569, tg = 22.59 t/s, tg_3s = 24.67 t/s 18.41.719.898 I slot print_timing: id 2 | task 23701 | n_gen = 234, tg = 23.08 t/s, tg_3s = 24.67 t/s 18.41.883.126 I slot print_timing: id 3 | task 23343 | prompt eval time = 685.04 ms / 439 tokens ( 1.56 ms per token, 640.84 tokens per second) 18.41.883.132 I slot print_timing: id 3 | task 23343 | eval time = 26153.51 ms / 594 tokens ( 44.10 ms per token, 22.67 tokens per second) 18.41.883.133 I slot print_timing: id 3 | task 23343 | total time = 26838.55 ms / 1033 tokens 18.41.883.134 I slot print_timing: id 3 | task 23343 | graphs reused = 22921 18.41.883.134 I slot print_timing: id 3 | task 23343 | graph reallocs = 0 / 0 (same size) / (changed size) 18.41.883.244 I slot release: id 3 | task 23343 | stop processing: n_tokens = 1727, truncated = 0 18.41.918.481 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.618 18.41.918.518 I slot launch_slot_: id 3 | task 23943 | processing task, is_child = 0 18.43.764.184 I slot print_timing: id 1 | task 23602 | n_gen = 366, tg = 21.82 t/s, tg_3s = 19.55 t/s 18.43.804.096 I slot print_timing: id 0 | task 23813 | n_gen = 159, tg = 22.49 t/s, tg_3s = 19.55 t/s 18.44.737.400 I slot print_timing: id 2 | task 23701 | n_gen = 293, tg = 22.27 t/s, tg_3s = 19.55 t/s 18.46.645.936 I slot print_timing: id 3 | task 23943 | n_gen = 100, tg = 24.64 t/s, tg_3s = 24.89 t/s 18.46.767.026 I slot print_timing: id 1 | task 23602 | n_gen = 440, tg = 22.25 t/s, tg_3s = 24.64 t/s 18.46.807.206 I slot print_timing: id 0 | task 23813 | n_gen = 233, tg = 23.13 t/s, tg_3s = 24.64 t/s 18.47.741.330 I slot print_timing: id 2 | task 23701 | n_gen = 367, tg = 22.71 t/s, tg_3s = 24.63 t/s 18.49.680.412 I slot print_timing: id 3 | task 23943 | n_gen = 175, tg = 24.67 t/s, tg_3s = 24.72 t/s 18.49.800.868 I slot print_timing: id 1 | task 23602 | n_gen = 515, tg = 22.58 t/s, tg_3s = 24.72 t/s 18.49.840.808 I slot print_timing: id 0 | task 23813 | n_gen = 308, tg = 23.50 t/s, tg_3s = 24.72 t/s 18.50.773.816 I slot print_timing: id 2 | task 23701 | n_gen = 442, tg = 23.03 t/s, tg_3s = 24.73 t/s 18.52.686.442 I slot print_timing: id 3 | task 23943 | n_gen = 249, tg = 24.66 t/s, tg_3s = 24.62 t/s 18.52.807.102 I slot print_timing: id 1 | task 23602 | n_gen = 589, tg = 22.82 t/s, tg_3s = 24.62 t/s 18.52.847.280 I slot print_timing: id 0 | task 23813 | n_gen = 382, tg = 23.71 t/s, tg_3s = 24.61 t/s 18.53.782.335 I slot print_timing: id 2 | task 23701 | n_gen = 516, tg = 23.24 t/s, tg_3s = 24.60 t/s 18.55.698.955 I slot print_timing: id 3 | task 23943 | n_gen = 323, tg = 24.64 t/s, tg_3s = 24.56 t/s 18.55.820.397 I slot print_timing: id 1 | task 23602 | n_gen = 663, tg = 23.00 t/s, tg_3s = 24.56 t/s 18.55.860.626 I slot print_timing: id 0 | task 23813 | n_gen = 456, tg = 23.84 t/s, tg_3s = 24.56 t/s 18.56.795.700 I slot print_timing: id 2 | task 23701 | n_gen = 590, tg = 23.40 t/s, tg_3s = 24.56 t/s 18.58.703.725 I slot print_timing: id 3 | task 23943 | n_gen = 397, tg = 24.63 t/s, tg_3s = 24.63 t/s 18.58.824.428 I slot print_timing: id 1 | task 23602 | n_gen = 737, tg = 23.15 t/s, tg_3s = 24.63 t/s 18.58.864.637 I slot print_timing: id 0 | task 23813 | n_gen = 530, tg = 23.95 t/s, tg_3s = 24.63 t/s 18.59.800.923 I slot print_timing: id 2 | task 23701 | n_gen = 664, tg = 23.53 t/s, tg_3s = 24.62 t/s 19.01.718.281 I slot print_timing: id 3 | task 23943 | n_gen = 471, tg = 24.62 t/s, tg_3s = 24.55 t/s 19.01.839.398 I slot print_timing: id 1 | task 23602 | n_gen = 811, tg = 23.27 t/s, tg_3s = 24.54 t/s 19.01.879.484 I slot print_timing: id 0 | task 23813 | n_gen = 604, tg = 24.02 t/s, tg_3s = 24.55 t/s 19.02.816.079 I slot print_timing: id 2 | task 23701 | n_gen = 738, tg = 23.63 t/s, tg_3s = 24.54 t/s 19.04.734.262 I slot print_timing: id 3 | task 23943 | n_gen = 545, tg = 24.61 t/s, tg_3s = 24.54 t/s 19.04.856.032 I slot print_timing: id 1 | task 23602 | n_gen = 885, tg = 23.37 t/s, tg_3s = 24.53 t/s 19.04.896.346 I slot print_timing: id 0 | task 23813 | n_gen = 678, tg = 24.08 t/s, tg_3s = 24.53 t/s 19.05.838.887 I slot print_timing: id 2 | task 23701 | n_gen = 812, tg = 23.70 t/s, tg_3s = 24.48 t/s 19.07.759.529 I slot print_timing: id 3 | task 23943 | n_gen = 619, tg = 24.59 t/s, tg_3s = 24.46 t/s 19.07.880.987 I slot print_timing: id 1 | task 23602 | n_gen = 959, tg = 23.46 t/s, tg_3s = 24.46 t/s 19.07.921.105 I slot print_timing: id 0 | task 23813 | n_gen = 752, tg = 24.11 t/s, tg_3s = 24.46 t/s 19.08.862.123 I slot print_timing: id 2 | task 23701 | n_gen = 886, tg = 23.77 t/s, tg_3s = 24.48 t/s 19.10.538.293 I slot print_timing: id 1 | task 23602 | prompt eval time = 885.02 ms / 526 tokens ( 1.68 ms per token, 594.34 tokens per second) 19.10.538.299 I slot print_timing: id 1 | task 23602 | eval time = 43500.63 ms / 1024 tokens ( 42.52 ms per token, 23.52 tokens per second) 19.10.538.301 I slot print_timing: id 1 | task 23602 | total time = 44385.64 ms / 1550 tokens 19.10.538.302 I slot print_timing: id 1 | task 23602 | graphs reused = 23604 19.10.538.303 I slot print_timing: id 1 | task 23602 | graph reallocs = 0 / 0 (same size) / (changed size) 19.10.538.408 I slot release: id 1 | task 23602 | stop processing: n_tokens = 2237, truncated = 0 19.10.582.228 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.904 (> 0.100 thold), f_keep = 0.477 19.10.588.657 I slot launch_slot_: id 1 | task 24633 | processing task, is_child = 0 19.11.254.079 I slot print_timing: id 0 | task 23813 | n_gen = 818, tg = 23.70 t/s, tg_3s = 19.80 t/s 19.11.254.653 I slot print_timing: id 3 | task 23943 | n_gen = 689, tg = 24.03 t/s, tg_3s = 20.03 t/s 19.11.902.095 I slot print_timing: id 2 | task 23701 | n_gen = 944, tg = 23.41 t/s, tg_3s = 19.08 t/s 19.14.269.721 I slot print_timing: id 0 | task 23813 | n_gen = 891, tg = 23.74 t/s, tg_3s = 24.21 t/s 19.14.271.339 I slot print_timing: id 3 | task 23943 | n_gen = 762, tg = 24.05 t/s, tg_3s = 24.20 t/s 19.14.915.682 I slot print_timing: id 2 | task 23701 | n_gen = 1018, tg = 23.49 t/s, tg_3s = 24.56 t/s 19.15.160.860 I slot print_timing: id 2 | task 23701 | prompt eval time = 723.82 ms / 455 tokens ( 1.59 ms per token, 628.61 tokens per second) 19.15.160.864 I slot print_timing: id 2 | task 23701 | eval time = 43537.27 ms / 1024 tokens ( 42.56 ms per token, 23.50 tokens per second) 19.15.160.865 I slot print_timing: id 2 | task 23701 | total time = 44261.09 ms / 1479 tokens 19.15.160.866 I slot print_timing: id 2 | task 23701 | graphs reused = 23697 19.15.160.867 I slot print_timing: id 2 | task 23701 | graph reallocs = 0 / 0 (same size) / (changed size) 19.15.160.979 I slot release: id 2 | task 23701 | stop processing: n_tokens = 2174, truncated = 0 19.15.204.610 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.491 19.15.210.933 I slot launch_slot_: id 2 | task 24731 | processing task, is_child = 0 19.16.014.681 I slot print_timing: id 1 | task 24633 | n_gen = 100, tg = 21.14 t/s, tg_3s = 21.35 t/s 19.17.272.564 I slot print_timing: id 0 | task 23813 | n_gen = 949, tg = 23.41 t/s, tg_3s = 19.32 t/s 19.17.274.265 I slot print_timing: id 3 | task 23943 | n_gen = 820, tg = 23.64 t/s, tg_3s = 19.31 t/s 19.18.492.585 I slot print_timing: id 0 | task 23813 | prompt eval time = 734.13 ms / 496 tokens ( 1.48 ms per token, 675.63 tokens per second) 19.18.492.590 I slot print_timing: id 0 | task 23813 | eval time = 41714.50 ms / 979 tokens ( 42.65 ms per token, 23.45 tokens per second) 19.18.492.591 I slot print_timing: id 0 | task 23813 | total time = 42448.63 ms / 1475 tokens 19.18.492.592 I slot print_timing: id 0 | task 23813 | graphs reused = 23759 19.18.492.592 I slot print_timing: id 0 | task 23813 | graph reallocs = 0 / 0 (same size) / (changed size) 19.18.492.698 I slot release: id 0 | task 23813 | stop processing: n_tokens = 2170, truncated = 0 19.18.529.163 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.492 19.18.534.772 I slot launch_slot_: id 0 | task 24798 | processing task, is_child = 0 19.19.179.777 I slot print_timing: id 1 | task 24633 | n_gen = 163, tg = 20.64 t/s, tg_3s = 19.90 t/s 19.20.304.712 I slot print_timing: id 3 | task 23943 | n_gen = 879, tg = 23.30 t/s, tg_3s = 19.47 t/s 19.20.586.908 I slot print_timing: id 2 | task 24731 | n_gen = 100, tg = 21.28 t/s, tg_3s = 21.49 t/s 19.22.211.105 I slot print_timing: id 1 | task 24633 | n_gen = 237, tg = 21.69 t/s, tg_3s = 24.41 t/s 19.23.267.695 I slot print_timing: id 0 | task 24798 | n_gen = 100, tg = 24.62 t/s, tg_3s = 24.87 t/s 19.23.309.920 I slot print_timing: id 3 | task 23943 | n_gen = 953, tg = 23.40 t/s, tg_3s = 24.62 t/s 19.23.593.960 I slot print_timing: id 2 | task 24731 | n_gen = 174, tg = 22.59 t/s, tg_3s = 24.61 t/s 19.25.216.597 I slot print_timing: id 1 | task 24633 | n_gen = 311, tg = 22.33 t/s, tg_3s = 24.62 t/s 19.26.030.213 I slot print_timing: id 3 | task 23943 | prompt eval time = 710.03 ms / 457 tokens ( 1.55 ms per token, 643.63 tokens per second) 19.26.030.221 I slot print_timing: id 3 | task 23943 | eval time = 43401.66 ms / 1020 tokens ( 42.59 ms per token, 23.48 tokens per second) 19.26.030.222 I slot print_timing: id 3 | task 23943 | total time = 44111.69 ms / 1477 tokens 19.26.030.223 I slot print_timing: id 3 | task 23943 | graphs reused = 23925 19.26.030.224 I slot print_timing: id 3 | task 23943 | graph reallocs = 0 / 0 (same size) / (changed size) 19.26.030.332 I slot release: id 3 | task 23943 | stop processing: n_tokens = 2171, truncated = 0 19.26.065.482 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.492 19.26.071.159 I slot launch_slot_: id 3 | task 24969 | processing task, is_child = 0 19.26.714.800 I slot print_timing: id 0 | task 24798 | n_gen = 170, tg = 22.63 t/s, tg_3s = 20.31 t/s 19.26.715.372 I slot print_timing: id 2 | task 24731 | n_gen = 236, tg = 21.80 t/s, tg_3s = 19.86 t/s 19.28.256.598 I slot print_timing: id 1 | task 24633 | n_gen = 370, tg = 21.80 t/s, tg_3s = 19.41 t/s 19.29.754.167 I slot print_timing: id 0 | task 24798 | n_gen = 244, tg = 23.13 t/s, tg_3s = 24.35 t/s 19.29.755.247 I slot print_timing: id 2 | task 24731 | n_gen = 310, tg = 22.36 t/s, tg_3s = 24.34 t/s 19.30.806.130 I slot print_timing: id 3 | task 24969 | n_gen = 100, tg = 24.62 t/s, tg_3s = 24.87 t/s 19.31.291.116 I slot print_timing: id 1 | task 24633 | n_gen = 445, tg = 22.24 t/s, tg_3s = 24.72 t/s 19.32.791.378 I slot print_timing: id 0 | task 24798 | n_gen = 319, tg = 23.48 t/s, tg_3s = 24.69 t/s 19.32.792.454 I slot print_timing: id 2 | task 24731 | n_gen = 385, tg = 22.78 t/s, tg_3s = 24.69 t/s 19.33.808.010 I slot print_timing: id 3 | task 24969 | n_gen = 174, tg = 24.63 t/s, tg_3s = 24.65 t/s 19.34.294.289 I slot print_timing: id 1 | task 24633 | n_gen = 519, tg = 22.56 t/s, tg_3s = 24.64 t/s 19.35.795.878 I slot print_timing: id 0 | task 24798 | n_gen = 393, tg = 23.69 t/s, tg_3s = 24.63 t/s 19.35.796.910 I slot print_timing: id 2 | task 24731 | n_gen = 459, tg = 23.06 t/s, tg_3s = 24.63 t/s 19.36.810.675 I slot print_timing: id 3 | task 24969 | n_gen = 248, tg = 24.64 t/s, tg_3s = 24.64 t/s 19.37.294.623 I slot print_timing: id 1 | task 24633 | n_gen = 593, tg = 22.80 t/s, tg_3s = 24.66 t/s 19.38.799.206 I slot print_timing: id 0 | task 24798 | n_gen = 467, tg = 23.83 t/s, tg_3s = 24.64 t/s 19.38.800.261 I slot print_timing: id 2 | task 24731 | n_gen = 533, tg = 23.27 t/s, tg_3s = 24.64 t/s 19.39.817.354 I slot print_timing: id 3 | task 24969 | n_gen = 322, tg = 24.63 t/s, tg_3s = 24.61 t/s 19.40.303.518 I slot print_timing: id 1 | task 24633 | n_gen = 667, tg = 22.99 t/s, tg_3s = 24.59 t/s 19.41.805.476 I slot print_timing: id 0 | task 24798 | n_gen = 541, tg = 23.94 t/s, tg_3s = 24.62 t/s 19.41.806.507 I slot print_timing: id 2 | task 24731 | n_gen = 607, tg = 23.42 t/s, tg_3s = 24.62 t/s 19.42.822.819 I slot print_timing: id 3 | task 24969 | n_gen = 396, tg = 24.63 t/s, tg_3s = 24.62 t/s 19.43.308.484 I slot print_timing: id 1 | task 24633 | n_gen = 741, tg = 23.14 t/s, tg_3s = 24.63 t/s 19.44.815.410 I slot print_timing: id 0 | task 24798 | n_gen = 615, tg = 24.01 t/s, tg_3s = 24.59 t/s 19.44.816.575 I slot print_timing: id 2 | task 24731 | n_gen = 681, tg = 23.54 t/s, tg_3s = 24.58 t/s 19.45.832.748 I slot print_timing: id 3 | task 24969 | n_gen = 470, tg = 24.62 t/s, tg_3s = 24.59 t/s 19.46.321.943 I slot print_timing: id 1 | task 24633 | n_gen = 815, tg = 23.26 t/s, tg_3s = 24.56 t/s 19.47.825.294 I slot print_timing: id 0 | task 24798 | n_gen = 689, tg = 24.07 t/s, tg_3s = 24.59 t/s 19.47.826.417 I slot print_timing: id 2 | task 24731 | n_gen = 755, tg = 23.64 t/s, tg_3s = 24.59 t/s 19.48.847.058 I slot print_timing: id 3 | task 24969 | n_gen = 544, tg = 24.61 t/s, tg_3s = 24.55 t/s 19.49.334.575 I slot print_timing: id 1 | task 24633 | n_gen = 889, tg = 23.37 t/s, tg_3s = 24.56 t/s 19.50.844.925 I slot print_timing: id 0 | task 24798 | n_gen = 763, tg = 24.12 t/s, tg_3s = 24.51 t/s 19.50.845.986 I slot print_timing: id 2 | task 24731 | n_gen = 829, tg = 23.72 t/s, tg_3s = 24.51 t/s 19.51.867.469 I slot print_timing: id 3 | task 24969 | n_gen = 618, tg = 24.60 t/s, tg_3s = 24.50 t/s 19.52.356.187 I slot print_timing: id 1 | task 24633 | n_gen = 963, tg = 23.45 t/s, tg_3s = 24.49 t/s 19.53.861.296 I slot print_timing: id 0 | task 24798 | n_gen = 837, tg = 24.15 t/s, tg_3s = 24.53 t/s 19.53.862.445 I slot print_timing: id 2 | task 24731 | n_gen = 903, tg = 23.78 t/s, tg_3s = 24.53 t/s 19.54.838.742 I slot print_timing: id 1 | task 24633 | prompt eval time = 742.18 ms / 484 tokens ( 1.53 ms per token, 652.14 tokens per second) 19.54.838.749 I slot print_timing: id 1 | task 24633 | eval time = 43507.90 ms / 1024 tokens ( 42.53 ms per token, 23.51 tokens per second) 19.54.838.750 I slot print_timing: id 1 | task 24633 | total time = 44250.07 ms / 1508 tokens 19.54.838.750 I slot print_timing: id 1 | task 24633 | graphs reused = 24611 19.54.838.751 I slot print_timing: id 1 | task 24633 | graph reallocs = 0 / 0 (same size) / (changed size) 19.54.838.881 I slot release: id 1 | task 24633 | stop processing: n_tokens = 2205, truncated = 0 19.54.882.936 I slot print_timing: id 3 | task 24969 | n_gen = 692, tg = 24.59 t/s, tg_3s = 24.54 t/s 19.54.882.951 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.484 19.54.889.625 I slot launch_slot_: id 1 | task 25663 | processing task, is_child = 0 19.56.653.344 I slot print_timing: id 0 | task 24798 | prompt eval time = 711.59 ms / 478 tokens ( 1.49 ms per token, 671.74 tokens per second) 19.56.653.350 I slot print_timing: id 0 | task 24798 | eval time = 37406.97 ms / 890 tokens ( 42.08 ms per token, 23.77 tokens per second) 19.56.653.351 I slot print_timing: id 0 | task 24798 | total time = 38118.56 ms / 1368 tokens 19.56.653.351 I slot print_timing: id 0 | task 24798 | graphs reused = 24636 19.56.653.352 I slot print_timing: id 0 | task 24798 | graph reallocs = 0 / 0 (same size) / (changed size) 19.56.653.452 I slot release: id 0 | task 24798 | stop processing: n_tokens = 2063, truncated = 0 19.56.690.513 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.518 19.56.690.548 I slot launch_slot_: id 0 | task 25693 | processing task, is_child = 0 19.57.323.833 I slot print_timing: id 2 | task 24731 | n_gen = 958, tg = 23.12 t/s, tg_3s = 15.89 t/s 19.57.910.884 I slot print_timing: id 3 | task 24969 | n_gen = 736, tg = 23.61 t/s, tg_3s = 14.53 t/s 20.00.038.403 I slot print_timing: id 2 | task 24731 | prompt eval time = 723.28 ms / 456 tokens ( 1.59 ms per token, 630.46 tokens per second) 20.00.038.408 I slot print_timing: id 2 | task 24731 | eval time = 44104.17 ms / 1024 tokens ( 43.11 ms per token, 23.20 tokens per second) 20.00.038.409 I slot print_timing: id 2 | task 24731 | total time = 44827.45 ms / 1480 tokens 20.00.038.410 I slot print_timing: id 2 | task 24731 | graphs reused = 24701 20.00.038.410 I slot print_timing: id 2 | task 24731 | graph reallocs = 0 / 0 (same size) / (changed size) 20.00.038.535 I slot release: id 2 | task 24731 | stop processing: n_tokens = 2175, truncated = 0 20.00.082.142 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.491 20.00.087.846 I slot launch_slot_: id 2 | task 25762 | processing task, is_child = 0 20.00.872.746 I slot print_timing: id 1 | task 25663 | n_gen = 100, tg = 18.74 t/s, tg_3s = 18.93 t/s 20.00.913.015 I slot print_timing: id 3 | task 24969 | n_gen = 794, tg = 23.24 t/s, tg_3s = 19.32 t/s 20.02.052.597 I slot print_timing: id 0 | task 25693 | n_gen = 100, tg = 21.23 t/s, tg_3s = 21.45 t/s 20.03.875.223 I slot print_timing: id 1 | task 25663 | n_gen = 174, tg = 20.88 t/s, tg_3s = 24.65 t/s 20.03.916.702 I slot print_timing: id 3 | task 24969 | n_gen = 868, tg = 23.35 t/s, tg_3s = 24.64 t/s 20.04.804.945 I slot print_timing: id 2 | task 25762 | n_gen = 100, tg = 24.67 t/s, tg_3s = 24.92 t/s 20.05.090.475 I slot print_timing: id 0 | task 25693 | n_gen = 175, tg = 22.60 t/s, tg_3s = 24.69 t/s 20.05.578.890 I slot print_timing: id 3 | task 24969 | prompt eval time = 713.36 ms / 464 tokens ( 1.54 ms per token, 650.45 tokens per second) 20.05.578.895 I slot print_timing: id 3 | task 24969 | eval time = 38794.36 ms / 909 tokens ( 42.73 ms per token, 23.41 tokens per second) 20.05.578.896 I slot print_timing: id 3 | task 24969 | total time = 39507.72 ms / 1373 tokens 20.05.578.897 I slot print_timing: id 3 | task 24969 | graphs reused = 24817 20.05.578.897 I slot print_timing: id 3 | task 24969 | graph reallocs = 0 / 0 (same size) / (changed size) 20.05.579.000 I slot release: id 3 | task 24969 | stop processing: n_tokens = 2067, truncated = 0 20.05.614.319 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.517 20.05.614.360 I slot launch_slot_: id 3 | task 25884 | processing task, is_child = 0 20.06.885.151 I slot print_timing: id 1 | task 25663 | n_gen = 233, tg = 20.54 t/s, tg_3s = 19.60 t/s 20.07.815.779 I slot print_timing: id 2 | task 25762 | n_gen = 159, tg = 22.50 t/s, tg_3s = 19.60 t/s 20.08.097.599 I slot print_timing: id 0 | task 25693 | n_gen = 234, tg = 21.76 t/s, tg_3s = 19.62 t/s 20.09.918.721 I slot print_timing: id 1 | task 25663 | n_gen = 308, tg = 21.43 t/s, tg_3s = 24.72 t/s 20.10.324.936 I slot print_timing: id 3 | task 25884 | n_gen = 100, tg = 24.73 t/s, tg_3s = 24.98 t/s 20.10.850.908 I slot print_timing: id 2 | task 25762 | n_gen = 234, tg = 23.16 t/s, tg_3s = 24.71 t/s 20.11.132.696 I slot print_timing: id 0 | task 25693 | n_gen = 309, tg = 22.41 t/s, tg_3s = 24.71 t/s 20.12.954.024 I slot print_timing: id 1 | task 25663 | n_gen = 383, tg = 22.00 t/s, tg_3s = 24.71 t/s 20.13.359.713 I slot print_timing: id 3 | task 25884 | n_gen = 175, tg = 24.73 t/s, tg_3s = 24.71 t/s 20.13.888.812 I slot print_timing: id 2 | task 25762 | n_gen = 309, tg = 23.52 t/s, tg_3s = 24.69 t/s 20.14.171.244 I slot print_timing: id 0 | task 25693 | n_gen = 384, tg = 22.82 t/s, tg_3s = 24.68 t/s 20.15.962.341 I slot print_timing: id 1 | task 25663 | n_gen = 457, tg = 22.38 t/s, tg_3s = 24.60 t/s 20.16.368.939 I slot print_timing: id 3 | task 25884 | n_gen = 249, tg = 24.69 t/s, tg_3s = 24.59 t/s 20.16.896.771 I slot print_timing: id 2 | task 25762 | n_gen = 383, tg = 23.72 t/s, tg_3s = 24.60 t/s 20.17.180.231 I slot print_timing: id 0 | task 25693 | n_gen = 458, tg = 23.09 t/s, tg_3s = 24.59 t/s 20.18.973.090 I slot print_timing: id 1 | task 25663 | n_gen = 531, tg = 22.67 t/s, tg_3s = 24.58 t/s 20.19.380.037 I slot print_timing: id 3 | task 25884 | n_gen = 323, tg = 24.66 t/s, tg_3s = 24.58 t/s 20.19.582.013 I slot print_timing: id 1 | task 25663 | prompt eval time = 701.67 ms / 441 tokens ( 1.59 ms per token, 628.50 tokens per second) 20.19.582.019 I slot print_timing: id 1 | task 25663 | eval time = 23990.69 ms / 546 tokens ( 44.02 ms per token, 22.72 tokens per second) 20.19.582.020 I slot print_timing: id 1 | task 25663 | total time = 24692.36 ms / 987 tokens 20.19.582.021 I slot print_timing: id 1 | task 25663 | graphs reused = 25142 20.19.582.022 I slot print_timing: id 1 | task 25663 | graph reallocs = 0 / 0 (same size) / (changed size) 20.19.582.144 I slot release: id 1 | task 25663 | stop processing: n_tokens = 1684, truncated = 0 20.19.625.975 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.882 (> 0.100 thold), f_keep = 0.634 20.19.626.013 I slot launch_slot_: id 1 | task 26215 | processing task, is_child = 0 20.20.323.973 I slot print_timing: id 0 | task 25693 | n_gen = 519, tg = 22.59 t/s, tg_3s = 19.40 t/s 20.20.324.280 I slot print_timing: id 2 | task 25762 | n_gen = 451, tg = 23.04 t/s, tg_3s = 19.84 t/s 20.21.709.383 I slot print_timing: id 2 | task 25762 | prompt eval time = 704.59 ms / 447 tokens ( 1.58 ms per token, 634.41 tokens per second) 20.21.709.388 I slot print_timing: id 2 | task 25762 | eval time = 20916.94 ms / 484 tokens ( 43.31 ms per token, 23.09 tokens per second) 20.21.709.390 I slot print_timing: id 2 | task 25762 | total time = 21621.52 ms / 931 tokens 20.21.709.391 I slot print_timing: id 2 | task 25762 | graphs reused = 25173 20.21.709.391 I slot print_timing: id 2 | task 25762 | graph reallocs = 0 / 0 (same size) / (changed size) 20.21.709.498 I slot release: id 2 | task 25762 | stop processing: n_tokens = 1626, truncated = 0 20.21.752.477 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.657 20.21.752.513 I slot launch_slot_: id 2 | task 26251 | processing task, is_child = 0 20.22.401.358 I slot print_timing: id 3 | task 25884 | n_gen = 365, tg = 22.64 t/s, tg_3s = 13.90 t/s 20.23.326.972 I slot print_timing: id 0 | task 25693 | n_gen = 576, tg = 22.17 t/s, tg_3s = 18.98 t/s 20.25.074.587 I slot print_timing: id 1 | task 26215 | n_gen = 100, tg = 21.18 t/s, tg_3s = 21.39 t/s 20.25.440.969 I slot print_timing: id 3 | task 25884 | n_gen = 439, tg = 22.91 t/s, tg_3s = 24.35 t/s 20.26.336.938 I slot print_timing: id 0 | task 25693 | n_gen = 650, tg = 22.42 t/s, tg_3s = 24.58 t/s 20.26.500.285 I slot print_timing: id 2 | task 26251 | n_gen = 100, tg = 24.61 t/s, tg_3s = 24.86 t/s 20.28.082.224 I slot print_timing: id 1 | task 26215 | n_gen = 174, tg = 22.52 t/s, tg_3s = 24.60 t/s 20.28.448.406 I slot print_timing: id 3 | task 25884 | n_gen = 513, tg = 23.14 t/s, tg_3s = 24.61 t/s 20.29.376.912 I slot print_timing: id 0 | task 25693 | n_gen = 725, tg = 22.63 t/s, tg_3s = 24.67 t/s 20.29.539.758 I slot print_timing: id 2 | task 26251 | n_gen = 175, tg = 24.64 t/s, tg_3s = 24.68 t/s 20.31.116.325 I slot print_timing: id 1 | task 26215 | n_gen = 249, tg = 23.14 t/s, tg_3s = 24.72 t/s 20.31.481.538 I slot print_timing: id 3 | task 25884 | n_gen = 588, tg = 23.33 t/s, tg_3s = 24.73 t/s 20.32.412.496 I slot print_timing: id 0 | task 25693 | n_gen = 800, tg = 22.81 t/s, tg_3s = 24.71 t/s 20.32.575.821 I slot print_timing: id 2 | task 26251 | n_gen = 250, tg = 24.66 t/s, tg_3s = 24.70 t/s 20.34.156.298 I slot print_timing: id 1 | task 26215 | n_gen = 324, tg = 23.48 t/s, tg_3s = 24.67 t/s 20.34.483.108 I slot print_timing: id 3 | task 25884 | n_gen = 662, tg = 23.47 t/s, tg_3s = 24.65 t/s 20.35.416.736 I slot print_timing: id 0 | task 25693 | n_gen = 874, tg = 22.96 t/s, tg_3s = 24.63 t/s 20.35.581.281 I slot print_timing: id 2 | task 26251 | n_gen = 324, tg = 24.65 t/s, tg_3s = 24.62 t/s 20.37.170.692 I slot print_timing: id 1 | task 26215 | n_gen = 398, tg = 23.67 t/s, tg_3s = 24.55 t/s 20.37.497.326 I slot print_timing: id 3 | task 25884 | n_gen = 736, tg = 23.58 t/s, tg_3s = 24.55 t/s 20.38.434.491 I slot print_timing: id 0 | task 25693 | n_gen = 948, tg = 23.07 t/s, tg_3s = 24.52 t/s 20.38.598.495 I slot print_timing: id 2 | task 26251 | n_gen = 398, tg = 24.63 t/s, tg_3s = 24.53 t/s 20.39.700.878 I slot print_timing: id 3 | task 25884 | prompt eval time = 708.01 ms / 455 tokens ( 1.56 ms per token, 642.64 tokens per second) 20.39.700.883 I slot print_timing: id 3 | task 25884 | eval time = 33378.49 ms / 790 tokens ( 42.30 ms per token, 23.64 tokens per second) 20.39.700.883 I slot print_timing: id 3 | task 25884 | total time = 34086.51 ms / 1245 tokens 20.39.700.884 I slot print_timing: id 3 | task 25884 | graphs reused = 25594 20.39.700.885 I slot print_timing: id 3 | task 25884 | graph reallocs = 0 / 0 (same size) / (changed size) 20.39.700.995 I slot release: id 3 | task 25884 | stop processing: n_tokens = 1939, truncated = 0 20.39.736.592 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.551 20.39.736.642 I slot launch_slot_: id 3 | task 26679 | processing task, is_child = 0 20.40.387.598 I slot print_timing: id 1 | task 26215 | n_gen = 462, tg = 23.06 t/s, tg_3s = 19.89 t/s 20.41.469.739 I slot print_timing: id 0 | task 25693 | n_gen = 1007, tg = 22.82 t/s, tg_3s = 19.44 t/s 20.41.635.022 I slot print_timing: id 2 | task 26251 | n_gen = 457, tg = 23.80 t/s, tg_3s = 19.43 t/s 20.42.165.214 I slot print_timing: id 0 | task 25693 | prompt eval time = 699.28 ms / 458 tokens ( 1.53 ms per token, 654.96 tokens per second) 20.42.165.220 I slot print_timing: id 0 | task 25693 | eval time = 44775.38 ms / 1024 tokens ( 43.77 ms per token, 22.85 tokens per second) 20.42.165.221 I slot print_timing: id 0 | task 25693 | total time = 45474.66 ms / 1482 tokens 20.42.165.222 I slot print_timing: id 0 | task 25693 | graphs reused = 25635 20.42.165.222 I slot print_timing: id 0 | task 25693 | graph reallocs = 0 / 0 (same size) / (changed size) 20.42.165.321 I slot release: id 0 | task 25693 | stop processing: n_tokens = 2177, truncated = 0 20.42.201.966 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.491 20.42.207.634 I slot launch_slot_: id 0 | task 26725 | processing task, is_child = 0 20.43.407.314 I slot print_timing: id 1 | task 26215 | n_gen = 521, tg = 22.60 t/s, tg_3s = 19.54 t/s 20.44.459.576 I slot print_timing: id 2 | task 26251 | prompt eval time = 724.71 ms / 459 tokens ( 1.58 ms per token, 633.36 tokens per second) 20.44.459.584 I slot print_timing: id 2 | task 26251 | eval time = 21982.34 ms / 512 tokens ( 43.02 ms per token, 23.25 tokens per second) 20.44.459.584 I slot print_timing: id 2 | task 26251 | total time = 22707.05 ms / 971 tokens 20.44.459.586 I slot print_timing: id 2 | task 26251 | graphs reused = 25674 20.44.459.586 I slot print_timing: id 2 | task 26251 | graph reallocs = 0 / 0 (same size) / (changed size) 20.44.459.707 I slot release: id 2 | task 26251 | stop processing: n_tokens = 1666, truncated = 0 20.44.502.673 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.641 20.44.502.712 I slot launch_slot_: id 2 | task 26768 | processing task, is_child = 0 20.45.749.299 I slot print_timing: id 3 | task 26679 | n_gen = 100, tg = 18.71 t/s, tg_3s = 18.90 t/s 20.46.434.175 I slot print_timing: id 1 | task 26215 | n_gen = 579, tg = 22.20 t/s, tg_3s = 19.16 t/s 20.47.569.724 I slot print_timing: id 0 | task 26725 | n_gen = 100, tg = 21.13 t/s, tg_3s = 21.35 t/s 20.48.786.494 I slot print_timing: id 3 | task 26679 | n_gen = 175, tg = 20.89 t/s, tg_3s = 24.69 t/s 20.49.271.474 I slot print_timing: id 2 | task 26768 | n_gen = 100, tg = 24.68 t/s, tg_3s = 24.93 t/s 20.49.473.363 I slot print_timing: id 1 | task 26215 | n_gen = 654, tg = 22.46 t/s, tg_3s = 24.68 t/s 20.50.605.934 I slot print_timing: id 0 | task 26725 | n_gen = 175, tg = 22.54 t/s, tg_3s = 24.70 t/s 20.51.825.826 I slot print_timing: id 3 | task 26679 | n_gen = 250, tg = 21.90 t/s, tg_3s = 24.68 t/s 20.52.271.705 I slot print_timing: id 2 | task 26768 | n_gen = 174, tg = 24.68 t/s, tg_3s = 24.66 t/s 20.52.473.823 I slot print_timing: id 1 | task 26215 | n_gen = 728, tg = 22.67 t/s, tg_3s = 24.66 t/s 20.53.609.776 I slot print_timing: id 0 | task 26725 | n_gen = 249, tg = 23.12 t/s, tg_3s = 24.64 t/s 20.53.650.271 I slot print_timing: id 0 | task 26725 | prompt eval time = 677.55 ms / 442 tokens ( 1.53 ms per token, 652.35 tokens per second) 20.53.650.277 I slot print_timing: id 0 | task 26725 | eval time = 10765.07 ms / 250 tokens ( 43.23 ms per token, 23.13 tokens per second) 20.53.650.278 I slot print_timing: id 0 | task 26725 | total time = 11442.63 ms / 692 tokens 20.53.650.279 I slot print_timing: id 0 | task 26725 | graphs reused = 25879 20.53.650.280 I slot print_timing: id 0 | task 26725 | graph reallocs = 0 / 0 (same size) / (changed size) 20.53.650.379 I slot release: id 0 | task 26725 | stop processing: n_tokens = 1387, truncated = 0 20.53.687.197 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.771 20.53.687.238 I slot launch_slot_: id 0 | task 26979 | processing task, is_child = 0 20.54.851.401 I slot print_timing: id 3 | task 26679 | n_gen = 310, tg = 21.47 t/s, tg_3s = 19.83 t/s 20.55.299.340 I slot print_timing: id 2 | task 26768 | n_gen = 234, tg = 23.21 t/s, tg_3s = 19.82 t/s 20.55.502.204 I slot print_timing: id 1 | task 26215 | n_gen = 788, tg = 22.42 t/s, tg_3s = 19.81 t/s 20.57.863.354 I slot print_timing: id 3 | task 26679 | n_gen = 384, tg = 22.00 t/s, tg_3s = 24.57 t/s 20.58.309.947 I slot print_timing: id 2 | task 26768 | n_gen = 308, tg = 23.53 t/s, tg_3s = 24.58 t/s 20.58.390.405 I slot print_timing: id 0 | task 26979 | n_gen = 100, tg = 24.59 t/s, tg_3s = 24.84 t/s 20.58.513.330 I slot print_timing: id 1 | task 26215 | n_gen = 862, tg = 22.59 t/s, tg_3s = 24.58 t/s 21.00.884.920 I slot print_timing: id 3 | task 26679 | n_gen = 458, tg = 22.37 t/s, tg_3s = 24.49 t/s 21.01.332.941 I slot print_timing: id 2 | task 26768 | n_gen = 382, tg = 23.71 t/s, tg_3s = 24.48 t/s 21.01.413.765 I slot print_timing: id 0 | task 26979 | n_gen = 174, tg = 24.54 t/s, tg_3s = 24.48 t/s 21.01.537.247 I slot print_timing: id 1 | task 26215 | n_gen = 936, tg = 22.73 t/s, tg_3s = 24.47 t/s 21.03.907.829 I slot print_timing: id 3 | task 26679 | n_gen = 532, tg = 22.64 t/s, tg_3s = 24.48 t/s 21.04.355.636 I slot print_timing: id 2 | task 26768 | n_gen = 456, tg = 23.83 t/s, tg_3s = 24.48 t/s 21.04.356.106 I slot print_timing: id 3 | task 26679 | prompt eval time = 720.26 ms / 473 tokens ( 1.52 ms per token, 656.71 tokens per second) 21.04.356.109 I slot print_timing: id 3 | task 26679 | eval time = 23899.19 ms / 543 tokens ( 44.09 ms per token, 22.68 tokens per second) 21.04.356.111 I slot print_timing: id 3 | task 26679 | total time = 24619.44 ms / 1016 tokens 21.04.356.112 I slot print_timing: id 3 | task 26679 | graphs reused = 26123 21.04.356.113 I slot print_timing: id 3 | task 26679 | graph reallocs = 0 / 0 (same size) / (changed size) 21.04.356.220 I slot release: id 3 | task 26679 | stop processing: n_tokens = 1710, truncated = 0 21.04.423.478 I slot print_timing: id 0 | task 26979 | n_gen = 248, tg = 24.55 t/s, tg_3s = 24.59 t/s 21.04.554.256 I slot print_timing: id 1 | task 26215 | n_gen = 1011, tg = 22.87 t/s, tg_3s = 24.86 t/s 21.04.978.317 I slot print_timing: id 1 | task 26215 | prompt eval time = 774.42 ms / 513 tokens ( 1.51 ms per token, 662.43 tokens per second) 21.04.978.321 I slot print_timing: id 1 | task 26215 | eval time = 44577.87 ms / 1024 tokens ( 43.58 ms per token, 22.95 tokens per second) 21.04.978.321 I slot print_timing: id 1 | task 26215 | total time = 45352.29 ms / 1537 tokens 21.04.978.322 I slot print_timing: id 1 | task 26215 | graphs reused = 26141 21.04.978.323 I slot print_timing: id 1 | task 26215 | graph reallocs = 0 / 0 (same size) / (changed size) 21.04.978.423 I slot release: id 1 | task 26215 | stop processing: n_tokens = 2234, truncated = 0 21.07.381.366 I slot print_timing: id 2 | task 26768 | n_gen = 544, tg = 24.55 t/s, tg_3s = 29.08 t/s 21.07.415.426 I slot print_timing: id 2 | task 26768 | prompt eval time = 757.85 ms / 491 tokens ( 1.54 ms per token, 647.89 tokens per second) 21.07.415.435 I slot print_timing: id 2 | task 26768 | eval time = 22154.86 ms / 545 tokens ( 40.73 ms per token, 24.55 tokens per second) 21.07.415.437 I slot print_timing: id 2 | task 26768 | total time = 22912.70 ms / 1036 tokens 21.07.415.438 I slot print_timing: id 2 | task 26768 | graphs reused = 26141 21.07.415.439 I slot print_timing: id 2 | task 26768 | graph reallocs = 0 / 0 (same size) / (changed size) 21.07.415.589 I slot release: id 2 | task 26768 | stop processing: n_tokens = 1731, truncated = 0 21.07.434.257 I slot print_timing: id 0 | task 26979 | n_gen = 336, tg = 25.63 t/s, tg_3s = 29.23 t/s 21.10.433.399 I slot print_timing: id 0 | task 26979 | prompt eval time = 676.92 ms / 443 tokens ( 1.53 ms per token, 654.44 tokens per second) 21.10.433.402 I slot print_timing: id 0 | task 26979 | eval time = 16069.24 ms / 536 tokens ( 30.04 ms per token, 33.29 tokens per second) 21.10.433.403 I slot print_timing: id 0 | task 26979 | total time = 16746.15 ms / 979 tokens 21.10.433.403 I slot print_timing: id 0 | task 26979 | graphs reused = 26340 21.10.433.404 I slot print_timing: id 0 | task 26979 | graph reallocs = 0 / 0 (same size) / (changed size) 21.10.433.476 I slot release: id 0 | task 26979 | stop processing: n_tokens = 1674, truncated = 0 21.10.449.286 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1710, t_last = 338971253328 21.10.452.765 I slot launch_slot_: id 3 | task 27517 | processing task, is_child = 0 21.10.463.107 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 2234, t_last = 338971875528 21.10.463.257 I slot launch_slot_: id 1 | task 27518 | processing task, is_child = 0 21.10.463.442 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1731, t_last = 338974312698 21.10.463.562 I slot launch_slot_: id 2 | task 27519 | processing task, is_child = 0 21.10.463.666 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1674, t_last = 338977330581 21.10.463.780 I slot launch_slot_: id 0 | task 27520 | processing task, is_child = 0 21.14.262.177 I slot print_timing: id 0 | task 27520 | prompt processing, n_tokens = 940, progress = 1.00, t = 3.80 s / 247.47 tokens per second 21.14.910.257 I slot print_timing: id 1 | task 27518 | prompt processing, n_tokens = 942, progress = 1.00, t = 3.80 s / 248.01 tokens per second 21.14.910.411 I slot print_timing: id 2 | task 27519 | prompt processing, n_tokens = 760, progress = 0.99, t = 3.80 s / 200.10 tokens per second 21.14.910.537 I slot print_timing: id 3 | task 27517 | prompt processing, n_tokens = 754, progress = 0.99, t = 3.80 s / 198.53 tokens per second 21.15.056.032 I slot print_timing: id 0 | task 27520 | prompt eval time = 4551.59 ms / 944 tokens ( 4.82 ms per token, 207.40 tokens per second) 21.15.056.034 I slot print_timing: id 0 | task 27520 | eval time = 40.66 ms / 2 tokens ( 40.66 ms per token, 24.60 tokens per second) 21.15.056.034 I slot print_timing: id 0 | task 27520 | total time = 4592.24 ms / 946 tokens 21.15.056.035 I slot print_timing: id 0 | task 27520 | graphs reused = 26342 21.15.056.035 I slot print_timing: id 0 | task 27520 | graph reallocs = 0 / 0 (same size) / (changed size) 21.15.056.085 I slot release: id 0 | task 27520 | stop processing: n_tokens = 945, truncated = 0 21.15.056.351 I slot print_timing: id 1 | task 27518 | prompt eval time = 4551.73 ms / 946 tokens ( 4.81 ms per token, 207.83 tokens per second) 21.15.056.353 I slot print_timing: id 1 | task 27518 | eval time = 40.69 ms / 2 tokens ( 40.69 ms per token, 24.57 tokens per second) 21.15.056.354 I slot print_timing: id 1 | task 27518 | total time = 4592.42 ms / 948 tokens 21.15.056.354 I slot print_timing: id 1 | task 27518 | graphs reused = 26342 21.15.056.354 I slot print_timing: id 1 | task 27518 | graph reallocs = 0 / 0 (same size) / (changed size) 21.15.056.415 I slot release: id 1 | task 27518 | stop processing: n_tokens = 947, truncated = 0 21.15.056.702 I slot print_timing: id 2 | task 27519 | prompt eval time = 4551.89 ms / 764 tokens ( 5.96 ms per token, 167.84 tokens per second) 21.15.056.704 I slot print_timing: id 2 | task 27519 | eval time = 40.72 ms / 2 tokens ( 40.72 ms per token, 24.56 tokens per second) 21.15.056.704 I slot print_timing: id 2 | task 27519 | total time = 4592.61 ms / 766 tokens 21.15.056.705 I slot print_timing: id 2 | task 27519 | graphs reused = 26342 21.15.056.705 I slot print_timing: id 2 | task 27519 | graph reallocs = 0 / 0 (same size) / (changed size) 21.15.056.738 I slot release: id 2 | task 27519 | stop processing: n_tokens = 765, truncated = 0 21.15.057.042 I slot print_timing: id 3 | task 27517 | prompt eval time = 4552.09 ms / 758 tokens ( 6.01 ms per token, 166.52 tokens per second) 21.15.057.043 I slot print_timing: id 3 | task 27517 | eval time = 40.74 ms / 2 tokens ( 40.74 ms per token, 24.55 tokens per second) 21.15.057.044 I slot print_timing: id 3 | task 27517 | total time = 4592.83 ms / 760 tokens 21.15.057.044 I slot print_timing: id 3 | task 27517 | graphs reused = 26342 21.15.057.044 I slot print_timing: id 3 | task 27517 | graph reallocs = 0 / 0 (same size) / (changed size) 21.15.057.084 I slot release: id 3 | task 27517 | stop processing: n_tokens = 759, truncated = 0 21.15.063.170 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 945, t_last = 338981953190 21.15.064.794 I slot launch_slot_: id 0 | task 27525 | processing task, is_child = 0 21.15.069.053 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 947, t_last = 338981953520 21.15.069.122 I slot launch_slot_: id 1 | task 27526 | processing task, is_child = 0 21.15.069.199 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 765, t_last = 338981953843 21.15.069.256 I slot launch_slot_: id 2 | task 27527 | processing task, is_child = 0 21.15.069.299 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 759, t_last = 338981954189 21.15.069.354 I slot launch_slot_: id 3 | task 27528 | processing task, is_child = 0 21.18.526.878 I slot print_timing: id 0 | task 27525 | prompt processing, n_tokens = 772, progress = 0.99, t = 3.46 s / 223.28 tokens per second 21.19.172.260 I slot print_timing: id 1 | task 27526 | prompt processing, n_tokens = 768, progress = 0.99, t = 3.46 s / 222.13 tokens per second 21.19.172.415 I slot print_timing: id 2 | task 27527 | prompt processing, n_tokens = 816, progress = 1.00, t = 3.46 s / 236.02 tokens per second 21.19.172.553 I slot print_timing: id 3 | task 27528 | prompt processing, n_tokens = 821, progress = 1.00, t = 3.46 s / 237.47 tokens per second 21.19.317.666 I slot print_timing: id 0 | task 27525 | prompt eval time = 4207.86 ms / 776 tokens ( 5.42 ms per token, 184.42 tokens per second) 21.19.317.668 I slot print_timing: id 0 | task 27525 | eval time = 40.44 ms / 2 tokens ( 40.44 ms per token, 24.73 tokens per second) 21.19.317.669 I slot print_timing: id 0 | task 27525 | total time = 4248.30 ms / 778 tokens 21.19.317.669 I slot print_timing: id 0 | task 27525 | graphs reused = 26343 21.19.317.670 I slot print_timing: id 0 | task 27525 | graph reallocs = 0 / 0 (same size) / (changed size) 21.19.317.720 I slot release: id 0 | task 27525 | stop processing: n_tokens = 777, truncated = 0 21.19.317.986 I slot print_timing: id 1 | task 27526 | prompt eval time = 4208.06 ms / 772 tokens ( 5.45 ms per token, 183.46 tokens per second) 21.19.317.988 I slot print_timing: id 1 | task 27526 | eval time = 40.49 ms / 2 tokens ( 40.49 ms per token, 24.70 tokens per second) 21.19.317.989 I slot print_timing: id 1 | task 27526 | total time = 4248.56 ms / 774 tokens 21.19.317.989 I slot print_timing: id 1 | task 27526 | graphs reused = 26343 21.19.317.989 I slot print_timing: id 1 | task 27526 | graph reallocs = 0 / 0 (same size) / (changed size) 21.19.318.020 I slot release: id 1 | task 27526 | stop processing: n_tokens = 773, truncated = 0 21.19.318.307 I slot print_timing: id 2 | task 27527 | prompt eval time = 4208.28 ms / 820 tokens ( 5.13 ms per token, 194.85 tokens per second) 21.19.318.310 I slot print_timing: id 2 | task 27527 | eval time = 40.54 ms / 2 tokens ( 40.54 ms per token, 24.67 tokens per second) 21.19.318.310 I slot print_timing: id 2 | task 27527 | total time = 4248.81 ms / 822 tokens 21.19.318.310 I slot print_timing: id 2 | task 27527 | graphs reused = 26343 21.19.318.311 I slot print_timing: id 2 | task 27527 | graph reallocs = 0 / 0 (same size) / (changed size) 21.19.318.340 I slot release: id 2 | task 27527 | stop processing: n_tokens = 821, truncated = 0 21.19.318.643 I slot print_timing: id 3 | task 27528 | prompt eval time = 4208.53 ms / 825 tokens ( 5.10 ms per token, 196.03 tokens per second) 21.19.318.647 I slot print_timing: id 3 | task 27528 | eval time = 40.56 ms / 2 tokens ( 40.56 ms per token, 24.65 tokens per second) 21.19.318.647 I slot print_timing: id 3 | task 27528 | total time = 4249.09 ms / 827 tokens 21.19.318.648 I slot print_timing: id 3 | task 27528 | graphs reused = 26343 21.19.318.648 I slot print_timing: id 3 | task 27528 | graph reallocs = 0 / 0 (same size) / (changed size) 21.19.318.675 I slot release: id 3 | task 27528 | stop processing: n_tokens = 826, truncated = 0 21.19.325.081 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 777, t_last = 338986214825 21.19.326.620 I slot launch_slot_: id 0 | task 27533 | processing task, is_child = 0 21.19.330.859 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.876 (> 0.100 thold), f_keep = 0.903 21.19.330.876 I slot launch_slot_: id 1 | task 27534 | processing task, is_child = 0 21.19.330.955 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 821, t_last = 338986215446 21.19.331.012 I slot launch_slot_: id 2 | task 27535 | processing task, is_child = 0 21.19.331.055 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 826, t_last = 338986215780 21.19.331.116 I slot launch_slot_: id 3 | task 27536 | processing task, is_child = 0 21.22.931.964 I slot print_timing: id 0 | task 27533 | prompt processing, n_tokens = 927, progress = 1.00, t = 3.60 s / 257.44 tokens per second 21.23.578.146 I slot print_timing: id 1 | task 27534 | prompt processing, n_tokens = 537, progress = 0.99, t = 3.60 s / 149.13 tokens per second 21.23.578.284 I slot print_timing: id 2 | task 27535 | prompt processing, n_tokens = 852, progress = 1.00, t = 3.60 s / 236.62 tokens per second 21.23.578.448 I slot print_timing: id 3 | task 27536 | prompt processing, n_tokens = 845, progress = 1.00, t = 3.60 s / 234.68 tokens per second 21.23.723.743 I slot print_timing: id 0 | task 27533 | prompt eval time = 4352.08 ms / 931 tokens ( 4.67 ms per token, 213.92 tokens per second) 21.23.723.745 I slot print_timing: id 0 | task 27533 | eval time = 40.54 ms / 2 tokens ( 40.54 ms per token, 24.67 tokens per second) 21.23.723.746 I slot print_timing: id 0 | task 27533 | total time = 4392.62 ms / 933 tokens 21.23.723.746 I slot print_timing: id 0 | task 27533 | graphs reused = 26345 21.23.723.746 I slot print_timing: id 0 | task 27533 | graph reallocs = 0 / 0 (same size) / (changed size) 21.23.723.797 I slot release: id 0 | task 27533 | stop processing: n_tokens = 932, truncated = 0 21.23.724.068 I slot print_timing: id 1 | task 27534 | prompt eval time = 4352.30 ms / 541 tokens ( 8.04 ms per token, 124.30 tokens per second) 21.23.724.070 I slot print_timing: id 1 | task 27534 | eval time = 40.59 ms / 2 tokens ( 40.59 ms per token, 24.64 tokens per second) 21.23.724.070 I slot print_timing: id 1 | task 27534 | total time = 4392.89 ms / 543 tokens 21.23.724.070 I slot print_timing: id 1 | task 27534 | graphs reused = 26345 21.23.724.071 I slot print_timing: id 1 | task 27534 | graph reallocs = 0 / 0 (same size) / (changed size) 21.23.724.110 I slot release: id 1 | task 27534 | stop processing: n_tokens = 798, truncated = 0 21.23.724.399 I slot print_timing: id 2 | task 27535 | prompt eval time = 4352.52 ms / 856 tokens ( 5.08 ms per token, 196.67 tokens per second) 21.23.724.403 I slot print_timing: id 2 | task 27535 | eval time = 40.63 ms / 2 tokens ( 40.63 ms per token, 24.61 tokens per second) 21.23.724.404 I slot print_timing: id 2 | task 27535 | total time = 4393.15 ms / 858 tokens 21.23.724.404 I slot print_timing: id 2 | task 27535 | graphs reused = 26345 21.23.724.404 I slot print_timing: id 2 | task 27535 | graph reallocs = 0 / 0 (same size) / (changed size) 21.23.724.445 I slot release: id 2 | task 27535 | stop processing: n_tokens = 857, truncated = 0 21.23.724.737 I slot print_timing: id 3 | task 27536 | prompt eval time = 4352.77 ms / 849 tokens ( 5.13 ms per token, 195.05 tokens per second) 21.23.724.739 I slot print_timing: id 3 | task 27536 | eval time = 40.65 ms / 2 tokens ( 40.65 ms per token, 24.60 tokens per second) 21.23.724.740 I slot print_timing: id 3 | task 27536 | total time = 4393.42 ms / 851 tokens 21.23.724.740 I slot print_timing: id 3 | task 27536 | graphs reused = 26345 21.23.724.740 I slot print_timing: id 3 | task 27536 | graph reallocs = 0 / 0 (same size) / (changed size) 21.23.724.784 I slot release: id 3 | task 27536 | stop processing: n_tokens = 850, truncated = 0 21.23.731.755 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 932, t_last = 338990620902 21.23.733.622 I slot launch_slot_: id 0 | task 27541 | processing task, is_child = 0 21.23.738.497 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 798, t_last = 338990621215 21.23.738.577 I slot launch_slot_: id 1 | task 27542 | processing task, is_child = 0 21.23.738.664 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 857, t_last = 338990621550 21.23.738.726 I slot launch_slot_: id 2 | task 27543 | processing task, is_child = 0 21.23.738.770 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 850, t_last = 338990621889 21.23.738.835 I slot launch_slot_: id 3 | task 27544 | processing task, is_child = 0 21.28.963.016 I slot print_timing: id 0 | task 27541 | prompt processing, n_tokens = 950, progress = 1.00, t = 5.22 s / 181.85 tokens per second 21.29.255.032 I slot print_timing: id 1 | task 27542 | prompt processing, n_tokens = 985, progress = 1.00, t = 5.22 s / 188.55 tokens per second 21.29.255.204 I slot print_timing: id 2 | task 27543 | prompt processing, n_tokens = 887, progress = 1.00, t = 5.22 s / 169.79 tokens per second 21.29.255.353 I slot print_timing: id 3 | task 27544 | prompt processing, n_tokens = 1226, progress = 0.70, t = 5.22 s / 234.69 tokens per second 21.30.018.188 I slot print_timing: id 3 | task 27544 | prompt processing, n_tokens = 1738, progress = 1.00, t = 6.28 s / 276.83 tokens per second 21.30.086.156 I slot print_timing: id 0 | task 27541 | prompt eval time = 6278.76 ms / 954 tokens ( 6.58 ms per token, 151.94 tokens per second) 21.30.086.158 I slot print_timing: id 0 | task 27541 | eval time = 68.55 ms / 2 tokens ( 68.55 ms per token, 14.59 tokens per second) 21.30.086.158 I slot print_timing: id 0 | task 27541 | total time = 6347.31 ms / 956 tokens 21.30.086.159 I slot print_timing: id 0 | task 27541 | graphs reused = 26346 21.30.086.159 I slot print_timing: id 0 | task 27541 | graph reallocs = 0 / 0 (same size) / (changed size) 21.30.086.213 I slot release: id 0 | task 27541 | stop processing: n_tokens = 955, truncated = 0 21.30.086.488 I slot print_timing: id 1 | task 27542 | prompt eval time = 6278.99 ms / 989 tokens ( 6.35 ms per token, 157.51 tokens per second) 21.30.086.492 I slot print_timing: id 1 | task 27542 | eval time = 68.59 ms / 2 tokens ( 68.59 ms per token, 14.58 tokens per second) 21.30.086.492 I slot print_timing: id 1 | task 27542 | total time = 6347.58 ms / 991 tokens 21.30.086.492 I slot print_timing: id 1 | task 27542 | graphs reused = 26346 21.30.086.493 I slot print_timing: id 1 | task 27542 | graph reallocs = 0 / 0 (same size) / (changed size) 21.30.086.537 I slot release: id 1 | task 27542 | stop processing: n_tokens = 990, truncated = 0 21.30.086.816 I slot print_timing: id 2 | task 27543 | prompt eval time = 6279.20 ms / 891 tokens ( 7.05 ms per token, 141.90 tokens per second) 21.30.086.818 I slot print_timing: id 2 | task 27543 | eval time = 68.64 ms / 2 tokens ( 68.64 ms per token, 14.57 tokens per second) 21.30.086.818 I slot print_timing: id 2 | task 27543 | total time = 6347.84 ms / 893 tokens 21.30.086.818 I slot print_timing: id 2 | task 27543 | graphs reused = 26346 21.30.086.819 I slot print_timing: id 2 | task 27543 | graph reallocs = 0 / 0 (same size) / (changed size) 21.30.086.861 I slot release: id 2 | task 27543 | stop processing: n_tokens = 892, truncated = 0 21.30.103.930 I slot print_timing: id 3 | task 27544 | prompt eval time = 6348.16 ms / 1742 tokens ( 3.64 ms per token, 274.41 tokens per second) 21.30.103.933 I slot print_timing: id 3 | task 27544 | eval time = 16.73 ms / 2 tokens ( 16.73 ms per token, 59.77 tokens per second) 21.30.103.934 I slot print_timing: id 3 | task 27544 | total time = 6364.89 ms / 1744 tokens 21.30.103.934 I slot print_timing: id 3 | task 27544 | graphs reused = 26346 21.30.103.935 I slot print_timing: id 3 | task 27544 | graph reallocs = 0 / 0 (same size) / (changed size) 21.30.104.029 I slot release: id 3 | task 27544 | stop processing: n_tokens = 1743, truncated = 0 21.30.104.035 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 955, t_last = 338996983318 21.30.106.076 I slot launch_slot_: id 0 | task 27550 | processing task, is_child = 0 21.30.112.561 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 990, t_last = 338996983642 21.30.112.631 I slot launch_slot_: id 1 | task 27551 | processing task, is_child = 0 21.30.112.751 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.828 (> 0.100 thold), f_keep = 0.843 21.30.112.766 I slot launch_slot_: id 2 | task 27552 | processing task, is_child = 0 21.30.112.837 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1743, t_last = 338997001135 21.30.112.924 I slot launch_slot_: id 3 | task 27553 | processing task, is_child = 0 21.33.383.099 I slot print_timing: id 0 | task 27550 | prompt processing, n_tokens = 858, progress = 1.00, t = 3.27 s / 262.37 tokens per second 21.34.027.135 I slot print_timing: id 1 | task 27551 | prompt processing, n_tokens = 723, progress = 0.99, t = 3.27 s / 221.10 tokens per second 21.34.027.266 I slot print_timing: id 2 | task 27552 | prompt processing, n_tokens = 529, progress = 1.00, t = 3.27 s / 161.77 tokens per second 21.34.027.420 I slot print_timing: id 3 | task 27553 | prompt processing, n_tokens = 696, progress = 0.99, t = 3.27 s / 212.85 tokens per second 21.34.172.663 I slot print_timing: id 0 | task 27550 | prompt eval time = 4019.09 ms / 862 tokens ( 4.66 ms per token, 214.48 tokens per second) 21.34.172.667 I slot print_timing: id 0 | task 27550 | eval time = 40.65 ms / 2 tokens ( 40.65 ms per token, 24.60 tokens per second) 21.34.172.667 I slot print_timing: id 0 | task 27550 | total time = 4059.73 ms / 864 tokens 21.34.172.668 I slot print_timing: id 0 | task 27550 | graphs reused = 26348 21.34.172.668 I slot print_timing: id 0 | task 27550 | graph reallocs = 0 / 0 (same size) / (changed size) 21.34.172.716 I slot release: id 0 | task 27550 | stop processing: n_tokens = 863, truncated = 0 21.34.172.984 I slot print_timing: id 1 | task 27551 | prompt eval time = 4019.30 ms / 727 tokens ( 5.53 ms per token, 180.88 tokens per second) 21.34.172.989 I slot print_timing: id 1 | task 27551 | eval time = 40.68 ms / 2 tokens ( 40.68 ms per token, 24.58 tokens per second) 21.34.172.989 I slot print_timing: id 1 | task 27551 | total time = 4059.97 ms / 729 tokens 21.34.172.989 I slot print_timing: id 1 | task 27551 | graphs reused = 26348 21.34.172.990 I slot print_timing: id 1 | task 27551 | graph reallocs = 0 / 0 (same size) / (changed size) 21.34.173.031 I slot release: id 1 | task 27551 | stop processing: n_tokens = 728, truncated = 0 21.34.173.299 I slot print_timing: id 2 | task 27552 | prompt eval time = 4019.58 ms / 533 tokens ( 7.54 ms per token, 132.60 tokens per second) 21.34.173.301 I slot print_timing: id 2 | task 27552 | eval time = 40.65 ms / 2 tokens ( 40.65 ms per token, 24.60 tokens per second) 21.34.173.301 I slot print_timing: id 2 | task 27552 | total time = 4060.23 ms / 535 tokens 21.34.173.301 I slot print_timing: id 2 | task 27552 | graphs reused = 26348 21.34.173.302 I slot print_timing: id 2 | task 27552 | graph reallocs = 0 / 0 (same size) / (changed size) 21.34.173.345 I slot release: id 2 | task 27552 | stop processing: n_tokens = 909, truncated = 0 21.34.173.621 I slot print_timing: id 3 | task 27553 | prompt eval time = 4020.02 ms / 700 tokens ( 5.74 ms per token, 174.13 tokens per second) 21.34.173.624 I slot print_timing: id 3 | task 27553 | eval time = 40.44 ms / 2 tokens ( 40.44 ms per token, 24.73 tokens per second) 21.34.173.625 I slot print_timing: id 3 | task 27553 | total time = 4060.46 ms / 702 tokens 21.34.173.625 I slot print_timing: id 3 | task 27553 | graphs reused = 26348 21.34.173.625 I slot print_timing: id 3 | task 27553 | graph reallocs = 0 / 0 (same size) / (changed size) 21.34.173.655 I slot release: id 3 | task 27553 | stop processing: n_tokens = 701, truncated = 0 21.34.180.281 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 863, t_last = 339001069821 21.34.182.044 I slot launch_slot_: id 0 | task 27559 | processing task, is_child = 0 21.34.186.332 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.876 (> 0.100 thold), f_keep = 0.848 21.34.186.349 I slot launch_slot_: id 1 | task 27561 | processing task, is_child = 0 21.34.186.427 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.874 (> 0.100 thold), f_keep = 0.880 21.34.186.442 I slot launch_slot_: id 3 | task 27558 | processing task, is_child = 0 21.34.186.487 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 909, t_last = 339001070450 21.34.187.006 I slot launch_slot_: id 2 | task 27560 | processing task, is_child = 0 21.37.441.425 I slot print_timing: id 0 | task 27559 | prompt processing, n_tokens = 824, progress = 1.00, t = 3.25 s / 253.24 tokens per second 21.37.441.580 I slot print_timing: id 3 | task 27558 | prompt processing, n_tokens = 518, progress = 0.99, t = 3.25 s / 159.21 tokens per second 21.37.534.160 I slot print_timing: id 1 | task 27561 | prompt eval time = 3254.05 ms / 493 tokens ( 6.60 ms per token, 151.50 tokens per second) 21.37.534.166 I slot print_timing: id 1 | task 27561 | eval time = 93.04 ms / 2 tokens ( 93.04 ms per token, 10.75 tokens per second) 21.37.534.166 I slot print_timing: id 1 | task 27561 | total time = 3347.09 ms / 495 tokens 21.37.534.167 I slot print_timing: id 1 | task 27561 | graphs reused = 26348 21.37.534.167 I slot print_timing: id 1 | task 27561 | graph reallocs = 0 / 0 (same size) / (changed size) 21.37.534.214 I slot release: id 1 | task 27561 | stop processing: n_tokens = 705, truncated = 0 21.37.534.465 I slot print_timing: id 2 | task 27560 | prompt eval time = 3254.23 ms / 497 tokens ( 6.55 ms per token, 152.72 tokens per second) 21.37.534.467 I slot print_timing: id 2 | task 27560 | eval time = 93.05 ms / 2 tokens ( 93.05 ms per token, 10.75 tokens per second) 21.37.534.467 I slot print_timing: id 2 | task 27560 | total time = 3347.28 ms / 499 tokens 21.37.534.467 I slot print_timing: id 2 | task 27560 | graphs reused = 26348 21.37.534.468 I slot print_timing: id 2 | task 27560 | graph reallocs = 0 / 0 (same size) / (changed size) 21.37.534.499 I slot release: id 2 | task 27560 | stop processing: n_tokens = 709, truncated = 0 21.37.566.298 I slot print_timing: id 0 | task 27559 | prompt eval time = 3346.89 ms / 828 tokens ( 4.04 ms per token, 247.39 tokens per second) 21.37.566.301 I slot print_timing: id 0 | task 27559 | eval time = 32.39 ms / 2 tokens ( 32.39 ms per token, 30.87 tokens per second) 21.37.566.301 I slot print_timing: id 0 | task 27559 | total time = 3379.28 ms / 830 tokens 21.37.566.302 I slot print_timing: id 0 | task 27559 | graphs reused = 26348 21.37.566.302 I slot print_timing: id 0 | task 27559 | graph reallocs = 0 / 0 (same size) / (changed size) 21.37.566.341 I slot release: id 0 | task 27559 | stop processing: n_tokens = 829, truncated = 0 21.37.566.611 I slot print_timing: id 3 | task 27558 | prompt eval time = 3347.53 ms / 522 tokens ( 6.41 ms per token, 155.94 tokens per second) 21.37.566.614 I slot print_timing: id 3 | task 27558 | eval time = 31.80 ms / 2 tokens ( 31.80 ms per token, 31.45 tokens per second) 21.37.566.614 I slot print_timing: id 3 | task 27558 | total time = 3379.32 ms / 524 tokens 21.37.566.614 I slot print_timing: id 3 | task 27558 | graphs reused = 26348 21.37.566.615 I slot print_timing: id 3 | task 27558 | graph reallocs = 0 / 0 (same size) / (changed size) 21.37.566.643 I slot release: id 3 | task 27558 | stop processing: n_tokens = 707, truncated = 0 21.37.566.647 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 705, t_last = 339004431319 21.37.567.400 I slot launch_slot_: id 1 | task 27566 | processing task, is_child = 0 21.37.572.018 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 709, t_last = 339004431604 21.37.572.086 I slot launch_slot_: id 2 | task 27567 | processing task, is_child = 0 21.37.572.170 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 829, t_last = 339004463447 21.37.572.230 I slot launch_slot_: id 0 | task 27568 | processing task, is_child = 0 21.37.572.272 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 707, t_last = 339004463748 21.37.572.329 I slot launch_slot_: id 3 | task 27569 | processing task, is_child = 0 21.41.924.741 I slot print_timing: id 0 | task 27568 | prompt processing, n_tokens = 932, progress = 1.00, t = 4.35 s / 214.14 tokens per second 21.42.574.623 I slot print_timing: id 1 | task 27566 | prompt processing, n_tokens = 913, progress = 1.00, t = 4.35 s / 209.77 tokens per second 21.42.574.774 I slot print_timing: id 2 | task 27567 | prompt processing, n_tokens = 958, progress = 1.00, t = 4.35 s / 220.11 tokens per second 21.42.574.934 I slot print_timing: id 3 | task 27569 | prompt processing, n_tokens = 922, progress = 1.00, t = 4.35 s / 211.85 tokens per second 21.42.720.290 I slot print_timing: id 0 | task 27568 | prompt eval time = 5107.18 ms / 936 tokens ( 5.46 ms per token, 183.27 tokens per second) 21.42.720.295 I slot print_timing: id 0 | task 27568 | eval time = 40.78 ms / 2 tokens ( 40.78 ms per token, 24.52 tokens per second) 21.42.720.296 I slot print_timing: id 0 | task 27568 | total time = 5147.95 ms / 938 tokens 21.42.720.297 I slot print_timing: id 0 | task 27568 | graphs reused = 26350 21.42.720.297 I slot print_timing: id 0 | task 27568 | graph reallocs = 0 / 0 (same size) / (changed size) 21.42.720.348 I slot release: id 0 | task 27568 | stop processing: n_tokens = 937, truncated = 0 21.42.720.609 I slot print_timing: id 1 | task 27566 | prompt eval time = 5107.39 ms / 917 tokens ( 5.57 ms per token, 179.54 tokens per second) 21.42.720.611 I slot print_timing: id 1 | task 27566 | eval time = 40.82 ms / 2 tokens ( 40.82 ms per token, 24.50 tokens per second) 21.42.720.611 I slot print_timing: id 1 | task 27566 | total time = 5148.21 ms / 919 tokens 21.42.720.611 I slot print_timing: id 1 | task 27566 | graphs reused = 26350 21.42.720.612 I slot print_timing: id 1 | task 27566 | graph reallocs = 0 / 0 (same size) / (changed size) 21.42.720.660 I slot release: id 1 | task 27566 | stop processing: n_tokens = 918, truncated = 0 21.42.720.939 I slot print_timing: id 2 | task 27567 | prompt eval time = 5107.71 ms / 962 tokens ( 5.31 ms per token, 188.34 tokens per second) 21.42.720.941 I slot print_timing: id 2 | task 27567 | eval time = 40.78 ms / 2 tokens ( 40.78 ms per token, 24.52 tokens per second) 21.42.720.941 I slot print_timing: id 2 | task 27567 | total time = 5148.49 ms / 964 tokens 21.42.720.942 I slot print_timing: id 2 | task 27567 | graphs reused = 26350 21.42.720.942 I slot print_timing: id 2 | task 27567 | graph reallocs = 0 / 0 (same size) / (changed size) 21.42.720.975 I slot release: id 2 | task 27567 | stop processing: n_tokens = 963, truncated = 0 21.42.721.271 I slot print_timing: id 3 | task 27569 | prompt eval time = 5108.14 ms / 926 tokens ( 5.52 ms per token, 181.28 tokens per second) 21.42.721.273 I slot print_timing: id 3 | task 27569 | eval time = 40.63 ms / 2 tokens ( 40.63 ms per token, 24.61 tokens per second) 21.42.721.274 I slot print_timing: id 3 | task 27569 | total time = 5148.77 ms / 928 tokens 21.42.721.274 I slot print_timing: id 3 | task 27569 | graphs reused = 26350 21.42.721.274 I slot print_timing: id 3 | task 27569 | graph reallocs = 0 / 0 (same size) / (changed size) 21.42.721.304 I slot release: id 3 | task 27569 | stop processing: n_tokens = 927, truncated = 0 21.42.727.438 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.892 (> 0.100 thold), f_keep = 0.879 21.42.727.467 I slot launch_slot_: id 0 | task 27574 | processing task, is_child = 0 21.42.732.512 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 918, t_last = 339009617765 21.42.732.583 I slot launch_slot_: id 1 | task 27575 | processing task, is_child = 0 21.42.732.677 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 963, t_last = 339009618080 21.42.732.743 I slot launch_slot_: id 2 | task 27576 | processing task, is_child = 0 21.42.732.788 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 927, t_last = 339009618409 21.42.732.851 I slot launch_slot_: id 3 | task 27577 | processing task, is_child = 0 21.47.320.489 I slot print_timing: id 1 | task 27575 | prompt processing, n_tokens = 817, progress = 1.00, t = 4.59 s / 178.10 tokens per second 21.47.320.640 I slot print_timing: id 2 | task 27576 | prompt processing, n_tokens = 882, progress = 1.00, t = 4.59 s / 192.28 tokens per second 21.47.320.795 I slot print_timing: id 3 | task 27577 | prompt processing, n_tokens = 996, progress = 1.00, t = 4.59 s / 217.13 tokens per second 21.47.424.930 I slot print_timing: id 0 | task 27574 | prompt eval time = 4587.62 ms / 504 tokens ( 9.10 ms per token, 109.86 tokens per second) 21.47.424.932 I slot print_timing: id 0 | task 27574 | eval time = 104.46 ms / 2 tokens ( 104.46 ms per token, 9.57 tokens per second) 21.47.424.933 I slot print_timing: id 0 | task 27574 | total time = 4692.07 ms / 506 tokens 21.47.424.933 I slot print_timing: id 0 | task 27574 | graphs reused = 26350 21.47.424.934 I slot print_timing: id 0 | task 27574 | graph reallocs = 0 / 0 (same size) / (changed size) 21.47.424.987 I slot release: id 0 | task 27574 | stop processing: n_tokens = 925, truncated = 0 21.47.458.442 I slot print_timing: id 1 | task 27575 | prompt eval time = 4692.29 ms / 821 tokens ( 5.72 ms per token, 174.97 tokens per second) 21.47.458.444 I slot print_timing: id 1 | task 27575 | eval time = 33.15 ms / 2 tokens ( 33.15 ms per token, 30.16 tokens per second) 21.47.458.445 I slot print_timing: id 1 | task 27575 | total time = 4725.45 ms / 823 tokens 21.47.458.445 I slot print_timing: id 1 | task 27575 | graphs reused = 26350 21.47.458.445 I slot print_timing: id 1 | task 27575 | graph reallocs = 0 / 0 (same size) / (changed size) 21.47.458.488 I slot release: id 1 | task 27575 | stop processing: n_tokens = 822, truncated = 0 21.47.458.763 I slot print_timing: id 2 | task 27576 | prompt eval time = 4692.50 ms / 886 tokens ( 5.30 ms per token, 188.81 tokens per second) 21.47.458.765 I slot print_timing: id 2 | task 27576 | eval time = 33.18 ms / 2 tokens ( 33.18 ms per token, 30.14 tokens per second) 21.47.458.766 I slot print_timing: id 2 | task 27576 | total time = 4725.68 ms / 888 tokens 21.47.458.767 I slot print_timing: id 2 | task 27576 | graphs reused = 26350 21.47.458.767 I slot print_timing: id 2 | task 27576 | graph reallocs = 0 / 0 (same size) / (changed size) 21.47.458.813 I slot release: id 2 | task 27576 | stop processing: n_tokens = 887, truncated = 0 21.47.459.085 I slot print_timing: id 3 | task 27577 | prompt eval time = 4692.75 ms / 1000 tokens ( 4.69 ms per token, 213.09 tokens per second) 21.47.459.088 I slot print_timing: id 3 | task 27577 | eval time = 33.19 ms / 2 tokens ( 33.19 ms per token, 30.13 tokens per second) 21.47.459.088 I slot print_timing: id 3 | task 27577 | total time = 4725.94 ms / 1002 tokens 21.47.459.088 I slot print_timing: id 3 | task 27577 | graphs reused = 26350 21.47.459.089 I slot print_timing: id 3 | task 27577 | graph reallocs = 0 / 0 (same size) / (changed size) 21.47.459.131 I slot release: id 3 | task 27577 | stop processing: n_tokens = 1001, truncated = 0 21.47.459.136 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.799 (> 0.100 thold), f_keep = 0.892 21.47.459.160 I slot launch_slot_: id 2 | task 27582 | processing task, is_child = 0 21.47.464.642 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.791 21.47.464.667 I slot launch_slot_: id 3 | task 27583 | processing task, is_child = 0 21.47.464.758 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 925, t_last = 339014322093 21.47.465.689 I slot launch_slot_: id 0 | task 27584 | processing task, is_child = 0 21.47.465.748 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 822, t_last = 339014355593 21.47.465.804 I slot launch_slot_: id 1 | task 27585 | processing task, is_child = 0 21.50.904.139 I slot print_timing: id 1 | task 27585 | prompt processing, n_tokens = 957, progress = 1.00, t = 3.44 s / 278.39 tokens per second 21.50.904.302 I slot print_timing: id 2 | task 27582 | prompt processing, n_tokens = 616, progress = 1.00, t = 3.44 s / 179.20 tokens per second 21.50.996.830 I slot print_timing: id 0 | task 27584 | prompt eval time = 3438.03 ms / 404 tokens ( 8.51 ms per token, 117.51 tokens per second) 21.50.996.833 I slot print_timing: id 0 | task 27584 | eval time = 92.99 ms / 2 tokens ( 92.99 ms per token, 10.75 tokens per second) 21.50.996.833 I slot print_timing: id 0 | task 27584 | total time = 3531.02 ms / 406 tokens 21.50.996.834 I slot print_timing: id 0 | task 27584 | graphs reused = 26350 21.50.996.834 I slot print_timing: id 0 | task 27584 | graph reallocs = 0 / 0 (same size) / (changed size) 21.50.996.885 I slot release: id 0 | task 27584 | stop processing: n_tokens = 889, truncated = 0 21.50.997.958 I slot print_timing: id 3 | task 27583 | prompt eval time = 3438.06 ms / 388 tokens ( 8.86 ms per token, 112.85 tokens per second) 21.50.997.960 I slot print_timing: id 3 | task 27583 | eval time = 93.83 ms / 2 tokens ( 93.83 ms per token, 10.66 tokens per second) 21.50.997.960 I slot print_timing: id 3 | task 27583 | total time = 3531.89 ms / 390 tokens 21.50.997.960 I slot print_timing: id 3 | task 27583 | graphs reused = 26350 21.50.997.961 I slot print_timing: id 3 | task 27583 | graph reallocs = 0 / 0 (same size) / (changed size) 21.50.998.009 I slot release: id 3 | task 27583 | stop processing: n_tokens = 873, truncated = 0 21.51.022.688 I slot print_timing: id 1 | task 27585 | prompt eval time = 3531.28 ms / 961 tokens ( 3.67 ms per token, 272.14 tokens per second) 21.51.022.690 I slot print_timing: id 1 | task 27585 | eval time = 25.48 ms / 2 tokens ( 25.48 ms per token, 39.25 tokens per second) 21.51.022.690 I slot print_timing: id 1 | task 27585 | total time = 3556.76 ms / 963 tokens 21.51.022.691 I slot print_timing: id 1 | task 27585 | graphs reused = 26350 21.51.022.691 I slot print_timing: id 1 | task 27585 | graph reallocs = 0 / 0 (same size) / (changed size) 21.51.022.740 I slot release: id 1 | task 27585 | stop processing: n_tokens = 962, truncated = 0 21.51.023.031 I slot print_timing: id 2 | task 27582 | prompt eval time = 3531.64 ms / 620 tokens ( 5.70 ms per token, 175.56 tokens per second) 21.51.023.033 I slot print_timing: id 2 | task 27582 | eval time = 25.41 ms / 2 tokens ( 25.41 ms per token, 39.36 tokens per second) 21.51.023.033 I slot print_timing: id 2 | task 27582 | total time = 3557.05 ms / 622 tokens 21.51.023.033 I slot print_timing: id 2 | task 27582 | graphs reused = 26350 21.51.023.033 I slot print_timing: id 2 | task 27582 | graph reallocs = 0 / 0 (same size) / (changed size) 21.51.023.077 I slot release: id 2 | task 27582 | stop processing: n_tokens = 991, truncated = 0 21.51.023.082 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 889, t_last = 339017893992 21.51.023.962 I slot launch_slot_: id 0 | task 27590 | processing task, is_child = 0 21.51.029.439 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 873, t_last = 339017895114 21.51.029.516 I slot launch_slot_: id 3 | task 27591 | processing task, is_child = 0 21.51.029.610 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 962, t_last = 339017919845 21.51.029.675 I slot launch_slot_: id 1 | task 27592 | processing task, is_child = 0 21.51.029.720 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 991, t_last = 339017920182 21.51.029.785 I slot launch_slot_: id 2 | task 27593 | processing task, is_child = 0 21.55.619.938 I slot print_timing: id 0 | task 27590 | prompt processing, n_tokens = 865, progress = 1.00, t = 4.59 s / 188.45 tokens per second 21.56.266.759 I slot print_timing: id 1 | task 27592 | prompt processing, n_tokens = 1276, progress = 1.00, t = 4.59 s / 277.99 tokens per second 21.56.266.965 I slot print_timing: id 2 | task 27593 | prompt processing, n_tokens = 899, progress = 1.00, t = 4.59 s / 195.86 tokens per second 21.56.267.116 I slot print_timing: id 3 | task 27591 | prompt processing, n_tokens = 906, progress = 1.00, t = 4.59 s / 197.39 tokens per second 21.56.412.320 I slot print_timing: id 0 | task 27590 | prompt eval time = 5342.15 ms / 869 tokens ( 6.15 ms per token, 162.67 tokens per second) 21.56.412.322 I slot print_timing: id 0 | task 27590 | eval time = 40.38 ms / 2 tokens ( 40.38 ms per token, 24.76 tokens per second) 21.56.412.323 I slot print_timing: id 0 | task 27590 | total time = 5382.53 ms / 871 tokens 21.56.412.323 I slot print_timing: id 0 | task 27590 | graphs reused = 26352 21.56.412.324 I slot print_timing: id 0 | task 27590 | graph reallocs = 0 / 0 (same size) / (changed size) 21.56.412.372 I slot release: id 0 | task 27590 | stop processing: n_tokens = 870, truncated = 0 21.56.412.655 I slot print_timing: id 1 | task 27592 | prompt eval time = 5342.35 ms / 1280 tokens ( 4.17 ms per token, 239.59 tokens per second) 21.56.412.658 I slot print_timing: id 1 | task 27592 | eval time = 40.43 ms / 2 tokens ( 40.43 ms per token, 24.73 tokens per second) 21.56.412.658 I slot print_timing: id 1 | task 27592 | total time = 5382.78 ms / 1282 tokens 21.56.412.659 I slot print_timing: id 1 | task 27592 | graphs reused = 26352 21.56.412.659 I slot print_timing: id 1 | task 27592 | graph reallocs = 0 / 0 (same size) / (changed size) 21.56.412.719 I slot release: id 1 | task 27592 | stop processing: n_tokens = 1281, truncated = 0 21.56.413.024 I slot print_timing: id 2 | task 27593 | prompt eval time = 5342.58 ms / 903 tokens ( 5.92 ms per token, 169.02 tokens per second) 21.56.413.031 I slot print_timing: id 2 | task 27593 | eval time = 40.51 ms / 2 tokens ( 40.51 ms per token, 24.68 tokens per second) 21.56.413.031 I slot print_timing: id 2 | task 27593 | total time = 5383.09 ms / 905 tokens 21.56.413.031 I slot print_timing: id 2 | task 27593 | graphs reused = 26352 21.56.413.032 I slot print_timing: id 2 | task 27593 | graph reallocs = 0 / 0 (same size) / (changed size) 21.56.413.072 I slot release: id 2 | task 27593 | stop processing: n_tokens = 904, truncated = 0 21.56.413.369 I slot print_timing: id 3 | task 27591 | prompt eval time = 5342.87 ms / 910 tokens ( 5.87 ms per token, 170.32 tokens per second) 21.56.413.371 I slot print_timing: id 3 | task 27591 | eval time = 40.49 ms / 2 tokens ( 40.49 ms per token, 24.70 tokens per second) 21.56.413.372 I slot print_timing: id 3 | task 27591 | total time = 5383.36 ms / 912 tokens 21.56.413.372 I slot print_timing: id 3 | task 27591 | graphs reused = 26352 21.56.413.372 I slot print_timing: id 3 | task 27591 | graph reallocs = 0 / 0 (same size) / (changed size) 21.56.413.410 I slot release: id 3 | task 27591 | stop processing: n_tokens = 911, truncated = 0 21.56.419.483 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 870, t_last = 339023309477 21.56.421.034 I slot launch_slot_: id 0 | task 27598 | processing task, is_child = 0 21.56.426.480 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.877 21.56.426.498 I slot launch_slot_: id 1 | task 27599 | processing task, is_child = 0 21.56.426.589 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 904, t_last = 339023310177 21.56.427.410 I slot launch_slot_: id 2 | task 27600 | processing task, is_child = 0 21.56.427.461 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 911, t_last = 339023310515 21.56.427.525 I slot launch_slot_: id 3 | task 27601 | processing task, is_child = 0 22.00.654.789 I slot print_timing: id 0 | task 27598 | prompt processing, n_tokens = 763, progress = 0.99, t = 4.23 s / 180.52 tokens per second 22.00.654.945 I slot print_timing: id 3 | task 27601 | prompt processing, n_tokens = 1283, progress = 1.00, t = 4.23 s / 303.57 tokens per second 22.00.748.175 I slot print_timing: id 1 | task 27599 | prompt eval time = 4226.89 ms / 439 tokens ( 9.63 ms per token, 103.86 tokens per second) 22.00.748.177 I slot print_timing: id 1 | task 27599 | eval time = 93.70 ms / 2 tokens ( 93.70 ms per token, 10.67 tokens per second) 22.00.748.178 I slot print_timing: id 1 | task 27599 | total time = 4320.59 ms / 441 tokens 22.00.748.178 I slot print_timing: id 1 | task 27599 | graphs reused = 26352 22.00.748.179 I slot print_timing: id 1 | task 27599 | graph reallocs = 0 / 0 (same size) / (changed size) 22.00.748.242 I slot release: id 1 | task 27599 | stop processing: n_tokens = 1204, truncated = 0 22.00.748.516 I slot print_timing: id 2 | task 27600 | prompt eval time = 4227.06 ms / 476 tokens ( 8.88 ms per token, 112.61 tokens per second) 22.00.748.518 I slot print_timing: id 2 | task 27600 | eval time = 93.74 ms / 2 tokens ( 93.74 ms per token, 10.67 tokens per second) 22.00.748.519 I slot print_timing: id 2 | task 27600 | total time = 4320.79 ms / 478 tokens 22.00.748.519 I slot print_timing: id 2 | task 27600 | graphs reused = 26352 22.00.748.520 I slot print_timing: id 2 | task 27600 | graph reallocs = 0 / 0 (same size) / (changed size) 22.00.748.562 I slot release: id 2 | task 27600 | stop processing: n_tokens = 1241, truncated = 0 22.00.780.782 I slot print_timing: id 0 | task 27598 | prompt eval time = 4320.39 ms / 767 tokens ( 5.63 ms per token, 177.53 tokens per second) 22.00.780.784 I slot print_timing: id 0 | task 27598 | eval time = 32.86 ms / 2 tokens ( 32.86 ms per token, 30.43 tokens per second) 22.00.780.785 I slot print_timing: id 0 | task 27598 | total time = 4353.25 ms / 769 tokens 22.00.780.785 I slot print_timing: id 0 | task 27598 | graphs reused = 26352 22.00.780.785 I slot print_timing: id 0 | task 27598 | graph reallocs = 0 / 0 (same size) / (changed size) 22.00.780.827 I slot release: id 0 | task 27598 | stop processing: n_tokens = 768, truncated = 0 22.00.781.109 I slot print_timing: id 3 | task 27601 | prompt eval time = 4321.06 ms / 1287 tokens ( 3.36 ms per token, 297.84 tokens per second) 22.00.781.113 I slot print_timing: id 3 | task 27601 | eval time = 32.23 ms / 2 tokens ( 32.23 ms per token, 31.03 tokens per second) 22.00.781.113 I slot print_timing: id 3 | task 27601 | total time = 4353.29 ms / 1289 tokens 22.00.781.114 I slot print_timing: id 3 | task 27601 | graphs reused = 26352 22.00.781.114 I slot print_timing: id 3 | task 27601 | graph reallocs = 0 / 0 (same size) / (changed size) 22.00.781.175 I slot release: id 3 | task 27601 | stop processing: n_tokens = 1288, truncated = 0 22.00.781.181 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.872 (> 0.100 thold), f_keep = 0.889 22.00.781.207 I slot launch_slot_: id 0 | task 27606 | processing task, is_child = 0 22.00.787.472 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1204, t_last = 339027645348 22.00.787.556 I slot launch_slot_: id 1 | task 27607 | processing task, is_child = 0 22.00.787.671 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1241, t_last = 339027645667 22.00.787.740 I slot launch_slot_: id 2 | task 27609 | processing task, is_child = 0 22.00.787.805 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1288, t_last = 339027678282 22.00.787.881 I slot launch_slot_: id 3 | task 27608 | processing task, is_child = 0 22.04.369.833 I slot print_timing: id 0 | task 27606 | prompt processing, n_tokens = 528, progress = 0.99, t = 3.58 s / 147.41 tokens per second 22.05.016.581 I slot print_timing: id 1 | task 27607 | prompt processing, n_tokens = 870, progress = 1.00, t = 3.58 s / 242.89 tokens per second 22.05.016.742 I slot print_timing: id 2 | task 27609 | prompt processing, n_tokens = 840, progress = 1.00, t = 3.58 s / 234.52 tokens per second 22.05.016.878 I slot print_timing: id 3 | task 27608 | prompt processing, n_tokens = 766, progress = 0.99, t = 3.58 s / 213.87 tokens per second 22.05.162.502 I slot print_timing: id 0 | task 27606 | prompt eval time = 4333.66 ms / 532 tokens ( 8.15 ms per token, 122.76 tokens per second) 22.05.162.504 I slot print_timing: id 0 | task 27606 | eval time = 40.95 ms / 2 tokens ( 40.95 ms per token, 24.42 tokens per second) 22.05.162.504 I slot print_timing: id 0 | task 27606 | total time = 4374.61 ms / 534 tokens 22.05.162.505 I slot print_timing: id 0 | task 27606 | graphs reused = 26353 22.05.162.505 I slot print_timing: id 0 | task 27606 | graph reallocs = 0 / 0 (same size) / (changed size) 22.05.162.556 I slot release: id 0 | task 27606 | stop processing: n_tokens = 784, truncated = 0 22.05.162.827 I slot print_timing: id 1 | task 27607 | prompt eval time = 4333.84 ms / 874 tokens ( 4.96 ms per token, 201.67 tokens per second) 22.05.162.830 I slot print_timing: id 1 | task 27607 | eval time = 41.01 ms / 2 tokens ( 41.01 ms per token, 24.39 tokens per second) 22.05.162.831 I slot print_timing: id 1 | task 27607 | total time = 4374.84 ms / 876 tokens 22.05.162.831 I slot print_timing: id 1 | task 27607 | graphs reused = 26353 22.05.162.831 I slot print_timing: id 1 | task 27607 | graph reallocs = 0 / 0 (same size) / (changed size) 22.05.162.873 I slot release: id 1 | task 27607 | stop processing: n_tokens = 875, truncated = 0 22.05.163.156 I slot print_timing: id 2 | task 27609 | prompt eval time = 4334.13 ms / 844 tokens ( 5.14 ms per token, 194.73 tokens per second) 22.05.163.159 I slot print_timing: id 2 | task 27609 | eval time = 40.94 ms / 2 tokens ( 40.94 ms per token, 24.42 tokens per second) 22.05.163.159 I slot print_timing: id 2 | task 27609 | total time = 4375.07 ms / 846 tokens 22.05.163.160 I slot print_timing: id 2 | task 27609 | graphs reused = 26353 22.05.163.160 I slot print_timing: id 2 | task 27609 | graph reallocs = 0 / 0 (same size) / (changed size) 22.05.163.202 I slot release: id 2 | task 27609 | stop processing: n_tokens = 845, truncated = 0 22.05.163.539 I slot print_timing: id 3 | task 27608 | prompt eval time = 4334.55 ms / 770 tokens ( 5.63 ms per token, 177.64 tokens per second) 22.05.163.542 I slot print_timing: id 3 | task 27608 | eval time = 40.81 ms / 2 tokens ( 40.81 ms per token, 24.50 tokens per second) 22.05.163.543 I slot print_timing: id 3 | task 27608 | total time = 4375.36 ms / 772 tokens 22.05.163.543 I slot print_timing: id 3 | task 27608 | graphs reused = 26353 22.05.163.543 I slot print_timing: id 3 | task 27608 | graph reallocs = 0 / 0 (same size) / (changed size) 22.05.163.583 I slot release: id 3 | task 27608 | stop processing: n_tokens = 771, truncated = 0 22.05.170.447 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.811 (> 0.100 thold), f_keep = 0.860 22.05.170.469 I slot launch_slot_: id 3 | task 27614 | processing task, is_child = 0 22.05.175.475 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 784, t_last = 339032059661 22.05.175.547 I slot launch_slot_: id 0 | task 27615 | processing task, is_child = 0 22.05.175.633 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 875, t_last = 339032059978 22.05.175.691 I slot launch_slot_: id 1 | task 27616 | processing task, is_child = 0 22.05.175.734 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 845, t_last = 339032060307 22.05.175.790 I slot launch_slot_: id 2 | task 27617 | processing task, is_child = 0 22.08.424.214 I slot print_timing: id 0 | task 27615 | prompt processing, n_tokens = 752, progress = 0.99, t = 3.25 s / 231.50 tokens per second 22.09.068.091 I slot print_timing: id 1 | task 27616 | prompt processing, n_tokens = 746, progress = 0.99, t = 3.25 s / 229.66 tokens per second 22.09.068.225 I slot print_timing: id 2 | task 27617 | prompt processing, n_tokens = 775, progress = 0.99, t = 3.25 s / 238.59 tokens per second 22.09.068.362 I slot print_timing: id 3 | task 27614 | prompt processing, n_tokens = 560, progress = 1.00, t = 3.25 s / 172.40 tokens per second 22.09.214.262 I slot print_timing: id 0 | task 27615 | prompt eval time = 3997.56 ms / 756 tokens ( 5.29 ms per token, 189.12 tokens per second) 22.09.214.264 I slot print_timing: id 0 | task 27615 | eval time = 40.91 ms / 2 tokens ( 40.91 ms per token, 24.45 tokens per second) 22.09.214.265 I slot print_timing: id 0 | task 27615 | total time = 4038.46 ms / 758 tokens 22.09.214.266 I slot print_timing: id 0 | task 27615 | graphs reused = 26354 22.09.214.266 I slot print_timing: id 0 | task 27615 | graph reallocs = 0 / 0 (same size) / (changed size) 22.09.214.310 I slot release: id 0 | task 27615 | stop processing: n_tokens = 757, truncated = 0 22.09.214.573 I slot print_timing: id 1 | task 27616 | prompt eval time = 3997.87 ms / 750 tokens ( 5.33 ms per token, 187.60 tokens per second) 22.09.214.574 I slot print_timing: id 1 | task 27616 | eval time = 40.85 ms / 2 tokens ( 40.85 ms per token, 24.48 tokens per second) 22.09.214.575 I slot print_timing: id 1 | task 27616 | total time = 4038.72 ms / 752 tokens 22.09.214.575 I slot print_timing: id 1 | task 27616 | graphs reused = 26354 22.09.214.576 I slot print_timing: id 1 | task 27616 | graph reallocs = 0 / 0 (same size) / (changed size) 22.09.214.611 I slot release: id 1 | task 27616 | stop processing: n_tokens = 751, truncated = 0 22.09.214.906 I slot print_timing: id 2 | task 27617 | prompt eval time = 3998.19 ms / 779 tokens ( 5.13 ms per token, 194.84 tokens per second) 22.09.214.909 I slot print_timing: id 2 | task 27617 | eval time = 40.81 ms / 2 tokens ( 40.81 ms per token, 24.50 tokens per second) 22.09.214.909 I slot print_timing: id 2 | task 27617 | total time = 4039.00 ms / 781 tokens 22.09.214.909 I slot print_timing: id 2 | task 27617 | graphs reused = 26354 22.09.214.910 I slot print_timing: id 2 | task 27617 | graph reallocs = 0 / 0 (same size) / (changed size) 22.09.214.949 I slot release: id 2 | task 27617 | stop processing: n_tokens = 780, truncated = 0 22.09.215.250 I slot print_timing: id 3 | task 27614 | prompt eval time = 3998.64 ms / 564 tokens ( 7.09 ms per token, 141.05 tokens per second) 22.09.215.252 I slot print_timing: id 3 | task 27614 | eval time = 40.64 ms / 2 tokens ( 40.64 ms per token, 24.61 tokens per second) 22.09.215.252 I slot print_timing: id 3 | task 27614 | total time = 4039.28 ms / 566 tokens 22.09.215.253 I slot print_timing: id 3 | task 27614 | graphs reused = 26354 22.09.215.253 I slot print_timing: id 3 | task 27614 | graph reallocs = 0 / 0 (same size) / (changed size) 22.09.215.285 I slot release: id 3 | task 27614 | stop processing: n_tokens = 819, truncated = 0 22.09.221.590 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 757, t_last = 339036111415 22.09.223.256 I slot launch_slot_: id 0 | task 27623 | processing task, is_child = 0 22.09.227.528 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 751, t_last = 339036111716 22.09.227.591 I slot launch_slot_: id 1 | task 27622 | processing task, is_child = 0 22.09.227.671 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 780, t_last = 339036112054 22.09.227.728 I slot launch_slot_: id 2 | task 27625 | processing task, is_child = 0 22.09.227.770 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 819, t_last = 339036112390 22.09.227.828 I slot launch_slot_: id 3 | task 27624 | processing task, is_child = 0 22.13.142.760 I slot print_timing: id 0 | task 27623 | prompt processing, n_tokens = 881, progress = 1.00, t = 3.91 s / 225.04 tokens per second 22.13.788.982 I slot print_timing: id 1 | task 27622 | prompt processing, n_tokens = 877, progress = 1.00, t = 3.91 s / 224.02 tokens per second 22.13.789.138 I slot print_timing: id 2 | task 27625 | prompt processing, n_tokens = 893, progress = 1.00, t = 3.91 s / 228.11 tokens per second 22.13.789.287 I slot print_timing: id 3 | task 27624 | prompt processing, n_tokens = 899, progress = 1.00, t = 3.91 s / 229.64 tokens per second 22.13.935.062 I slot print_timing: id 0 | task 27623 | prompt eval time = 4666.45 ms / 885 tokens ( 5.27 ms per token, 189.65 tokens per second) 22.13.935.064 I slot print_timing: id 0 | task 27623 | eval time = 40.77 ms / 2 tokens ( 40.77 ms per token, 24.53 tokens per second) 22.13.935.066 I slot print_timing: id 0 | task 27623 | total time = 4707.22 ms / 887 tokens 22.13.935.066 I slot print_timing: id 0 | task 27623 | graphs reused = 26356 22.13.935.067 I slot print_timing: id 0 | task 27623 | graph reallocs = 0 / 0 (same size) / (changed size) 22.13.935.123 I slot release: id 0 | task 27623 | stop processing: n_tokens = 886, truncated = 0 22.13.935.388 I slot print_timing: id 1 | task 27622 | prompt eval time = 4666.77 ms / 881 tokens ( 5.30 ms per token, 188.78 tokens per second) 22.13.935.390 I slot print_timing: id 1 | task 27622 | eval time = 40.73 ms / 2 tokens ( 40.73 ms per token, 24.55 tokens per second) 22.13.935.391 I slot print_timing: id 1 | task 27622 | total time = 4707.50 ms / 883 tokens 22.13.935.391 I slot print_timing: id 1 | task 27622 | graphs reused = 26356 22.13.935.391 I slot print_timing: id 1 | task 27622 | graph reallocs = 0 / 0 (same size) / (changed size) 22.13.935.424 I slot release: id 1 | task 27622 | stop processing: n_tokens = 882, truncated = 0 22.13.935.678 I slot print_timing: id 2 | task 27625 | prompt eval time = 4667.02 ms / 897 tokens ( 5.20 ms per token, 192.20 tokens per second) 22.13.935.680 I slot print_timing: id 2 | task 27625 | eval time = 40.72 ms / 2 tokens ( 40.72 ms per token, 24.56 tokens per second) 22.13.935.680 I slot print_timing: id 2 | task 27625 | total time = 4707.74 ms / 899 tokens 22.13.935.680 I slot print_timing: id 2 | task 27625 | graphs reused = 26356 22.13.935.681 I slot print_timing: id 2 | task 27625 | graph reallocs = 0 / 0 (same size) / (changed size) 22.13.935.715 I slot release: id 2 | task 27625 | stop processing: n_tokens = 898, truncated = 0 22.13.936.008 I slot print_timing: id 3 | task 27624 | prompt eval time = 4667.31 ms / 903 tokens ( 5.17 ms per token, 193.47 tokens per second) 22.13.936.014 I slot print_timing: id 3 | task 27624 | eval time = 40.72 ms / 2 tokens ( 40.72 ms per token, 24.56 tokens per second) 22.13.936.014 I slot print_timing: id 3 | task 27624 | total time = 4708.02 ms / 905 tokens 22.13.936.014 I slot print_timing: id 3 | task 27624 | graphs reused = 26356 22.13.936.014 I slot print_timing: id 3 | task 27624 | graph reallocs = 0 / 0 (same size) / (changed size) 22.13.936.051 I slot release: id 3 | task 27624 | stop processing: n_tokens = 904, truncated = 0 22.13.942.959 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 886, t_last = 339040832228 22.13.944.720 I slot launch_slot_: id 0 | task 27630 | processing task, is_child = 0 22.13.949.782 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 882, t_last = 339040832529 22.13.949.849 I slot launch_slot_: id 1 | task 27631 | processing task, is_child = 0 22.13.949.937 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 898, t_last = 339040832820 22.13.949.998 I slot launch_slot_: id 2 | task 27632 | processing task, is_child = 0 22.13.950.045 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.895 (> 0.100 thold), f_keep = 0.889 22.13.950.059 I slot launch_slot_: id 3 | task 27633 | processing task, is_child = 0 22.18.129.501 I slot print_timing: id 0 | task 27630 | prompt processing, n_tokens = 773, progress = 0.99, t = 4.18 s / 184.97 tokens per second 22.18.129.658 I slot print_timing: id 1 | task 27631 | prompt processing, n_tokens = 773, progress = 0.99, t = 4.18 s / 184.97 tokens per second 22.18.129.791 I slot print_timing: id 2 | task 27632 | prompt processing, n_tokens = 941, progress = 1.00, t = 4.18 s / 225.17 tokens per second 22.18.227.225 I slot print_timing: id 3 | task 27633 | prompt eval time = 4179.25 ms / 511 tokens ( 8.18 ms per token, 122.27 tokens per second) 22.18.227.228 I slot print_timing: id 3 | task 27633 | eval time = 97.74 ms / 2 tokens ( 97.74 ms per token, 10.23 tokens per second) 22.18.227.229 I slot print_timing: id 3 | task 27633 | total time = 4276.99 ms / 513 tokens 22.18.227.229 I slot print_timing: id 3 | task 27633 | graphs reused = 26356 22.18.227.230 I slot print_timing: id 3 | task 27633 | graph reallocs = 0 / 0 (same size) / (changed size) 22.18.227.319 I slot release: id 3 | task 27633 | stop processing: n_tokens = 899, truncated = 0 22.18.259.806 I slot print_timing: id 0 | task 27630 | prompt eval time = 4276.25 ms / 777 tokens ( 5.50 ms per token, 181.70 tokens per second) 22.18.259.808 I slot print_timing: id 0 | task 27630 | eval time = 33.49 ms / 2 tokens ( 33.49 ms per token, 29.86 tokens per second) 22.18.259.809 I slot print_timing: id 0 | task 27630 | total time = 4309.74 ms / 779 tokens 22.18.259.809 I slot print_timing: id 0 | task 27630 | graphs reused = 26356 22.18.259.809 I slot print_timing: id 0 | task 27630 | graph reallocs = 0 / 0 (same size) / (changed size) 22.18.259.854 I slot release: id 0 | task 27630 | stop processing: n_tokens = 778, truncated = 0 22.18.260.130 I slot print_timing: id 1 | task 27631 | prompt eval time = 4276.52 ms / 777 tokens ( 5.50 ms per token, 181.69 tokens per second) 22.18.260.132 I slot print_timing: id 1 | task 27631 | eval time = 33.49 ms / 2 tokens ( 33.49 ms per token, 29.86 tokens per second) 22.18.260.133 I slot print_timing: id 1 | task 27631 | total time = 4310.01 ms / 779 tokens 22.18.260.133 I slot print_timing: id 1 | task 27631 | graphs reused = 26356 22.18.260.133 I slot print_timing: id 1 | task 27631 | graph reallocs = 0 / 0 (same size) / (changed size) 22.18.260.170 I slot release: id 1 | task 27631 | stop processing: n_tokens = 778, truncated = 0 22.18.260.439 I slot print_timing: id 2 | task 27632 | prompt eval time = 4276.74 ms / 945 tokens ( 4.53 ms per token, 220.96 tokens per second) 22.18.260.447 I slot print_timing: id 2 | task 27632 | eval time = 33.53 ms / 2 tokens ( 33.53 ms per token, 29.83 tokens per second) 22.18.260.448 I slot print_timing: id 2 | task 27632 | total time = 4310.26 ms / 947 tokens 22.18.260.448 I slot print_timing: id 2 | task 27632 | graphs reused = 26356 22.18.260.448 I slot print_timing: id 2 | task 27632 | graph reallocs = 0 / 0 (same size) / (changed size) 22.18.260.491 I slot release: id 2 | task 27632 | stop processing: n_tokens = 946, truncated = 0 22.18.260.495 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.893 (> 0.100 thold), f_keep = 0.871 22.18.260.523 I slot launch_slot_: id 2 | task 27638 | processing task, is_child = 0 22.18.269.109 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 899, t_last = 339045124425 22.18.269.188 I slot launch_slot_: id 3 | task 27640 | processing task, is_child = 0 22.18.269.274 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 778, t_last = 339045156959 22.18.269.336 I slot launch_slot_: id 0 | task 27641 | processing task, is_child = 0 22.18.269.378 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 778, t_last = 339045157275 22.18.269.441 I slot launch_slot_: id 1 | task 27642 | processing task, is_child = 0 22.22.628.042 I slot print_timing: id 2 | task 27638 | prompt eval time = 2404.47 ms / 494 tokens ( 4.87 ms per token, 205.45 tokens per second) 22.22.628.045 I slot print_timing: id 2 | task 27638 | eval time = 1958.03 ms / 2 tokens ( 1958.03 ms per token, 0.51 tokens per second) 22.22.628.045 I slot print_timing: id 2 | task 27638 | total time = 4362.50 ms / 496 tokens 22.22.628.046 I slot print_timing: id 2 | task 27638 | graphs reused = 26356 22.22.628.046 I slot print_timing: id 2 | task 27638 | graph reallocs = 0 / 0 (same size) / (changed size) 22.22.628.099 I slot release: id 2 | task 27638 | stop processing: n_tokens = 924, truncated = 0 22.22.628.111 I slot print_timing: id 0 | task 27641 | prompt processing, n_tokens = 876, progress = 1.00, t = 4.36 s / 201.00 tokens per second 22.22.628.296 I slot print_timing: id 1 | task 27642 | prompt processing, n_tokens = 908, progress = 1.00, t = 4.36 s / 208.34 tokens per second 22.22.628.491 I slot print_timing: id 3 | task 27640 | prompt processing, n_tokens = 925, progress = 1.00, t = 3.73 s / 247.99 tokens per second 22.22.718.199 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 924, t_last = 339049525204 22.22.721.279 I slot launch_slot_: id 2 | task 27646 | processing task, is_child = 0 22.23.267.163 I slot print_timing: id 0 | task 27641 | prompt eval time = 4448.07 ms / 880 tokens ( 5.05 ms per token, 197.84 tokens per second) 22.23.267.165 I slot print_timing: id 0 | task 27641 | eval time = 549.64 ms / 2 tokens ( 549.64 ms per token, 1.82 tokens per second) 22.23.267.165 I slot print_timing: id 0 | task 27641 | total time = 4997.71 ms / 882 tokens 22.23.267.166 I slot print_timing: id 0 | task 27641 | graphs reused = 26356 22.23.267.166 I slot print_timing: id 0 | task 27641 | graph reallocs = 0 / 0 (same size) / (changed size) 22.23.267.217 I slot release: id 0 | task 27641 | stop processing: n_tokens = 881, truncated = 0 22.23.267.500 I slot print_timing: id 1 | task 27642 | prompt eval time = 4448.32 ms / 912 tokens ( 4.88 ms per token, 205.02 tokens per second) 22.23.267.502 I slot print_timing: id 1 | task 27642 | eval time = 549.68 ms / 2 tokens ( 549.68 ms per token, 1.82 tokens per second) 22.23.267.503 I slot print_timing: id 1 | task 27642 | total time = 4997.99 ms / 914 tokens 22.23.267.503 I slot print_timing: id 1 | task 27642 | graphs reused = 26356 22.23.267.503 I slot print_timing: id 1 | task 27642 | graph reallocs = 0 / 0 (same size) / (changed size) 22.23.267.545 I slot release: id 1 | task 27642 | stop processing: n_tokens = 913, truncated = 0 22.23.267.818 I slot print_timing: id 3 | task 27640 | prompt eval time = 3820.42 ms / 929 tokens ( 4.11 ms per token, 243.17 tokens per second) 22.23.267.820 I slot print_timing: id 3 | task 27640 | eval time = 549.62 ms / 2 tokens ( 549.62 ms per token, 1.82 tokens per second) 22.23.267.820 I slot print_timing: id 3 | task 27640 | total time = 4370.04 ms / 931 tokens 22.23.267.821 I slot print_timing: id 3 | task 27640 | graphs reused = 26356 22.23.267.821 I slot print_timing: id 3 | task 27640 | graph reallocs = 0 / 0 (same size) / (changed size) 22.23.267.878 I slot release: id 3 | task 27640 | stop processing: n_tokens = 930, truncated = 0 22.23.949.858 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.894 22.23.949.887 I slot launch_slot_: id 0 | task 27650 | processing task, is_child = 0 22.23.954.712 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 22.23.954.734 I slot launch_slot_: id 1 | task 27651 | processing task, is_child = 0 22.23.954.781 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 930, t_last = 339050164983 22.23.954.849 I slot launch_slot_: id 3 | task 27652 | processing task, is_child = 0 22.26.264.586 I slot print_timing: id 2 | task 27646 | prompt eval time = 1228.56 ms / 884 tokens ( 1.39 ms per token, 719.54 tokens per second) 22.26.264.589 I slot print_timing: id 2 | task 27646 | eval time = 2314.73 ms / 2 tokens ( 2314.73 ms per token, 0.43 tokens per second) 22.26.264.589 I slot print_timing: id 2 | task 27646 | total time = 3543.29 ms / 886 tokens 22.26.264.590 I slot print_timing: id 2 | task 27646 | graphs reused = 26356 22.26.264.590 I slot print_timing: id 2 | task 27646 | graph reallocs = 0 / 0 (same size) / (changed size) 22.26.264.647 I slot release: id 2 | task 27646 | stop processing: n_tokens = 885, truncated = 0 22.26.970.837 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 885, t_last = 339053161752 22.26.973.748 I slot launch_slot_: id 2 | task 27655 | processing task, is_child = 0 22.26.973.848 I slot print_timing: id 3 | task 27652 | prompt processing, n_tokens = 1168, progress = 1.00, t = 3.02 s / 387.38 tokens per second 22.27.990.707 I slot print_timing: id 0 | task 27650 | prompt eval time = 3015.68 ms / 506 tokens ( 5.96 ms per token, 167.79 tokens per second) 22.27.990.711 I slot print_timing: id 0 | task 27650 | eval time = 1020.16 ms / 2 tokens ( 1020.16 ms per token, 0.98 tokens per second) 22.27.990.711 I slot print_timing: id 0 | task 27650 | total time = 4035.85 ms / 508 tokens 22.27.990.712 I slot print_timing: id 0 | task 27650 | graphs reused = 26356 22.27.990.712 I slot print_timing: id 0 | task 27650 | graph reallocs = 0 / 0 (same size) / (changed size) 22.27.990.764 I slot release: id 0 | task 27650 | stop processing: n_tokens = 871, truncated = 0 22.27.991.049 I slot print_timing: id 1 | task 27651 | prompt eval time = 3015.84 ms / 486 tokens ( 6.21 ms per token, 161.15 tokens per second) 22.27.991.054 I slot print_timing: id 1 | task 27651 | eval time = 1020.22 ms / 2 tokens ( 1020.22 ms per token, 0.98 tokens per second) 22.27.991.055 I slot print_timing: id 1 | task 27651 | total time = 4036.06 ms / 488 tokens 22.27.991.055 I slot print_timing: id 1 | task 27651 | graphs reused = 26356 22.27.991.055 I slot print_timing: id 1 | task 27651 | graph reallocs = 0 / 0 (same size) / (changed size) 22.27.991.099 I slot release: id 1 | task 27651 | stop processing: n_tokens = 883, truncated = 0 22.28.654.825 I slot print_timing: id 3 | task 27652 | prompt eval time = 4036.30 ms / 1172 tokens ( 3.44 ms per token, 290.36 tokens per second) 22.28.654.827 I slot print_timing: id 3 | task 27652 | eval time = 663.41 ms / 2 tokens ( 663.41 ms per token, 1.51 tokens per second) 22.28.654.828 I slot print_timing: id 3 | task 27652 | total time = 4699.71 ms / 1174 tokens 22.28.654.828 I slot print_timing: id 3 | task 27652 | graphs reused = 26356 22.28.654.829 I slot print_timing: id 3 | task 27652 | graph reallocs = 0 / 0 (same size) / (changed size) 22.28.654.889 I slot release: id 3 | task 27652 | stop processing: n_tokens = 1173, truncated = 0 22.28.654.896 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.835 (> 0.100 thold), f_keep = 0.883 22.28.654.925 I slot launch_slot_: id 3 | task 27658 | processing task, is_child = 0 22.28.659.823 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 871, t_last = 339054887869 22.28.659.901 I slot launch_slot_: id 0 | task 27659 | processing task, is_child = 0 22.30.606.519 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 883, t_last = 339054888204 22.30.606.657 I slot launch_slot_: id 1 | task 27661 | processing task, is_child = 0 22.34.248.586 I slot print_timing: id 0 | task 27659 | prompt processing, n_tokens = 2076, progress = 0.80, t = 5.59 s / 371.49 tokens per second 22.34.248.636 I slot print_timing: id 1 | task 27661 | prompt processing, n_tokens = 1983, progress = 0.79, t = 3.64 s / 544.54 tokens per second 22.35.788.344 I slot print_timing: id 2 | task 27655 | prompt eval time = 7274.80 ms / 1179 tokens ( 6.17 ms per token, 162.07 tokens per second) 22.35.788.347 I slot print_timing: id 2 | task 27655 | eval time = 1539.78 ms / 2 tokens ( 1539.78 ms per token, 0.65 tokens per second) 22.35.788.348 I slot print_timing: id 2 | task 27655 | total time = 8814.57 ms / 1181 tokens 22.35.788.348 I slot print_timing: id 2 | task 27655 | graphs reused = 26356 22.35.788.349 I slot print_timing: id 2 | task 27655 | graph reallocs = 0 / 0 (same size) / (changed size) 22.35.788.417 I slot release: id 2 | task 27655 | stop processing: n_tokens = 1180, truncated = 0 22.35.788.431 I slot print_timing: id 0 | task 27659 | prompt processing, n_tokens = 2588, progress = 1.00, t = 7.13 s / 363.07 tokens per second 22.35.788.792 I slot print_timing: id 1 | task 27661 | prompt processing, n_tokens = 2495, progress = 1.00, t = 5.18 s / 481.53 tokens per second 22.35.789.156 I slot print_timing: id 3 | task 27658 | prompt processing, n_tokens = 68, progress = 0.58, t = 4.52 s / 15.05 tokens per second 22.36.496.295 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1180, t_last = 339062685523 22.36.499.921 I slot launch_slot_: id 2 | task 27665 | processing task, is_child = 0 22.39.143.229 I slot print_timing: id 0 | task 27659 | prompt eval time = 7835.94 ms / 2592 tokens ( 3.02 ms per token, 330.78 tokens per second) 22.39.143.232 I slot print_timing: id 0 | task 27659 | eval time = 2647.33 ms / 2 tokens ( 2647.33 ms per token, 0.38 tokens per second) 22.39.143.232 I slot print_timing: id 0 | task 27659 | total time = 10483.27 ms / 2594 tokens 22.39.143.232 I slot print_timing: id 0 | task 27659 | graphs reused = 26356 22.39.143.233 I slot print_timing: id 0 | task 27659 | graph reallocs = 0 / 0 (same size) / (changed size) 22.39.143.361 I slot release: id 0 | task 27659 | stop processing: n_tokens = 2593, truncated = 0 22.39.143.636 I slot print_timing: id 1 | task 27661 | prompt eval time = 5889.62 ms / 2499 tokens ( 2.36 ms per token, 424.31 tokens per second) 22.39.143.638 I slot print_timing: id 1 | task 27661 | eval time = 2647.34 ms / 2 tokens ( 2647.34 ms per token, 0.38 tokens per second) 22.39.143.639 I slot print_timing: id 1 | task 27661 | total time = 8536.96 ms / 2501 tokens 22.39.143.639 I slot print_timing: id 1 | task 27661 | graphs reused = 26356 22.39.143.639 I slot print_timing: id 1 | task 27661 | graph reallocs = 0 / 0 (same size) / (changed size) 22.39.143.736 I slot release: id 1 | task 27661 | stop processing: n_tokens = 2500, truncated = 0 22.39.143.765 I slot print_timing: id 3 | task 27658 | prompt processing, n_tokens = 580, progress = 1.00, t = 5.23 s / 110.96 tokens per second 22.39.527.330 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.880 (> 0.100 thold), f_keep = 0.896 22.39.527.361 I slot launch_slot_: id 0 | task 27668 | processing task, is_child = 0 22.39.534.319 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 2500, t_last = 339066040842 22.39.534.452 I slot launch_slot_: id 1 | task 27669 | processing task, is_child = 0 22.39.534.724 I slot print_timing: id 2 | task 27665 | prompt processing, n_tokens = 2230, progress = 0.81, t = 3.03 s / 736.69 tokens per second 22.42.090.838 I slot print_timing: id 3 | task 27658 | prompt eval time = 8258.99 ms / 584 tokens ( 14.14 ms per token, 70.71 tokens per second) 22.42.090.840 I slot print_timing: id 3 | task 27658 | eval time = 2563.51 ms / 2 tokens ( 2563.51 ms per token, 0.39 tokens per second) 22.42.090.841 I slot print_timing: id 3 | task 27658 | total time = 10822.50 ms / 586 tokens 22.42.090.841 I slot print_timing: id 3 | task 27658 | graphs reused = 26356 22.42.090.842 I slot print_timing: id 3 | task 27658 | graph reallocs = 0 / 0 (same size) / (changed size) 22.42.090.908 I slot release: id 3 | task 27658 | stop processing: n_tokens = 1241, truncated = 0 22.42.091.006 I slot print_timing: id 2 | task 27665 | prompt processing, n_tokens = 2742, progress = 1.00, t = 5.59 s / 490.46 tokens per second 22.43.501.958 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1241, t_last = 339068988013 22.43.505.938 I slot launch_slot_: id 3 | task 27672 | processing task, is_child = 0 22.43.505.960 I slot print_timing: id 0 | task 27668 | prompt processing, n_tokens = 562, progress = 1.00, t = 3.97 s / 141.66 tokens per second 22.43.506.391 I slot print_timing: id 1 | task 27669 | prompt processing, n_tokens = 1755, progress = 1.00, t = 3.97 s / 442.39 tokens per second 22.45.287.090 I slot print_timing: id 2 | task 27665 | prompt eval time = 7002.02 ms / 2746 tokens ( 2.55 ms per token, 392.17 tokens per second) 22.45.287.095 I slot print_timing: id 2 | task 27665 | eval time = 1785.13 ms / 2 tokens ( 1785.13 ms per token, 0.56 tokens per second) 22.45.287.096 I slot print_timing: id 2 | task 27665 | total time = 8787.15 ms / 2748 tokens 22.45.287.097 I slot print_timing: id 2 | task 27665 | graphs reused = 26356 22.45.287.097 I slot print_timing: id 2 | task 27665 | graph reallocs = 0 / 0 (same size) / (changed size) 22.45.287.266 I slot release: id 2 | task 27665 | stop processing: n_tokens = 2747, truncated = 0 22.45.971.198 I slot print_timing: id 0 | task 27668 | prompt eval time = 5751.98 ms / 566 tokens ( 10.16 ms per token, 98.40 tokens per second) 22.45.971.202 I slot print_timing: id 0 | task 27668 | eval time = 684.75 ms / 2 tokens ( 684.75 ms per token, 1.46 tokens per second) 22.45.971.202 I slot print_timing: id 0 | task 27668 | total time = 6436.73 ms / 568 tokens 22.45.971.203 I slot print_timing: id 0 | task 27668 | graphs reused = 26356 22.45.971.203 I slot print_timing: id 0 | task 27668 | graph reallocs = 0 / 0 (same size) / (changed size) 22.45.971.333 I slot release: id 0 | task 27668 | stop processing: n_tokens = 2643, truncated = 0 22.45.971.633 I slot print_timing: id 1 | task 27669 | prompt eval time = 5752.26 ms / 1759 tokens ( 3.27 ms per token, 305.79 tokens per second) 22.45.971.635 I slot print_timing: id 1 | task 27669 | eval time = 684.82 ms / 2 tokens ( 684.82 ms per token, 1.46 tokens per second) 22.45.971.636 I slot print_timing: id 1 | task 27669 | total time = 6437.08 ms / 1761 tokens 22.45.971.636 I slot print_timing: id 1 | task 27669 | graphs reused = 26356 22.45.971.637 I slot print_timing: id 1 | task 27669 | graph reallocs = 0 / 0 (same size) / (changed size) 22.45.971.732 I slot release: id 1 | task 27669 | stop processing: n_tokens = 1760, truncated = 0 22.45.971.740 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.728 (> 0.100 thold), f_keep = 0.830 22.45.971.789 I slot launch_slot_: id 1 | task 27675 | processing task, is_child = 0 22.45.982.971 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 2747, t_last = 339072184372 22.45.983.114 I slot launch_slot_: id 2 | task 27676 | processing task, is_child = 0 22.45.983.219 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 2643, t_last = 339072868439 22.45.983.342 I slot launch_slot_: id 0 | task 27677 | processing task, is_child = 0 22.51.547.762 I slot print_timing: id 0 | task 27677 | prompt processing, n_tokens = 1904, progress = 1.00, t = 5.56 s / 342.20 tokens per second 22.51.548.049 I slot print_timing: id 1 | task 27675 | prompt processing, n_tokens = 758, progress = 1.00, t = 5.56 s / 136.24 tokens per second 22.51.548.336 I slot print_timing: id 2 | task 27676 | prompt processing, n_tokens = 1313, progress = 0.72, t = 5.56 s / 235.99 tokens per second 22.52.301.977 I slot print_timing: id 3 | task 27672 | prompt eval time = 8041.06 ms / 1811 tokens ( 4.44 ms per token, 225.22 tokens per second) 22.52.301.980 I slot print_timing: id 3 | task 27672 | eval time = 754.24 ms / 2 tokens ( 754.24 ms per token, 1.33 tokens per second) 22.52.301.980 I slot print_timing: id 3 | task 27672 | total time = 8795.30 ms / 1813 tokens 22.52.301.981 I slot print_timing: id 3 | task 27672 | graphs reused = 26356 22.52.301.981 I slot print_timing: id 3 | task 27672 | graph reallocs = 0 / 0 (same size) / (changed size) 22.52.302.083 I slot release: id 3 | task 27672 | stop processing: n_tokens = 1812, truncated = 0 22.52.302.096 I slot print_timing: id 2 | task 27676 | prompt processing, n_tokens = 1825, progress = 1.00, t = 6.32 s / 288.88 tokens per second 22.52.363.374 I slot print_timing: id 0 | task 27677 | prompt eval time = 6318.01 ms / 1908 tokens ( 3.31 ms per token, 301.99 tokens per second) 22.52.363.376 I slot print_timing: id 0 | task 27677 | eval time = 62.01 ms / 2 tokens ( 62.01 ms per token, 16.13 tokens per second) 22.52.363.377 I slot print_timing: id 0 | task 27677 | total time = 6380.02 ms / 1910 tokens 22.52.363.377 I slot print_timing: id 0 | task 27677 | graphs reused = 26356 22.52.363.378 I slot print_timing: id 0 | task 27677 | graph reallocs = 0 / 0 (same size) / (changed size) 22.52.363.479 I slot release: id 0 | task 27677 | stop processing: n_tokens = 1909, truncated = 0 22.52.363.777 I slot print_timing: id 1 | task 27675 | prompt eval time = 6318.16 ms / 762 tokens ( 8.29 ms per token, 120.60 tokens per second) 22.52.363.780 I slot print_timing: id 1 | task 27675 | eval time = 62.09 ms / 2 tokens ( 62.09 ms per token, 16.11 tokens per second) 22.52.363.780 I slot print_timing: id 1 | task 27675 | total time = 6380.25 ms / 764 tokens 22.52.363.780 I slot print_timing: id 1 | task 27675 | graphs reused = 26356 22.52.363.781 I slot print_timing: id 1 | task 27675 | graph reallocs = 0 / 0 (same size) / (changed size) 22.52.363.867 I slot release: id 1 | task 27675 | stop processing: n_tokens = 2006, truncated = 0 22.52.364.295 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.836 (> 0.100 thold), f_keep = 0.765 22.52.364.336 I slot launch_slot_: id 0 | task 27682 | processing task, is_child = 0 22.52.371.554 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1812, t_last = 339079199190 22.52.371.665 I slot launch_slot_: id 3 | task 27683 | processing task, is_child = 0 22.52.371.748 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 2006, t_last = 339079260973 22.52.371.848 I slot launch_slot_: id 1 | task 27684 | processing task, is_child = 0 22.53.601.391 I slot print_timing: id 2 | task 27676 | prompt eval time = 6380.67 ms / 1829 tokens ( 3.49 ms per token, 286.65 tokens per second) 22.53.601.393 I slot print_timing: id 2 | task 27676 | eval time = 1237.11 ms / 2 tokens ( 1237.11 ms per token, 0.81 tokens per second) 22.53.601.393 I slot print_timing: id 2 | task 27676 | total time = 7617.78 ms / 1831 tokens 22.53.601.394 I slot print_timing: id 2 | task 27676 | graphs reused = 26356 22.53.601.394 I slot print_timing: id 2 | task 27676 | graph reallocs = 0 / 0 (same size) / (changed size) 22.53.601.507 I slot release: id 2 | task 27676 | stop processing: n_tokens = 1830, truncated = 0 22.54.941.834 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1830, t_last = 339080498612 22.54.947.615 I slot launch_slot_: id 2 | task 27687 | processing task, is_child = 0 22.55.408.715 I slot print_timing: id 0 | task 27682 | prompt eval time = 2569.98 ms / 355 tokens ( 7.24 ms per token, 138.13 tokens per second) 22.55.408.716 I slot print_timing: id 0 | task 27682 | eval time = 466.88 ms / 2 tokens ( 466.88 ms per token, 2.14 tokens per second) 22.55.408.717 I slot print_timing: id 0 | task 27682 | total time = 3036.86 ms / 357 tokens 22.55.408.718 I slot print_timing: id 0 | task 27682 | graphs reused = 26356 22.55.408.718 I slot print_timing: id 0 | task 27682 | graph reallocs = 0 / 0 (same size) / (changed size) 22.55.408.820 I slot release: id 0 | task 27682 | stop processing: n_tokens = 1748, truncated = 0 22.56.089.531 I slot print_timing: id 1 | task 27684 | prompt eval time = 3037.15 ms / 733 tokens ( 4.14 ms per token, 241.34 tokens per second) 22.56.089.533 I slot print_timing: id 1 | task 27684 | eval time = 680.40 ms / 2 tokens ( 680.40 ms per token, 1.47 tokens per second) 22.56.089.533 I slot print_timing: id 1 | task 27684 | total time = 3717.55 ms / 735 tokens 22.56.089.534 I slot print_timing: id 1 | task 27684 | graphs reused = 26356 22.56.089.534 I slot print_timing: id 1 | task 27684 | graph reallocs = 0 / 0 (same size) / (changed size) 22.56.089.578 I slot release: id 1 | task 27684 | stop processing: n_tokens = 734, truncated = 0 22.56.089.890 I slot print_timing: id 3 | task 27683 | prompt eval time = 3037.31 ms / 711 tokens ( 4.27 ms per token, 234.09 tokens per second) 22.56.089.892 I slot print_timing: id 3 | task 27683 | eval time = 680.46 ms / 2 tokens ( 680.46 ms per token, 1.47 tokens per second) 22.56.089.892 I slot print_timing: id 3 | task 27683 | total time = 3717.77 ms / 713 tokens 22.56.089.893 I slot print_timing: id 3 | task 27683 | graphs reused = 26356 22.56.089.893 I slot print_timing: id 3 | task 27683 | graph reallocs = 0 / 0 (same size) / (changed size) 22.56.089.926 I slot release: id 3 | task 27683 | stop processing: n_tokens = 712, truncated = 0 22.56.089.931 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.883 (> 0.100 thold), f_keep = 0.854 22.56.089.959 I slot launch_slot_: id 1 | task 27690 | processing task, is_child = 0 22.56.096.942 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.864 (> 0.100 thold), f_keep = 0.881 22.56.096.964 I slot launch_slot_: id 3 | task 27691 | processing task, is_child = 0 22.56.097.044 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1748, t_last = 339082305926 22.56.097.135 I slot launch_slot_: id 0 | task 27692 | processing task, is_child = 0 22.58.772.571 I slot print_timing: id 2 | task 27687 | prompt eval time = 2461.61 ms / 744 tokens ( 3.31 ms per token, 302.24 tokens per second) 22.58.772.574 I slot print_timing: id 2 | task 27687 | eval time = 1363.20 ms / 2 tokens ( 1363.20 ms per token, 0.73 tokens per second) 22.58.772.574 I slot print_timing: id 2 | task 27687 | total time = 3824.81 ms / 746 tokens 22.58.772.575 I slot print_timing: id 2 | task 27687 | graphs reused = 26356 22.58.772.575 I slot print_timing: id 2 | task 27687 | graph reallocs = 0 / 0 (same size) / (changed size) 22.58.772.631 I slot release: id 2 | task 27687 | stop processing: n_tokens = 745, truncated = 0 22.58.855.184 I slot print_timing: id 1 | task 27690 | prompt eval time = 2675.02 ms / 493 tokens ( 5.43 ms per token, 184.30 tokens per second) 22.58.855.186 I slot print_timing: id 1 | task 27690 | eval time = 82.89 ms / 2 tokens ( 82.89 ms per token, 12.06 tokens per second) 22.58.855.188 I slot print_timing: id 1 | task 27690 | total time = 2757.90 ms / 495 tokens 22.58.855.188 I slot print_timing: id 1 | task 27690 | graphs reused = 26356 22.58.855.188 I slot print_timing: id 1 | task 27690 | graph reallocs = 0 / 0 (same size) / (changed size) 22.58.855.233 I slot release: id 1 | task 27690 | stop processing: n_tokens = 711, truncated = 0 22.58.855.638 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 745, t_last = 339085669736 22.58.857.360 I slot launch_slot_: id 2 | task 27696 | processing task, is_child = 0 22.59.600.122 I slot print_timing: id 0 | task 27692 | prompt eval time = 2757.76 ms / 789 tokens ( 3.50 ms per token, 286.10 tokens per second) 22.59.600.126 I slot print_timing: id 0 | task 27692 | eval time = 745.22 ms / 2 tokens ( 745.22 ms per token, 1.34 tokens per second) 22.59.600.127 I slot print_timing: id 0 | task 27692 | total time = 3502.98 ms / 791 tokens 22.59.600.127 I slot print_timing: id 0 | task 27692 | graphs reused = 26356 22.59.600.128 I slot print_timing: id 0 | task 27692 | graph reallocs = 0 / 0 (same size) / (changed size) 22.59.600.172 I slot release: id 0 | task 27692 | stop processing: n_tokens = 790, truncated = 0 22.59.600.455 I slot print_timing: id 3 | task 27691 | prompt eval time = 2758.12 ms / 531 tokens ( 5.19 ms per token, 192.52 tokens per second) 22.59.600.457 I slot print_timing: id 3 | task 27691 | eval time = 744.82 ms / 2 tokens ( 744.82 ms per token, 1.34 tokens per second) 22.59.600.457 I slot print_timing: id 3 | task 27691 | total time = 3502.94 ms / 533 tokens 22.59.600.458 I slot print_timing: id 3 | task 27691 | graphs reused = 26356 22.59.600.458 I slot print_timing: id 3 | task 27691 | graph reallocs = 0 / 0 (same size) / (changed size) 22.59.600.499 I slot release: id 3 | task 27691 | stop processing: n_tokens = 727, truncated = 0 22.59.600.503 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 711, t_last = 339085752338 22.59.600.598 I slot launch_slot_: id 1 | task 27698 | processing task, is_child = 0 23.00.389.239 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 790, t_last = 339086497277 23.00.389.338 I slot launch_slot_: id 0 | task 27700 | processing task, is_child = 0 23.00.389.383 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 727, t_last = 339086497604 23.00.389.445 I slot launch_slot_: id 3 | task 27701 | processing task, is_child = 0 23.03.873.683 I slot print_timing: id 2 | task 27696 | prompt eval time = 3653.51 ms / 1040 tokens ( 3.51 ms per token, 284.66 tokens per second) 23.03.873.685 I slot print_timing: id 2 | task 27696 | eval time = 1361.38 ms / 2 tokens ( 1361.38 ms per token, 0.73 tokens per second) 23.03.873.685 I slot print_timing: id 2 | task 27696 | total time = 5014.88 ms / 1042 tokens 23.03.873.686 I slot print_timing: id 2 | task 27696 | graphs reused = 26356 23.03.873.686 I slot print_timing: id 2 | task 27696 | graph reallocs = 0 / 0 (same size) / (changed size) 23.03.873.750 I slot release: id 2 | task 27696 | stop processing: n_tokens = 1041, truncated = 0 23.03.873.763 I slot print_timing: id 0 | task 27700 | prompt processing, n_tokens = 827, progress = 1.00, t = 3.48 s / 237.40 tokens per second 23.03.873.913 I slot print_timing: id 3 | task 27701 | prompt processing, n_tokens = 772, progress = 0.99, t = 3.10 s / 249.00 tokens per second 23.03.956.072 I slot print_timing: id 1 | task 27698 | prompt eval time = 4268.29 ms / 784 tokens ( 5.44 ms per token, 183.68 tokens per second) 23.03.956.075 I slot print_timing: id 1 | task 27698 | eval time = 82.69 ms / 2 tokens ( 82.69 ms per token, 12.09 tokens per second) 23.03.956.076 I slot print_timing: id 1 | task 27698 | total time = 4350.97 ms / 786 tokens 23.03.956.076 I slot print_timing: id 1 | task 27698 | graphs reused = 26356 23.03.956.077 I slot print_timing: id 1 | task 27698 | graph reallocs = 0 / 0 (same size) / (changed size) 23.03.956.127 I slot release: id 1 | task 27698 | stop processing: n_tokens = 785, truncated = 0 23.03.956.520 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1041, t_last = 339090770855 23.03.958.704 I slot launch_slot_: id 2 | task 27705 | processing task, is_child = 0 23.04.431.426 I slot print_timing: id 0 | task 27700 | prompt eval time = 3566.36 ms / 831 tokens ( 4.29 ms per token, 233.01 tokens per second) 23.04.431.428 I slot print_timing: id 0 | task 27700 | eval time = 475.61 ms / 2 tokens ( 475.61 ms per token, 2.10 tokens per second) 23.04.431.428 I slot print_timing: id 0 | task 27700 | total time = 4041.97 ms / 833 tokens 23.04.431.429 I slot print_timing: id 0 | task 27700 | graphs reused = 26356 23.04.431.429 I slot print_timing: id 0 | task 27700 | graph reallocs = 0 / 0 (same size) / (changed size) 23.04.431.475 I slot release: id 0 | task 27700 | stop processing: n_tokens = 832, truncated = 0 23.04.431.752 I slot print_timing: id 3 | task 27701 | prompt eval time = 3183.90 ms / 776 tokens ( 4.10 ms per token, 243.73 tokens per second) 23.04.431.755 I slot print_timing: id 3 | task 27701 | eval time = 475.24 ms / 2 tokens ( 475.24 ms per token, 2.10 tokens per second) 23.04.431.755 I slot print_timing: id 3 | task 27701 | total time = 3659.13 ms / 778 tokens 23.04.431.756 I slot print_timing: id 3 | task 27701 | graphs reused = 26356 23.04.431.756 I slot print_timing: id 3 | task 27701 | graph reallocs = 0 / 0 (same size) / (changed size) 23.04.431.801 I slot release: id 3 | task 27701 | stop processing: n_tokens = 777, truncated = 0 23.04.431.806 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.832 (> 0.100 thold), f_keep = 0.885 23.04.431.835 I slot launch_slot_: id 0 | task 27707 | processing task, is_child = 0 23.04.637.607 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 785, t_last = 339090853233 23.04.637.704 I slot launch_slot_: id 1 | task 27709 | processing task, is_child = 0 23.04.637.749 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 777, t_last = 339091328906 23.04.637.816 I slot launch_slot_: id 3 | task 27710 | processing task, is_child = 0 23.08.505.774 I slot print_timing: id 2 | task 27705 | prompt eval time = 3182.79 ms / 825 tokens ( 3.86 ms per token, 259.21 tokens per second) 23.08.505.777 I slot print_timing: id 2 | task 27705 | eval time = 1362.77 ms / 2 tokens ( 1362.77 ms per token, 0.73 tokens per second) 23.08.505.777 I slot print_timing: id 2 | task 27705 | total time = 4545.57 ms / 827 tokens 23.08.505.778 I slot print_timing: id 2 | task 27705 | graphs reused = 26356 23.08.505.778 I slot print_timing: id 2 | task 27705 | graph reallocs = 0 / 0 (same size) / (changed size) 23.08.505.825 I slot release: id 2 | task 27705 | stop processing: n_tokens = 826, truncated = 0 23.08.505.837 I slot print_timing: id 1 | task 27709 | prompt processing, n_tokens = 844, progress = 1.00, t = 3.23 s / 261.37 tokens per second 23.08.505.995 I slot print_timing: id 3 | task 27710 | prompt processing, n_tokens = 888, progress = 1.00, t = 3.23 s / 275.01 tokens per second 23.08.590.739 I slot print_timing: id 0 | task 27707 | prompt eval time = 4071.17 ms / 570 tokens ( 7.14 ms per token, 140.01 tokens per second) 23.08.590.742 I slot print_timing: id 0 | task 27707 | eval time = 85.22 ms / 2 tokens ( 85.22 ms per token, 11.74 tokens per second) 23.08.590.742 I slot print_timing: id 0 | task 27707 | total time = 4156.39 ms / 572 tokens 23.08.590.742 I slot print_timing: id 0 | task 27707 | graphs reused = 26356 23.08.590.743 I slot print_timing: id 0 | task 27707 | graph reallocs = 0 / 0 (same size) / (changed size) 23.08.590.796 I slot release: id 0 | task 27707 | stop processing: n_tokens = 886, truncated = 0 23.08.591.584 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 826, t_last = 339095402930 23.08.593.354 I slot launch_slot_: id 2 | task 27714 | processing task, is_child = 0 23.08.595.072 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 886, t_last = 339095487901 23.08.595.159 I slot launch_slot_: id 0 | task 27715 | processing task, is_child = 0 23.09.343.922 I slot print_timing: id 1 | task 27709 | prompt eval time = 3315.14 ms / 848 tokens ( 3.91 ms per token, 255.80 tokens per second) 23.09.343.925 I slot print_timing: id 1 | task 27709 | eval time = 752.73 ms / 2 tokens ( 752.73 ms per token, 1.33 tokens per second) 23.09.343.925 I slot print_timing: id 1 | task 27709 | total time = 4067.87 ms / 850 tokens 23.09.343.926 I slot print_timing: id 1 | task 27709 | graphs reused = 26356 23.09.343.926 I slot print_timing: id 1 | task 27709 | graph reallocs = 0 / 0 (same size) / (changed size) 23.09.343.980 I slot release: id 1 | task 27709 | stop processing: n_tokens = 849, truncated = 0 23.09.344.268 I slot print_timing: id 3 | task 27710 | prompt eval time = 3315.32 ms / 892 tokens ( 3.72 ms per token, 269.05 tokens per second) 23.09.344.270 I slot print_timing: id 3 | task 27710 | eval time = 752.69 ms / 2 tokens ( 752.69 ms per token, 1.33 tokens per second) 23.09.344.270 I slot print_timing: id 3 | task 27710 | total time = 4068.01 ms / 894 tokens 23.09.344.271 I slot print_timing: id 3 | task 27710 | graphs reused = 26356 23.09.344.271 I slot print_timing: id 3 | task 27710 | graph reallocs = 0 / 0 (same size) / (changed size) 23.09.344.321 I slot release: id 3 | task 27710 | stop processing: n_tokens = 893, truncated = 0 23.09.989.911 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 849, t_last = 339096241085 23.10.627.802 I slot launch_slot_: id 1 | task 27718 | processing task, is_child = 0 23.10.630.363 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 893, t_last = 339096241426 23.10.630.466 I slot launch_slot_: id 3 | task 27719 | processing task, is_child = 0 23.12.855.355 I slot print_timing: id 0 | task 27715 | prompt eval time = 2925.86 ms / 792 tokens ( 3.69 ms per token, 270.69 tokens per second) 23.12.855.358 I slot print_timing: id 0 | task 27715 | eval time = 1334.33 ms / 2 tokens ( 1334.33 ms per token, 0.75 tokens per second) 23.12.855.358 I slot print_timing: id 0 | task 27715 | total time = 4260.19 ms / 794 tokens 23.12.855.358 I slot print_timing: id 0 | task 27715 | graphs reused = 26356 23.12.855.359 I slot print_timing: id 0 | task 27715 | graph reallocs = 0 / 0 (same size) / (changed size) 23.12.855.411 I slot release: id 0 | task 27715 | stop processing: n_tokens = 793, truncated = 0 23.12.855.704 I slot print_timing: id 2 | task 27714 | prompt eval time = 2926.07 ms / 677 tokens ( 4.32 ms per token, 231.37 tokens per second) 23.12.855.707 I slot print_timing: id 2 | task 27714 | eval time = 1334.40 ms / 2 tokens ( 1334.40 ms per token, 0.75 tokens per second) 23.12.855.707 I slot print_timing: id 2 | task 27714 | total time = 4260.47 ms / 679 tokens 23.12.855.707 I slot print_timing: id 2 | task 27714 | graphs reused = 26356 23.12.855.708 I slot print_timing: id 2 | task 27714 | graph reallocs = 0 / 0 (same size) / (changed size) 23.12.855.744 I slot release: id 2 | task 27714 | stop processing: n_tokens = 678, truncated = 0 23.12.923.237 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 793, t_last = 339099752516 23.12.924.925 I slot launch_slot_: id 0 | task 27723 | processing task, is_child = 0 23.12.926.249 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 678, t_last = 339099752849 23.12.926.314 I slot launch_slot_: id 2 | task 27724 | processing task, is_child = 0 23.13.629.965 I slot print_timing: id 1 | task 27718 | prompt eval time = 2292.19 ms / 740 tokens ( 3.10 ms per token, 322.83 tokens per second) 23.13.629.967 I slot print_timing: id 1 | task 27718 | eval time = 707.10 ms / 2 tokens ( 707.10 ms per token, 1.41 tokens per second) 23.13.629.968 I slot print_timing: id 1 | task 27718 | total time = 2999.29 ms / 742 tokens 23.13.629.968 I slot print_timing: id 1 | task 27718 | graphs reused = 26356 23.13.629.968 I slot print_timing: id 1 | task 27718 | graph reallocs = 0 / 0 (same size) / (changed size) 23.13.630.015 I slot release: id 1 | task 27718 | stop processing: n_tokens = 741, truncated = 0 23.13.630.305 I slot print_timing: id 3 | task 27719 | prompt eval time = 2292.34 ms / 813 tokens ( 2.82 ms per token, 354.66 tokens per second) 23.13.630.307 I slot print_timing: id 3 | task 27719 | eval time = 707.07 ms / 2 tokens ( 707.07 ms per token, 1.41 tokens per second) 23.13.630.308 I slot print_timing: id 3 | task 27719 | total time = 2999.41 ms / 815 tokens 23.13.630.308 I slot print_timing: id 3 | task 27719 | graphs reused = 26356 23.13.630.308 I slot print_timing: id 3 | task 27719 | graph reallocs = 0 / 0 (same size) / (changed size) 23.13.630.349 I slot release: id 3 | task 27719 | stop processing: n_tokens = 814, truncated = 0 23.14.276.213 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 741, t_last = 339100527120 23.14.917.458 I slot launch_slot_: id 1 | task 27727 | processing task, is_child = 0 23.14.919.883 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 814, t_last = 339100527454 23.14.919.955 I slot launch_slot_: id 3 | task 27728 | processing task, is_child = 0 23.17.016.990 I slot print_timing: id 0 | task 27723 | prompt eval time = 2759.85 ms / 719 tokens ( 3.84 ms per token, 260.52 tokens per second) 23.17.016.992 I slot print_timing: id 0 | task 27723 | eval time = 1330.82 ms / 2 tokens ( 1330.82 ms per token, 0.75 tokens per second) 23.17.016.992 I slot print_timing: id 0 | task 27723 | total time = 4090.67 ms / 721 tokens 23.17.016.993 I slot print_timing: id 0 | task 27723 | graphs reused = 26356 23.17.016.993 I slot print_timing: id 0 | task 27723 | graph reallocs = 0 / 0 (same size) / (changed size) 23.17.017.035 I slot release: id 0 | task 27723 | stop processing: n_tokens = 720, truncated = 0 23.17.017.322 I slot print_timing: id 2 | task 27724 | prompt eval time = 2760.07 ms / 694 tokens ( 3.98 ms per token, 251.44 tokens per second) 23.17.017.324 I slot print_timing: id 2 | task 27724 | eval time = 1330.87 ms / 2 tokens ( 1330.87 ms per token, 0.75 tokens per second) 23.17.017.325 I slot print_timing: id 2 | task 27724 | total time = 4090.94 ms / 696 tokens 23.17.017.325 I slot print_timing: id 2 | task 27724 | graphs reused = 26356 23.17.017.325 I slot print_timing: id 2 | task 27724 | graph reallocs = 0 / 0 (same size) / (changed size) 23.17.017.361 I slot release: id 2 | task 27724 | stop processing: n_tokens = 695, truncated = 0 23.17.084.951 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.883 (> 0.100 thold), f_keep = 0.881 23.17.084.980 I slot launch_slot_: id 2 | task 27732 | processing task, is_child = 0 23.17.086.474 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 720, t_last = 339103914140 23.17.086.543 I slot launch_slot_: id 0 | task 27733 | processing task, is_child = 0 23.18.090.577 I slot print_timing: id 1 | task 27727 | prompt eval time = 2164.48 ms / 718 tokens ( 3.01 ms per token, 331.72 tokens per second) 23.18.090.580 I slot print_timing: id 1 | task 27727 | eval time = 1006.00 ms / 2 tokens ( 1006.00 ms per token, 0.99 tokens per second) 23.18.090.581 I slot print_timing: id 1 | task 27727 | total time = 3170.47 ms / 720 tokens 23.18.090.582 I slot print_timing: id 1 | task 27727 | graphs reused = 26356 23.18.090.582 I slot print_timing: id 1 | task 27727 | graph reallocs = 0 / 0 (same size) / (changed size) 23.18.090.626 I slot release: id 1 | task 27727 | stop processing: n_tokens = 719, truncated = 0 23.18.090.905 I slot print_timing: id 3 | task 27728 | prompt eval time = 2164.67 ms / 694 tokens ( 3.12 ms per token, 320.60 tokens per second) 23.18.090.907 I slot print_timing: id 3 | task 27728 | eval time = 1005.96 ms / 2 tokens ( 1005.96 ms per token, 0.99 tokens per second) 23.18.090.908 I slot print_timing: id 3 | task 27728 | total time = 3170.64 ms / 696 tokens 23.18.090.908 I slot print_timing: id 3 | task 27728 | graphs reused = 26356 23.18.090.909 I slot print_timing: id 3 | task 27728 | graph reallocs = 0 / 0 (same size) / (changed size) 23.18.090.937 I slot release: id 3 | task 27728 | stop processing: n_tokens = 695, truncated = 0 23.18.766.865 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.890 (> 0.100 thold), f_keep = 0.851 23.18.766.901 I slot launch_slot_: id 1 | task 27736 | processing task, is_child = 0 23.18.768.382 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.887 (> 0.100 thold), f_keep = 0.881 23.18.768.406 I slot launch_slot_: id 3 | task 27737 | processing task, is_child = 0 23.20.096.289 I slot print_timing: id 2 | task 27732 | prompt eval time = 1680.26 ms / 515 tokens ( 3.26 ms per token, 306.50 tokens per second) 23.20.096.294 I slot print_timing: id 2 | task 27732 | eval time = 1329.43 ms / 2 tokens ( 1329.43 ms per token, 0.75 tokens per second) 23.20.096.295 I slot print_timing: id 2 | task 27732 | total time = 3009.69 ms / 517 tokens 23.20.096.295 I slot print_timing: id 2 | task 27732 | graphs reused = 26356 23.20.096.296 I slot print_timing: id 2 | task 27732 | graph reallocs = 0 / 0 (same size) / (changed size) 23.20.096.340 I slot release: id 2 | task 27732 | stop processing: n_tokens = 694, truncated = 0 23.20.181.565 I slot print_timing: id 0 | task 27733 | prompt eval time = 3009.46 ms / 696 tokens ( 4.32 ms per token, 231.27 tokens per second) 23.20.181.567 I slot print_timing: id 0 | task 27733 | eval time = 85.55 ms / 2 tokens ( 85.55 ms per token, 11.69 tokens per second) 23.20.181.567 I slot print_timing: id 0 | task 27733 | total time = 3095.01 ms / 698 tokens 23.20.181.568 I slot print_timing: id 0 | task 27733 | graphs reused = 26356 23.20.181.568 I slot print_timing: id 0 | task 27733 | graph reallocs = 0 / 0 (same size) / (changed size) 23.20.181.612 I slot release: id 0 | task 27733 | stop processing: n_tokens = 697, truncated = 0 23.20.182.347 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.876 (> 0.100 thold), f_keep = 0.885 23.20.182.394 I slot launch_slot_: id 2 | task 27740 | processing task, is_child = 0 23.20.263.306 I slot print_timing: id 1 | task 27736 | prompt eval time = 1413.38 ms / 486 tokens ( 2.91 ms per token, 343.86 tokens per second) 23.20.263.308 I slot print_timing: id 1 | task 27736 | eval time = 81.39 ms / 2 tokens ( 81.39 ms per token, 12.29 tokens per second) 23.20.263.309 I slot print_timing: id 1 | task 27736 | total time = 1494.77 ms / 488 tokens 23.20.263.309 I slot print_timing: id 1 | task 27736 | graphs reused = 26356 23.20.263.310 I slot print_timing: id 1 | task 27736 | graph reallocs = 0 / 0 (same size) / (changed size) 23.20.263.355 I slot release: id 1 | task 27736 | stop processing: n_tokens = 689, truncated = 0 23.20.263.643 I slot print_timing: id 3 | task 27737 | prompt eval time = 1413.68 ms / 512 tokens ( 2.76 ms per token, 362.18 tokens per second) 23.20.263.646 I slot print_timing: id 3 | task 27737 | eval time = 81.30 ms / 2 tokens ( 81.30 ms per token, 12.30 tokens per second) 23.20.263.646 I slot print_timing: id 3 | task 27737 | total time = 1494.98 ms / 514 tokens 23.20.263.646 I slot print_timing: id 3 | task 27737 | graphs reused = 26356 23.20.263.646 I slot print_timing: id 3 | task 27737 | graph reallocs = 0 / 0 (same size) / (changed size) 23.20.263.679 I slot release: id 3 | task 27737 | stop processing: n_tokens = 691, truncated = 0 23.20.263.684 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.878 (> 0.100 thold), f_keep = 0.890 23.20.263.708 I slot launch_slot_: id 1 | task 27742 | processing task, is_child = 0 23.21.519.409 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.837 (> 0.100 thold), f_keep = 0.878 23.21.519.455 I slot launch_slot_: id 0 | task 27744 | processing task, is_child = 0 23.21.519.520 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.886 (> 0.100 thold), f_keep = 0.886 23.21.519.539 I slot launch_slot_: id 3 | task 27745 | processing task, is_child = 0 23.23.244.466 I slot print_timing: id 1 | task 27742 | prompt eval time = 2276.84 ms / 496 tokens ( 4.59 ms per token, 217.85 tokens per second) 23.23.244.468 I slot print_timing: id 1 | task 27742 | eval time = 702.48 ms / 2 tokens ( 702.48 ms per token, 1.42 tokens per second) 23.23.244.468 I slot print_timing: id 1 | task 27742 | total time = 2979.32 ms / 498 tokens 23.23.244.469 I slot print_timing: id 1 | task 27742 | graphs reused = 26356 23.23.244.469 I slot print_timing: id 1 | task 27742 | graph reallocs = 0 / 0 (same size) / (changed size) 23.23.244.510 I slot release: id 1 | task 27742 | stop processing: n_tokens = 699, truncated = 0 23.23.244.781 I slot print_timing: id 2 | task 27740 | prompt eval time = 2357.97 ms / 523 tokens ( 4.51 ms per token, 221.80 tokens per second) 23.23.244.783 I slot print_timing: id 2 | task 27740 | eval time = 702.50 ms / 2 tokens ( 702.50 ms per token, 1.42 tokens per second) 23.23.244.783 I slot print_timing: id 2 | task 27740 | total time = 3060.47 ms / 525 tokens 23.23.244.783 I slot print_timing: id 2 | task 27740 | graphs reused = 26356 23.23.244.784 I slot print_timing: id 2 | task 27740 | graph reallocs = 0 / 0 (same size) / (changed size) 23.23.244.818 I slot release: id 2 | task 27740 | stop processing: n_tokens = 702, truncated = 0 23.23.294.925 I slot print_timing: id 3 | task 27745 | prompt eval time = 1611.12 ms / 513 tokens ( 3.14 ms per token, 318.41 tokens per second) 23.23.294.931 I slot print_timing: id 3 | task 27745 | eval time = 49.79 ms / 2 tokens ( 49.79 ms per token, 20.08 tokens per second) 23.23.294.931 I slot print_timing: id 3 | task 27745 | total time = 1660.92 ms / 515 tokens 23.23.294.931 I slot print_timing: id 3 | task 27745 | graphs reused = 26356 23.23.294.932 I slot print_timing: id 3 | task 27745 | graph reallocs = 0 / 0 (same size) / (changed size) 23.23.294.969 I slot release: id 3 | task 27745 | stop processing: n_tokens = 692, truncated = 0 23.23.294.975 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 699, t_last = 339110141615 23.23.296.585 I slot launch_slot_: id 1 | task 27749 | processing task, is_child = 0 23.23.299.402 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 702, t_last = 339110141923 23.23.299.471 I slot launch_slot_: id 2 | task 27750 | processing task, is_child = 0 23.23.299.514 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 692, t_last = 339110192074 23.23.299.570 I slot launch_slot_: id 3 | task 27751 | processing task, is_child = 0 23.25.246.302 I slot print_timing: id 0 | task 27744 | prompt eval time = 1775.12 ms / 551 tokens ( 3.22 ms per token, 310.40 tokens per second) 23.25.246.304 I slot print_timing: id 0 | task 27744 | eval time = 1951.63 ms / 2 tokens ( 1951.63 ms per token, 0.51 tokens per second) 23.25.246.305 I slot print_timing: id 0 | task 27744 | total time = 3726.75 ms / 553 tokens 23.25.246.305 I slot print_timing: id 0 | task 27744 | graphs reused = 26356 23.25.246.306 I slot print_timing: id 0 | task 27744 | graph reallocs = 0 / 0 (same size) / (changed size) 23.25.246.359 I slot release: id 0 | task 27744 | stop processing: n_tokens = 732, truncated = 0 23.27.235.819 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 732, t_last = 339112143464 23.27.282.138 I slot launch_slot_: id 0 | task 27754 | processing task, is_child = 0 23.27.282.209 I slot print_timing: id 1 | task 27749 | prompt processing, n_tokens = 857, progress = 1.00, t = 3.94 s / 217.72 tokens per second 23.27.282.357 I slot print_timing: id 2 | task 27750 | prompt processing, n_tokens = 870, progress = 1.00, t = 3.94 s / 221.03 tokens per second 23.27.282.510 I slot print_timing: id 3 | task 27751 | prompt processing, n_tokens = 1101, progress = 1.00, t = 3.94 s / 279.72 tokens per second 23.28.915.240 I slot print_timing: id 1 | task 27749 | prompt eval time = 4936.30 ms / 861 tokens ( 5.73 ms per token, 174.42 tokens per second) 23.28.915.242 I slot print_timing: id 1 | task 27749 | eval time = 679.36 ms / 2 tokens ( 679.36 ms per token, 1.47 tokens per second) 23.28.915.243 I slot print_timing: id 1 | task 27749 | total time = 5615.66 ms / 863 tokens 23.28.915.243 I slot print_timing: id 1 | task 27749 | graphs reused = 26356 23.28.915.244 I slot print_timing: id 1 | task 27749 | graph reallocs = 0 / 0 (same size) / (changed size) 23.28.915.296 I slot release: id 1 | task 27749 | stop processing: n_tokens = 862, truncated = 0 23.28.915.578 I slot print_timing: id 2 | task 27750 | prompt eval time = 4936.61 ms / 874 tokens ( 5.65 ms per token, 177.04 tokens per second) 23.28.915.581 I slot print_timing: id 2 | task 27750 | eval time = 679.33 ms / 2 tokens ( 679.33 ms per token, 1.47 tokens per second) 23.28.915.581 I slot print_timing: id 2 | task 27750 | total time = 5615.93 ms / 876 tokens 23.28.915.582 I slot print_timing: id 2 | task 27750 | graphs reused = 26356 23.28.915.582 I slot print_timing: id 2 | task 27750 | graph reallocs = 0 / 0 (same size) / (changed size) 23.28.915.618 I slot release: id 2 | task 27750 | stop processing: n_tokens = 875, truncated = 0 23.28.915.887 I slot print_timing: id 3 | task 27751 | prompt eval time = 4936.84 ms / 1105 tokens ( 4.47 ms per token, 223.83 tokens per second) 23.28.915.890 I slot print_timing: id 3 | task 27751 | eval time = 679.36 ms / 2 tokens ( 679.36 ms per token, 1.47 tokens per second) 23.28.915.891 I slot print_timing: id 3 | task 27751 | total time = 5616.20 ms / 1107 tokens 23.28.915.891 I slot print_timing: id 3 | task 27751 | graphs reused = 26356 23.28.915.891 I slot print_timing: id 3 | task 27751 | graph reallocs = 0 / 0 (same size) / (changed size) 23.28.915.939 I slot release: id 3 | task 27751 | stop processing: n_tokens = 1106, truncated = 0 23.28.950.816 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.901 (> 0.100 thold), f_keep = 0.892 23.28.950.840 I slot launch_slot_: id 3 | task 27758 | processing task, is_child = 0 23.28.954.399 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 862, t_last = 339115812401 23.28.954.473 I slot launch_slot_: id 1 | task 27759 | processing task, is_child = 0 23.28.954.520 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 875, t_last = 339115812723 23.28.954.587 I slot launch_slot_: id 2 | task 27760 | processing task, is_child = 0 23.31.266.911 I slot print_timing: id 0 | task 27754 | prompt eval time = 1668.66 ms / 1096 tokens ( 1.52 ms per token, 656.81 tokens per second) 23.31.266.913 I slot print_timing: id 0 | task 27754 | eval time = 2316.10 ms / 2 tokens ( 2316.10 ms per token, 0.43 tokens per second) 23.31.266.914 I slot print_timing: id 0 | task 27754 | total time = 3984.76 ms / 1098 tokens 23.31.266.914 I slot print_timing: id 0 | task 27754 | graphs reused = 26356 23.31.266.915 I slot print_timing: id 0 | task 27754 | graph reallocs = 0 / 0 (same size) / (changed size) 23.31.266.968 I slot release: id 0 | task 27754 | stop processing: n_tokens = 1097, truncated = 0 23.32.637.303 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.898 23.32.637.342 I slot launch_slot_: id 0 | task 27763 | processing task, is_child = 0 23.32.637.480 I slot print_timing: id 1 | task 27759 | prompt processing, n_tokens = 1094, progress = 1.00, t = 3.68 s / 297.09 tokens per second 23.32.637.656 I slot print_timing: id 2 | task 27760 | prompt processing, n_tokens = 1082, progress = 1.00, t = 3.68 s / 293.84 tokens per second 23.33.377.071 I slot print_timing: id 3 | task 27758 | prompt eval time = 3682.58 ms / 505 tokens ( 7.29 ms per token, 137.13 tokens per second) 23.33.377.073 I slot print_timing: id 3 | task 27758 | eval time = 739.77 ms / 2 tokens ( 739.77 ms per token, 1.35 tokens per second) 23.33.377.073 I slot print_timing: id 3 | task 27758 | total time = 4422.35 ms / 507 tokens 23.33.377.074 I slot print_timing: id 3 | task 27758 | graphs reused = 26356 23.33.377.074 I slot print_timing: id 3 | task 27758 | graph reallocs = 0 / 0 (same size) / (changed size) 23.33.377.135 I slot release: id 3 | task 27758 | stop processing: n_tokens = 1095, truncated = 0 23.33.434.924 I slot print_timing: id 1 | task 27759 | prompt eval time = 4421.83 ms / 1098 tokens ( 4.03 ms per token, 248.31 tokens per second) 23.33.434.927 I slot print_timing: id 1 | task 27759 | eval time = 58.50 ms / 2 tokens ( 58.50 ms per token, 17.09 tokens per second) 23.33.434.927 I slot print_timing: id 1 | task 27759 | total time = 4480.33 ms / 1100 tokens 23.33.434.928 I slot print_timing: id 1 | task 27759 | graphs reused = 26356 23.33.434.928 I slot print_timing: id 1 | task 27759 | graph reallocs = 0 / 0 (same size) / (changed size) 23.33.434.986 I slot release: id 1 | task 27759 | stop processing: n_tokens = 1099, truncated = 0 23.33.435.263 I slot print_timing: id 2 | task 27760 | prompt eval time = 4422.13 ms / 1086 tokens ( 4.07 ms per token, 245.58 tokens per second) 23.33.435.268 I slot print_timing: id 2 | task 27760 | eval time = 58.47 ms / 2 tokens ( 58.47 ms per token, 17.10 tokens per second) 23.33.435.268 I slot print_timing: id 2 | task 27760 | total time = 4480.60 ms / 1088 tokens 23.33.435.269 I slot print_timing: id 2 | task 27760 | graphs reused = 26356 23.33.435.269 I slot print_timing: id 2 | task 27760 | graph reallocs = 0 / 0 (same size) / (changed size) 23.33.435.318 I slot release: id 2 | task 27760 | stop processing: n_tokens = 1087, truncated = 0 23.33.435.325 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.897 23.33.435.364 I slot launch_slot_: id 1 | task 27766 | processing task, is_child = 0 23.34.103.542 I slot print_timing: id 0 | task 27763 | prompt eval time = 797.32 ms / 515 tokens ( 1.55 ms per token, 645.91 tokens per second) 23.34.103.546 I slot print_timing: id 0 | task 27763 | eval time = 668.87 ms / 2 tokens ( 668.87 ms per token, 1.50 tokens per second) 23.34.103.546 I slot print_timing: id 0 | task 27763 | total time = 1466.19 ms / 517 tokens 23.34.103.547 I slot print_timing: id 0 | task 27763 | graphs reused = 26356 23.34.103.547 I slot print_timing: id 0 | task 27763 | graph reallocs = 0 / 0 (same size) / (changed size) 23.34.103.601 I slot release: id 0 | task 27763 | stop processing: n_tokens = 1096, truncated = 0 23.34.103.610 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.894 (> 0.100 thold), f_keep = 0.900 23.34.103.639 I slot launch_slot_: id 0 | task 27768 | processing task, is_child = 0 23.34.103.758 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.907 23.34.103.783 I slot launch_slot_: id 2 | task 27769 | processing task, is_child = 0 23.34.245.745 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.900 23.34.245.775 I slot launch_slot_: id 3 | task 27771 | processing task, is_child = 0 23.36.261.200 I slot print_timing: id 1 | task 27766 | prompt eval time = 805.67 ms / 504 tokens ( 1.60 ms per token, 625.57 tokens per second) 23.36.261.203 I slot print_timing: id 1 | task 27766 | eval time = 2015.46 ms / 2 tokens ( 2015.46 ms per token, 0.50 tokens per second) 23.36.261.204 I slot print_timing: id 1 | task 27766 | total time = 2821.13 ms / 506 tokens 23.36.261.204 I slot print_timing: id 1 | task 27766 | graphs reused = 26356 23.36.261.204 I slot print_timing: id 1 | task 27766 | graph reallocs = 0 / 0 (same size) / (changed size) 23.36.261.260 I slot release: id 1 | task 27766 | stop processing: n_tokens = 1087, truncated = 0 23.36.351.993 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.907 23.36.352.032 I slot launch_slot_: id 1 | task 27774 | processing task, is_child = 0 23.37.038.082 I slot print_timing: id 0 | task 27768 | prompt eval time = 2247.37 ms / 523 tokens ( 4.30 ms per token, 232.72 tokens per second) 23.37.038.085 I slot print_timing: id 0 | task 27768 | eval time = 686.86 ms / 2 tokens ( 686.86 ms per token, 1.46 tokens per second) 23.37.038.085 I slot print_timing: id 0 | task 27768 | total time = 2934.23 ms / 525 tokens 23.37.038.086 I slot print_timing: id 0 | task 27768 | graphs reused = 26356 23.37.038.086 I slot print_timing: id 0 | task 27768 | graph reallocs = 0 / 0 (same size) / (changed size) 23.37.038.150 I slot release: id 0 | task 27768 | stop processing: n_tokens = 1104, truncated = 0 23.37.038.414 I slot print_timing: id 2 | task 27769 | prompt eval time = 2247.47 ms / 525 tokens ( 4.28 ms per token, 233.60 tokens per second) 23.37.038.416 I slot print_timing: id 2 | task 27769 | eval time = 686.82 ms / 2 tokens ( 686.82 ms per token, 1.46 tokens per second) 23.37.038.416 I slot print_timing: id 2 | task 27769 | total time = 2934.29 ms / 527 tokens 23.37.038.416 I slot print_timing: id 2 | task 27769 | graphs reused = 26356 23.37.038.417 I slot print_timing: id 2 | task 27769 | graph reallocs = 0 / 0 (same size) / (changed size) 23.37.038.467 I slot release: id 2 | task 27769 | stop processing: n_tokens = 1096, truncated = 0 23.37.038.784 I slot print_timing: id 3 | task 27771 | prompt eval time = 2106.13 ms / 507 tokens ( 4.15 ms per token, 240.73 tokens per second) 23.37.038.786 I slot print_timing: id 3 | task 27771 | eval time = 686.80 ms / 2 tokens ( 686.80 ms per token, 1.46 tokens per second) 23.37.038.786 I slot print_timing: id 3 | task 27771 | total time = 2792.93 ms / 509 tokens 23.37.038.786 I slot print_timing: id 3 | task 27771 | graphs reused = 26356 23.37.038.787 I slot print_timing: id 3 | task 27771 | graph reallocs = 0 / 0 (same size) / (changed size) 23.37.038.827 I slot release: id 3 | task 27771 | stop processing: n_tokens = 1097, truncated = 0 23.37.074.229 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.893 23.37.074.257 I slot launch_slot_: id 0 | task 27777 | processing task, is_child = 0 23.37.078.848 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.900 23.37.078.876 I slot launch_slot_: id 2 | task 27778 | processing task, is_child = 0 23.37.078.932 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.902 (> 0.100 thold), f_keep = 0.899 23.37.078.948 I slot launch_slot_: id 3 | task 27779 | processing task, is_child = 0 23.39.082.160 I slot print_timing: id 1 | task 27774 | prompt eval time = 722.19 ms / 506 tokens ( 1.43 ms per token, 700.65 tokens per second) 23.39.082.162 I slot print_timing: id 1 | task 27774 | eval time = 2007.93 ms / 2 tokens ( 2007.93 ms per token, 0.50 tokens per second) 23.39.082.163 I slot print_timing: id 1 | task 27774 | total time = 2730.12 ms / 508 tokens 23.39.082.163 I slot print_timing: id 1 | task 27774 | graphs reused = 26356 23.39.082.164 I slot print_timing: id 1 | task 27774 | graph reallocs = 0 / 0 (same size) / (changed size) 23.39.082.224 I slot release: id 1 | task 27774 | stop processing: n_tokens = 1089, truncated = 0 23.39.172.642 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.904 (> 0.100 thold), f_keep = 0.905 23.39.172.676 I slot launch_slot_: id 1 | task 27782 | processing task, is_child = 0 23.39.861.141 I slot print_timing: id 0 | task 27777 | prompt eval time = 2092.99 ms / 502 tokens ( 4.17 ms per token, 239.85 tokens per second) 23.39.861.144 I slot print_timing: id 0 | task 27777 | eval time = 689.18 ms / 2 tokens ( 689.18 ms per token, 1.45 tokens per second) 23.39.861.144 I slot print_timing: id 0 | task 27777 | total time = 2782.17 ms / 504 tokens 23.39.861.145 I slot print_timing: id 0 | task 27777 | graphs reused = 26356 23.39.861.145 I slot print_timing: id 0 | task 27777 | graph reallocs = 0 / 0 (same size) / (changed size) 23.39.861.199 I slot release: id 0 | task 27777 | stop processing: n_tokens = 1090, truncated = 0 23.39.861.545 I slot print_timing: id 2 | task 27778 | prompt eval time = 2093.22 ms / 513 tokens ( 4.08 ms per token, 245.08 tokens per second) 23.39.861.547 I slot print_timing: id 2 | task 27778 | eval time = 689.24 ms / 2 tokens ( 689.24 ms per token, 1.45 tokens per second) 23.39.861.547 I slot print_timing: id 2 | task 27778 | total time = 2782.46 ms / 515 tokens 23.39.861.547 I slot print_timing: id 2 | task 27778 | graphs reused = 26356 23.39.861.548 I slot print_timing: id 2 | task 27778 | graph reallocs = 0 / 0 (same size) / (changed size) 23.39.861.584 I slot release: id 2 | task 27778 | stop processing: n_tokens = 1093, truncated = 0 23.39.861.852 I slot print_timing: id 3 | task 27779 | prompt eval time = 2093.44 ms / 504 tokens ( 4.15 ms per token, 240.75 tokens per second) 23.39.861.855 I slot print_timing: id 3 | task 27779 | eval time = 689.22 ms / 2 tokens ( 689.22 ms per token, 1.45 tokens per second) 23.39.861.857 I slot print_timing: id 3 | task 27779 | total time = 2782.65 ms / 506 tokens 23.39.861.857 I slot print_timing: id 3 | task 27779 | graphs reused = 26356 23.39.861.857 I slot print_timing: id 3 | task 27779 | graph reallocs = 0 / 0 (same size) / (changed size) 23.39.861.907 I slot release: id 3 | task 27779 | stop processing: n_tokens = 1094, truncated = 0 23.39.896.828 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1090, t_last = 339126758304 23.39.899.363 I slot launch_slot_: id 0 | task 27785 | processing task, is_child = 0 23.39.903.527 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1093, t_last = 339126758689 23.39.903.613 I slot launch_slot_: id 2 | task 27786 | processing task, is_child = 0 23.39.903.669 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1094, t_last = 339126759012 23.39.903.742 I slot launch_slot_: id 3 | task 27787 | processing task, is_child = 0 23.41.959.945 I slot print_timing: id 1 | task 27782 | prompt eval time = 724.14 ms / 509 tokens ( 1.42 ms per token, 702.90 tokens per second) 23.41.959.949 I slot print_timing: id 1 | task 27782 | eval time = 2063.11 ms / 2 tokens ( 2063.11 ms per token, 0.48 tokens per second) 23.41.959.950 I slot print_timing: id 1 | task 27782 | total time = 2787.26 ms / 511 tokens 23.41.959.950 I slot print_timing: id 1 | task 27782 | graphs reused = 26356 23.41.959.951 I slot print_timing: id 1 | task 27782 | graph reallocs = 0 / 0 (same size) / (changed size) 23.41.960.006 I slot release: id 1 | task 27782 | stop processing: n_tokens = 1092, truncated = 0 23.43.249.779 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1092, t_last = 339128857111 23.43.897.564 I slot launch_slot_: id 1 | task 27790 | processing task, is_child = 0 23.43.897.592 I slot print_timing: id 0 | task 27785 | prompt processing, n_tokens = 979, progress = 1.00, t = 3.35 s / 292.59 tokens per second 23.43.897.876 I slot print_timing: id 2 | task 27786 | prompt processing, n_tokens = 1062, progress = 1.00, t = 3.35 s / 317.40 tokens per second 23.43.898.066 I slot print_timing: id 3 | task 27787 | prompt processing, n_tokens = 992, progress = 1.00, t = 3.35 s / 296.49 tokens per second 23.45.369.398 I slot print_timing: id 0 | task 27785 | prompt eval time = 4772.73 ms / 983 tokens ( 4.86 ms per token, 205.96 tokens per second) 23.45.369.401 I slot print_timing: id 0 | task 27785 | eval time = 692.91 ms / 2 tokens ( 692.91 ms per token, 1.44 tokens per second) 23.45.369.405 I slot print_timing: id 0 | task 27785 | total time = 5465.64 ms / 985 tokens 23.45.369.407 I slot print_timing: id 0 | task 27785 | graphs reused = 26356 23.45.369.409 I slot print_timing: id 0 | task 27785 | graph reallocs = 0 / 0 (same size) / (changed size) 23.45.369.479 I slot release: id 0 | task 27785 | stop processing: n_tokens = 984, truncated = 0 23.45.369.788 I slot print_timing: id 2 | task 27786 | prompt eval time = 4772.95 ms / 1066 tokens ( 4.48 ms per token, 223.34 tokens per second) 23.45.369.790 I slot print_timing: id 2 | task 27786 | eval time = 693.01 ms / 2 tokens ( 693.01 ms per token, 1.44 tokens per second) 23.45.369.791 I slot print_timing: id 2 | task 27786 | total time = 5465.95 ms / 1068 tokens 23.45.369.791 I slot print_timing: id 2 | task 27786 | graphs reused = 26356 23.45.369.791 I slot print_timing: id 2 | task 27786 | graph reallocs = 0 / 0 (same size) / (changed size) 23.45.369.844 I slot release: id 2 | task 27786 | stop processing: n_tokens = 1067, truncated = 0 23.45.370.176 I slot print_timing: id 3 | task 27787 | prompt eval time = 4773.19 ms / 996 tokens ( 4.79 ms per token, 208.67 tokens per second) 23.45.370.178 I slot print_timing: id 3 | task 27787 | eval time = 693.07 ms / 2 tokens ( 693.07 ms per token, 1.44 tokens per second) 23.45.370.179 I slot print_timing: id 3 | task 27787 | total time = 5466.27 ms / 998 tokens 23.45.370.179 I slot print_timing: id 3 | task 27787 | graphs reused = 26356 23.45.370.179 I slot print_timing: id 3 | task 27787 | graph reallocs = 0 / 0 (same size) / (changed size) 23.45.370.227 I slot release: id 3 | task 27787 | stop processing: n_tokens = 997, truncated = 0 23.45.405.382 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.877 (> 0.100 thold), f_keep = 0.886 23.45.405.410 I slot launch_slot_: id 0 | task 27794 | processing task, is_child = 0 23.45.409.564 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.866 (> 0.100 thold), f_keep = 0.817 23.45.409.589 I slot launch_slot_: id 2 | task 27795 | processing task, is_child = 0 23.45.409.637 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 997, t_last = 339132267333 23.45.409.705 I slot launch_slot_: id 3 | task 27796 | processing task, is_child = 0 23.46.452.846 I slot print_timing: id 1 | task 27790 | prompt eval time = 1507.59 ms / 1037 tokens ( 1.45 ms per token, 687.85 tokens per second) 23.46.452.851 I slot print_timing: id 1 | task 27790 | eval time = 1047.47 ms / 2 tokens ( 1047.47 ms per token, 0.95 tokens per second) 23.46.452.852 I slot print_timing: id 1 | task 27790 | total time = 2555.06 ms / 1039 tokens 23.46.452.853 I slot print_timing: id 1 | task 27790 | graphs reused = 26356 23.46.452.853 I slot print_timing: id 1 | task 27790 | graph reallocs = 0 / 0 (same size) / (changed size) 23.46.452.910 I slot release: id 1 | task 27790 | stop processing: n_tokens = 1038, truncated = 0 23.47.795.700 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1038, t_last = 339133350015 23.47.798.884 I slot launch_slot_: id 1 | task 27799 | processing task, is_child = 0 23.48.292.788 I slot print_timing: id 2 | task 27795 | prompt eval time = 2385.89 ms / 457 tokens ( 5.22 ms per token, 191.54 tokens per second) 23.48.292.790 I slot print_timing: id 2 | task 27795 | eval time = 497.09 ms / 2 tokens ( 497.09 ms per token, 2.01 tokens per second) 23.48.292.790 I slot print_timing: id 2 | task 27795 | total time = 2882.98 ms / 459 tokens 23.48.292.791 I slot print_timing: id 2 | task 27795 | graphs reused = 26356 23.48.292.791 I slot print_timing: id 2 | task 27795 | graph reallocs = 0 / 0 (same size) / (changed size) 23.48.292.852 I slot release: id 2 | task 27795 | stop processing: n_tokens = 1008, truncated = 0 23.48.974.945 I slot print_timing: id 0 | task 27794 | prompt eval time = 2882.77 ms / 527 tokens ( 5.47 ms per token, 182.81 tokens per second) 23.48.974.947 I slot print_timing: id 0 | task 27794 | eval time = 682.46 ms / 2 tokens ( 682.46 ms per token, 1.47 tokens per second) 23.48.974.948 I slot print_timing: id 0 | task 27794 | total time = 3565.23 ms / 529 tokens 23.48.974.948 I slot print_timing: id 0 | task 27794 | graphs reused = 26356 23.48.974.949 I slot print_timing: id 0 | task 27794 | graph reallocs = 0 / 0 (same size) / (changed size) 23.48.975.005 I slot release: id 0 | task 27794 | stop processing: n_tokens = 995, truncated = 0 23.48.975.286 I slot print_timing: id 3 | task 27796 | prompt eval time = 2883.23 ms / 731 tokens ( 3.94 ms per token, 253.53 tokens per second) 23.48.975.288 I slot print_timing: id 3 | task 27796 | eval time = 682.14 ms / 2 tokens ( 682.14 ms per token, 1.47 tokens per second) 23.48.975.288 I slot print_timing: id 3 | task 27796 | total time = 3565.37 ms / 733 tokens 23.48.975.289 I slot print_timing: id 3 | task 27796 | graphs reused = 26356 23.48.975.289 I slot print_timing: id 3 | task 27796 | graph reallocs = 0 / 0 (same size) / (changed size) 23.48.975.331 I slot release: id 3 | task 27796 | stop processing: n_tokens = 732, truncated = 0 23.48.975.336 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.894 (> 0.100 thold), f_keep = 0.862 23.48.975.363 I slot launch_slot_: id 3 | task 27802 | processing task, is_child = 0 23.49.638.976 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1008, t_last = 339135189958 23.49.639.077 I slot launch_slot_: id 2 | task 27804 | processing task, is_child = 0 23.49.639.129 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 995, t_last = 339135872110 23.49.639.201 I slot launch_slot_: id 0 | task 27805 | processing task, is_child = 0 23.50.405.374 I slot print_timing: id 1 | task 27799 | prompt eval time = 1839.90 ms / 774 tokens ( 2.38 ms per token, 420.68 tokens per second) 23.50.405.376 I slot print_timing: id 1 | task 27799 | eval time = 766.40 ms / 2 tokens ( 766.40 ms per token, 1.30 tokens per second) 23.50.405.377 I slot print_timing: id 1 | task 27799 | total time = 2606.30 ms / 776 tokens 23.50.405.377 I slot print_timing: id 1 | task 27799 | graphs reused = 26356 23.50.405.378 I slot print_timing: id 1 | task 27799 | graph reallocs = 0 / 0 (same size) / (changed size) 23.50.405.424 I slot release: id 1 | task 27799 | stop processing: n_tokens = 775, truncated = 0 23.51.704.587 I slot print_timing: id 3 | task 27802 | prompt eval time = 1425.37 ms / 491 tokens ( 2.90 ms per token, 344.47 tokens per second) 23.51.704.590 I slot print_timing: id 3 | task 27802 | eval time = 1298.72 ms / 2 tokens ( 1298.72 ms per token, 0.77 tokens per second) 23.51.704.591 I slot print_timing: id 3 | task 27802 | total time = 2724.09 ms / 493 tokens 23.51.704.591 I slot print_timing: id 3 | task 27802 | graphs reused = 26356 23.51.704.592 I slot print_timing: id 3 | task 27802 | graph reallocs = 0 / 0 (same size) / (changed size) 23.51.704.642 I slot release: id 3 | task 27802 | stop processing: n_tokens = 707, truncated = 0 23.51.704.649 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.883 (> 0.100 thold), f_keep = 0.814 23.51.704.683 I slot launch_slot_: id 1 | task 27808 | processing task, is_child = 0 23.52.377.760 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.890 (> 0.100 thold), f_keep = 0.893 23.52.377.787 I slot launch_slot_: id 3 | task 27810 | processing task, is_child = 0 23.53.078.138 I slot print_timing: id 0 | task 27805 | prompt eval time = 2738.25 ms / 721 tokens ( 3.80 ms per token, 263.31 tokens per second) 23.53.078.140 I slot print_timing: id 0 | task 27805 | eval time = 700.67 ms / 2 tokens ( 700.67 ms per token, 1.43 tokens per second) 23.53.078.141 I slot print_timing: id 0 | task 27805 | total time = 3438.93 ms / 723 tokens 23.53.078.142 I slot print_timing: id 0 | task 27805 | graphs reused = 26356 23.53.078.142 I slot print_timing: id 0 | task 27805 | graph reallocs = 0 / 0 (same size) / (changed size) 23.53.078.186 I slot release: id 0 | task 27805 | stop processing: n_tokens = 722, truncated = 0 23.53.078.809 I slot print_timing: id 2 | task 27804 | prompt eval time = 2738.48 ms / 723 tokens ( 3.79 ms per token, 264.02 tokens per second) 23.53.078.813 I slot print_timing: id 2 | task 27804 | eval time = 701.05 ms / 2 tokens ( 701.05 ms per token, 1.43 tokens per second) 23.53.078.813 I slot print_timing: id 2 | task 27804 | total time = 3439.53 ms / 725 tokens 23.53.078.813 I slot print_timing: id 2 | task 27804 | graphs reused = 26356 23.53.078.814 I slot print_timing: id 2 | task 27804 | graph reallocs = 0 / 0 (same size) / (changed size) 23.53.078.855 I slot release: id 2 | task 27804 | stop processing: n_tokens = 724, truncated = 0 23.53.128.326 I slot print_timing: id 1 | task 27808 | prompt eval time = 1371.28 ms / 457 tokens ( 3.00 ms per token, 333.27 tokens per second) 23.53.128.329 I slot print_timing: id 1 | task 27808 | eval time = 49.79 ms / 2 tokens ( 49.79 ms per token, 20.09 tokens per second) 23.53.128.330 I slot print_timing: id 1 | task 27808 | total time = 1421.06 ms / 459 tokens 23.53.128.330 I slot print_timing: id 1 | task 27808 | graphs reused = 26356 23.53.128.330 I slot print_timing: id 1 | task 27808 | graph reallocs = 0 / 0 (same size) / (changed size) 23.53.128.367 I slot release: id 1 | task 27808 | stop processing: n_tokens = 716, truncated = 0 23.53.128.657 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.863 (> 0.100 thold), f_keep = 0.874 23.53.128.687 I slot launch_slot_: id 0 | task 27813 | processing task, is_child = 0 23.53.131.823 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.873 (> 0.100 thold), f_keep = 0.881 23.53.131.848 I slot launch_slot_: id 1 | task 27814 | processing task, is_child = 0 23.53.857.709 I slot print_timing: id 3 | task 27810 | prompt eval time = 750.74 ms / 494 tokens ( 1.52 ms per token, 658.01 tokens per second) 23.53.857.712 I slot print_timing: id 3 | task 27810 | eval time = 729.05 ms / 2 tokens ( 729.05 ms per token, 1.37 tokens per second) 23.53.857.712 I slot print_timing: id 3 | task 27810 | total time = 1479.80 ms / 496 tokens 23.53.857.713 I slot print_timing: id 3 | task 27810 | graphs reused = 26356 23.53.857.713 I slot print_timing: id 3 | task 27810 | graph reallocs = 0 / 0 (same size) / (changed size) 23.53.857.755 I slot release: id 3 | task 27810 | stop processing: n_tokens = 710, truncated = 0 23.53.857.760 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 724, t_last = 339139975960 23.53.857.854 I slot launch_slot_: id 2 | task 27816 | processing task, is_child = 0 23.55.136.476 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 710, t_last = 339140754860 23.55.136.586 I slot launch_slot_: id 3 | task 27818 | processing task, is_child = 0 23.56.549.152 I slot print_timing: id 1 | task 27814 | prompt eval time = 2004.49 ms / 465 tokens ( 4.31 ms per token, 231.98 tokens per second) 23.56.549.157 I slot print_timing: id 1 | task 27814 | eval time = 1412.68 ms / 2 tokens ( 1412.68 ms per token, 0.71 tokens per second) 23.56.549.157 I slot print_timing: id 1 | task 27814 | total time = 3417.17 ms / 467 tokens 23.56.549.158 I slot print_timing: id 1 | task 27814 | graphs reused = 26356 23.56.549.158 I slot print_timing: id 1 | task 27814 | graph reallocs = 0 / 0 (same size) / (changed size) 23.56.549.203 I slot release: id 1 | task 27814 | stop processing: n_tokens = 724, truncated = 0 23.57.263.243 I slot print_timing: id 0 | task 27813 | prompt eval time = 3416.94 ms / 526 tokens ( 6.50 ms per token, 153.94 tokens per second) 23.57.263.245 I slot print_timing: id 0 | task 27813 | eval time = 714.40 ms / 2 tokens ( 714.40 ms per token, 1.40 tokens per second) 23.57.263.246 I slot print_timing: id 0 | task 27813 | total time = 4131.34 ms / 528 tokens 23.57.263.246 I slot print_timing: id 0 | task 27813 | graphs reused = 26356 23.57.263.247 I slot print_timing: id 0 | task 27813 | graph reallocs = 0 / 0 (same size) / (changed size) 23.57.263.293 I slot release: id 0 | task 27813 | stop processing: n_tokens = 732, truncated = 0 23.57.263.712 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 724, t_last = 339143446308 23.57.265.794 I slot launch_slot_: id 1 | task 27821 | processing task, is_child = 0 23.57.848.814 I slot print_timing: id 2 | task 27816 | prompt eval time = 3403.32 ms / 944 tokens ( 3.61 ms per token, 277.38 tokens per second) 23.57.848.817 I slot print_timing: id 2 | task 27816 | eval time = 585.11 ms / 2 tokens ( 585.11 ms per token, 1.71 tokens per second) 23.57.848.818 I slot print_timing: id 2 | task 27816 | total time = 3988.43 ms / 946 tokens 23.57.848.818 I slot print_timing: id 2 | task 27816 | graphs reused = 26356 23.57.848.818 I slot print_timing: id 2 | task 27816 | graph reallocs = 0 / 0 (same size) / (changed size) 23.57.848.871 I slot release: id 2 | task 27816 | stop processing: n_tokens = 945, truncated = 0 23.57.849.250 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.806 (> 0.100 thold), f_keep = 0.852 23.57.849.279 I slot launch_slot_: id 2 | task 27823 | processing task, is_child = 0 23.58.726.121 I slot print_timing: id 3 | task 27818 | prompt eval time = 2712.45 ms / 930 tokens ( 2.92 ms per token, 342.86 tokens per second) 23.58.726.123 I slot print_timing: id 3 | task 27818 | eval time = 876.87 ms / 2 tokens ( 876.87 ms per token, 1.14 tokens per second) 23.58.726.124 I slot print_timing: id 3 | task 27818 | total time = 3589.33 ms / 932 tokens 23.58.726.124 I slot print_timing: id 3 | task 27818 | graphs reused = 26356 23.58.726.125 I slot print_timing: id 3 | task 27818 | graph reallocs = 0 / 0 (same size) / (changed size) 23.58.726.182 I slot release: id 3 | task 27818 | stop processing: n_tokens = 931, truncated = 0 23.58.726.188 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 732, t_last = 339144160398 23.58.726.284 I slot launch_slot_: id 0 | task 27825 | processing task, is_child = 0 24.00.202.493 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 931, t_last = 339145623287 24.00.202.601 I slot launch_slot_: id 3 | task 27827 | processing task, is_child = 0 24.01.690.279 I slot print_timing: id 1 | task 27821 | prompt eval time = 2935.14 ms / 914 tokens ( 3.21 ms per token, 311.40 tokens per second) 24.01.690.284 I slot print_timing: id 1 | task 27821 | eval time = 1487.79 ms / 2 tokens ( 1487.79 ms per token, 0.67 tokens per second) 24.01.690.285 I slot print_timing: id 1 | task 27821 | total time = 4422.93 ms / 916 tokens 24.01.690.285 I slot print_timing: id 1 | task 27821 | graphs reused = 26356 24.01.690.286 I slot print_timing: id 1 | task 27821 | graph reallocs = 0 / 0 (same size) / (changed size) 24.01.690.338 I slot release: id 1 | task 27821 | stop processing: n_tokens = 915, truncated = 0 24.02.396.625 I slot print_timing: id 2 | task 27823 | prompt eval time = 3841.30 ms / 571 tokens ( 6.73 ms per token, 148.65 tokens per second) 24.02.396.629 I slot print_timing: id 2 | task 27823 | eval time = 705.93 ms / 2 tokens ( 705.93 ms per token, 1.42 tokens per second) 24.02.396.629 I slot print_timing: id 2 | task 27823 | total time = 4547.23 ms / 573 tokens 24.02.396.629 I slot print_timing: id 2 | task 27823 | graphs reused = 26356 24.02.396.630 I slot print_timing: id 2 | task 27823 | graph reallocs = 0 / 0 (same size) / (changed size) 24.02.396.688 I slot release: id 2 | task 27823 | stop processing: n_tokens = 1000, truncated = 0 24.02.396.694 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 915, t_last = 339148587443 24.02.400.188 I slot launch_slot_: id 1 | task 27830 | processing task, is_child = 0 24.04.509.983 I slot print_timing: id 0 | task 27825 | prompt eval time = 3667.10 ms / 1051 tokens ( 3.49 ms per token, 286.60 tokens per second) 24.04.509.989 I slot print_timing: id 0 | task 27825 | eval time = 2113.67 ms / 2 tokens ( 2113.67 ms per token, 0.47 tokens per second) 24.04.509.990 I slot print_timing: id 0 | task 27825 | total time = 5780.77 ms / 1053 tokens 24.04.509.990 I slot print_timing: id 0 | task 27825 | graphs reused = 26356 24.04.509.991 I slot print_timing: id 0 | task 27825 | graph reallocs = 0 / 0 (same size) / (changed size) 24.04.510.054 I slot release: id 0 | task 27825 | stop processing: n_tokens = 1052, truncated = 0 24.04.510.437 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1000, t_last = 339149293793 24.04.510.556 I slot launch_slot_: id 2 | task 27832 | processing task, is_child = 0 24.07.141.168 I slot print_timing: id 3 | task 27827 | prompt eval time = 4307.60 ms / 1054 tokens ( 4.09 ms per token, 244.68 tokens per second) 24.07.141.171 I slot print_timing: id 3 | task 27827 | eval time = 2630.73 ms / 2 tokens ( 2630.73 ms per token, 0.38 tokens per second) 24.07.141.172 I slot print_timing: id 3 | task 27827 | total time = 6938.32 ms / 1056 tokens 24.07.141.172 I slot print_timing: id 3 | task 27827 | graphs reused = 26356 24.07.141.173 I slot print_timing: id 3 | task 27827 | graph reallocs = 0 / 0 (same size) / (changed size) 24.07.141.232 I slot release: id 3 | task 27827 | stop processing: n_tokens = 1055, truncated = 0 24.07.141.239 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1052, t_last = 339151407160 24.07.141.362 I slot launch_slot_: id 0 | task 27834 | processing task, is_child = 0 24.07.144.065 I slot print_timing: id 1 | task 27830 | prompt processing, n_tokens = 2067, progress = 1.00, t = 4.74 s / 436.22 tokens per second 24.09.326.321 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1055, t_last = 339154038337 24.09.326.445 I slot launch_slot_: id 3 | task 27836 | processing task, is_child = 0 24.09.326.507 I slot print_timing: id 2 | task 27832 | prompt processing, n_tokens = 1569, progress = 0.75, t = 4.81 s / 326.11 tokens per second 24.11.973.547 I slot print_timing: id 1 | task 27830 | prompt eval time = 6923.88 ms / 2071 tokens ( 3.34 ms per token, 299.11 tokens per second) 24.11.973.549 I slot print_timing: id 1 | task 27830 | eval time = 2647.23 ms / 2 tokens ( 2647.23 ms per token, 0.38 tokens per second) 24.11.973.550 I slot print_timing: id 1 | task 27830 | total time = 9571.10 ms / 2073 tokens 24.11.973.550 I slot print_timing: id 1 | task 27830 | graphs reused = 26356 24.11.973.551 I slot print_timing: id 1 | task 27830 | graph reallocs = 0 / 0 (same size) / (changed size) 24.11.973.663 I slot release: id 1 | task 27830 | stop processing: n_tokens = 2072, truncated = 0 24.11.973.682 I slot print_timing: id 0 | task 27834 | prompt processing, n_tokens = 2045, progress = 1.00, t = 4.83 s / 423.46 tokens per second 24.11.974.015 I slot print_timing: id 2 | task 27832 | prompt processing, n_tokens = 2081, progress = 1.00, t = 7.46 s / 279.01 tokens per second 24.12.702.215 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.842 (> 0.100 thold), f_keep = 0.856 24.12.702.253 I slot launch_slot_: id 1 | task 27839 | processing task, is_child = 0 24.12.702.363 I slot print_timing: id 3 | task 27836 | prompt processing, n_tokens = 1510, progress = 0.75, t = 3.37 s / 447.42 tokens per second 24.13.571.735 I slot print_timing: id 0 | task 27834 | prompt eval time = 5557.82 ms / 2049 tokens ( 2.71 ms per token, 368.67 tokens per second) 24.13.571.738 I slot print_timing: id 0 | task 27834 | eval time = 869.94 ms / 2 tokens ( 869.94 ms per token, 1.15 tokens per second) 24.13.571.738 I slot print_timing: id 0 | task 27834 | total time = 6427.75 ms / 2051 tokens 24.13.571.739 I slot print_timing: id 0 | task 27834 | graphs reused = 26356 24.13.571.739 I slot print_timing: id 0 | task 27834 | graph reallocs = 0 / 0 (same size) / (changed size) 24.13.571.864 I slot release: id 0 | task 27834 | stop processing: n_tokens = 2050, truncated = 0 24.13.572.194 I slot print_timing: id 2 | task 27832 | prompt eval time = 8187.48 ms / 2085 tokens ( 3.93 ms per token, 254.66 tokens per second) 24.13.572.197 I slot print_timing: id 2 | task 27832 | eval time = 869.98 ms / 2 tokens ( 869.98 ms per token, 1.15 tokens per second) 24.13.572.197 I slot print_timing: id 2 | task 27832 | total time = 9057.46 ms / 2087 tokens 24.13.572.197 I slot print_timing: id 2 | task 27832 | graphs reused = 26356 24.13.572.198 I slot print_timing: id 2 | task 27832 | graph reallocs = 0 / 0 (same size) / (changed size) 24.13.572.287 I slot release: id 2 | task 27832 | stop processing: n_tokens = 2086, truncated = 0 24.13.572.345 I slot print_timing: id 3 | task 27836 | prompt processing, n_tokens = 2022, progress = 1.00, t = 4.24 s / 476.34 tokens per second 24.14.275.322 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.866 (> 0.100 thold), f_keep = 0.865 24.14.275.351 I slot launch_slot_: id 0 | task 27842 | processing task, is_child = 0 24.14.281.895 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.838 (> 0.100 thold), f_keep = 0.850 24.14.281.918 I slot launch_slot_: id 2 | task 27843 | processing task, is_child = 0 24.15.189.810 I slot print_timing: id 3 | task 27836 | prompt eval time = 4948.76 ms / 2026 tokens ( 2.44 ms per token, 409.40 tokens per second) 24.15.189.812 I slot print_timing: id 3 | task 27836 | eval time = 914.49 ms / 2 tokens ( 914.49 ms per token, 1.09 tokens per second) 24.15.189.812 I slot print_timing: id 3 | task 27836 | total time = 5863.25 ms / 2028 tokens 24.15.189.813 I slot print_timing: id 3 | task 27836 | graphs reused = 26356 24.15.189.813 I slot print_timing: id 3 | task 27836 | graph reallocs = 0 / 0 (same size) / (changed size) 24.15.189.930 I slot release: id 3 | task 27836 | stop processing: n_tokens = 2027, truncated = 0 24.15.914.174 I slot print_timing: id 1 | task 27839 | prompt eval time = 2487.23 ms / 551 tokens ( 4.51 ms per token, 221.53 tokens per second) 24.15.914.177 I slot print_timing: id 1 | task 27839 | eval time = 724.68 ms / 2 tokens ( 724.68 ms per token, 1.38 tokens per second) 24.15.914.177 I slot print_timing: id 1 | task 27839 | total time = 3211.91 ms / 553 tokens 24.15.914.178 I slot print_timing: id 1 | task 27839 | graphs reused = 26356 24.15.914.178 I slot print_timing: id 1 | task 27839 | graph reallocs = 0 / 0 (same size) / (changed size) 24.15.914.283 I slot release: id 1 | task 27839 | stop processing: n_tokens = 2107, truncated = 0 24.15.914.292 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.834 (> 0.100 thold), f_keep = 0.842 24.15.914.321 I slot launch_slot_: id 1 | task 27846 | processing task, is_child = 0 24.16.091.270 I slot print_timing: id 0 | task 27842 | prompt eval time = 1631.92 ms / 514 tokens ( 3.17 ms per token, 314.97 tokens per second) 24.16.091.275 I slot print_timing: id 0 | task 27842 | eval time = 177.42 ms / 2 tokens ( 177.42 ms per token, 5.64 tokens per second) 24.16.091.276 I slot print_timing: id 0 | task 27842 | total time = 1809.34 ms / 516 tokens 24.16.091.276 I slot print_timing: id 0 | task 27842 | graphs reused = 26356 24.16.091.277 I slot print_timing: id 0 | task 27842 | graph reallocs = 0 / 0 (same size) / (changed size) 24.16.091.382 I slot release: id 0 | task 27842 | stop processing: n_tokens = 2048, truncated = 0 24.16.091.791 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.805 (> 0.100 thold), f_keep = 0.875 24.16.091.819 I slot launch_slot_: id 3 | task 27848 | processing task, is_child = 0 24.16.096.854 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.866 24.16.096.899 I slot launch_slot_: id 0 | task 27849 | processing task, is_child = 0 24.17.840.624 I slot print_timing: id 2 | task 27843 | prompt eval time = 1809.39 ms / 547 tokens ( 3.31 ms per token, 302.31 tokens per second) 24.17.840.630 I slot print_timing: id 2 | task 27843 | eval time = 1748.83 ms / 2 tokens ( 1748.83 ms per token, 0.57 tokens per second) 24.17.840.631 I slot print_timing: id 2 | task 27843 | total time = 3558.22 ms / 549 tokens 24.17.840.631 I slot print_timing: id 2 | task 27843 | graphs reused = 26356 24.17.840.632 I slot print_timing: id 2 | task 27843 | graph reallocs = 0 / 0 (same size) / (changed size) 24.17.840.747 I slot release: id 2 | task 27843 | stop processing: n_tokens = 2117, truncated = 0 24.18.564.248 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.887 (> 0.100 thold), f_keep = 0.838 24.18.564.292 I slot launch_slot_: id 2 | task 27852 | processing task, is_child = 0 24.19.195.403 I slot print_timing: id 0 | task 27849 | prompt eval time = 2466.92 ms / 422 tokens ( 5.85 ms per token, 171.06 tokens per second) 24.19.195.407 I slot print_timing: id 0 | task 27849 | eval time = 631.58 ms / 2 tokens ( 631.58 ms per token, 1.58 tokens per second) 24.19.195.408 I slot print_timing: id 0 | task 27849 | total time = 3098.50 ms / 424 tokens 24.19.195.408 I slot print_timing: id 0 | task 27849 | graphs reused = 26356 24.19.195.409 I slot print_timing: id 0 | task 27849 | graph reallocs = 0 / 0 (same size) / (changed size) 24.19.195.513 I slot release: id 0 | task 27849 | stop processing: n_tokens = 1956, truncated = 0 24.19.195.801 I slot print_timing: id 1 | task 27846 | prompt eval time = 2644.30 ms / 536 tokens ( 4.93 ms per token, 202.70 tokens per second) 24.19.195.804 I slot print_timing: id 1 | task 27846 | eval time = 631.56 ms / 2 tokens ( 631.56 ms per token, 1.58 tokens per second) 24.19.195.805 I slot print_timing: id 1 | task 27846 | total time = 3275.86 ms / 538 tokens 24.19.195.805 I slot print_timing: id 1 | task 27846 | graphs reused = 26356 24.19.195.805 I slot print_timing: id 1 | task 27846 | graph reallocs = 0 / 0 (same size) / (changed size) 24.19.195.902 I slot release: id 1 | task 27846 | stop processing: n_tokens = 2127, truncated = 0 24.19.246.912 I slot print_timing: id 3 | task 27848 | prompt eval time = 3099.20 ms / 694 tokens ( 4.47 ms per token, 223.93 tokens per second) 24.19.246.915 I slot print_timing: id 3 | task 27848 | eval time = 50.61 ms / 2 tokens ( 50.61 ms per token, 19.76 tokens per second) 24.19.246.915 I slot print_timing: id 3 | task 27848 | total time = 3149.81 ms / 696 tokens 24.19.246.916 I slot print_timing: id 3 | task 27848 | graphs reused = 26356 24.19.246.916 I slot print_timing: id 3 | task 27848 | graph reallocs = 0 / 0 (same size) / (changed size) 24.19.247.023 I slot release: id 3 | task 27848 | stop processing: n_tokens = 2205, truncated = 0 24.19.247.032 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.906 24.19.247.057 I slot launch_slot_: id 0 | task 27855 | processing task, is_child = 0 24.19.255.485 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.865 (> 0.100 thold), f_keep = 0.834 24.19.255.518 I slot launch_slot_: id 1 | task 27856 | processing task, is_child = 0 24.19.255.618 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.848 (> 0.100 thold), f_keep = 0.805 24.19.255.635 I slot launch_slot_: id 3 | task 27857 | processing task, is_child = 0 24.21.140.869 I slot print_timing: id 2 | task 27852 | prompt eval time = 682.31 ms / 400 tokens ( 1.71 ms per token, 586.24 tokens per second) 24.21.140.872 I slot print_timing: id 2 | task 27852 | eval time = 1894.25 ms / 2 tokens ( 1894.25 ms per token, 0.53 tokens per second) 24.21.140.873 I slot print_timing: id 2 | task 27852 | total time = 2576.56 ms / 402 tokens 24.21.140.873 I slot print_timing: id 2 | task 27852 | graphs reused = 26356 24.21.140.874 I slot print_timing: id 2 | task 27852 | graph reallocs = 0 / 0 (same size) / (changed size) 24.21.140.994 I slot release: id 2 | task 27852 | stop processing: n_tokens = 2001, truncated = 0 24.21.233.335 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.886 24.21.233.370 I slot launch_slot_: id 2 | task 27860 | processing task, is_child = 0 24.21.788.990 I slot print_timing: id 0 | task 27855 | prompt eval time = 1976.98 ms / 464 tokens ( 4.26 ms per token, 234.70 tokens per second) 24.21.788.996 I slot print_timing: id 0 | task 27855 | eval time = 556.37 ms / 2 tokens ( 556.37 ms per token, 1.80 tokens per second) 24.21.788.996 I slot print_timing: id 0 | task 27855 | total time = 2533.35 ms / 466 tokens 24.21.788.996 I slot print_timing: id 0 | task 27855 | graphs reused = 26356 24.21.788.997 I slot print_timing: id 0 | task 27855 | graph reallocs = 0 / 0 (same size) / (changed size) 24.21.789.102 I slot release: id 0 | task 27855 | stop processing: n_tokens = 1998, truncated = 0 24.21.789.457 I slot print_timing: id 1 | task 27856 | prompt eval time = 1977.18 ms / 441 tokens ( 4.48 ms per token, 223.05 tokens per second) 24.21.789.458 I slot print_timing: id 1 | task 27856 | eval time = 556.51 ms / 2 tokens ( 556.51 ms per token, 1.80 tokens per second) 24.21.789.459 I slot print_timing: id 1 | task 27856 | total time = 2533.69 ms / 443 tokens 24.21.789.459 I slot print_timing: id 1 | task 27856 | graphs reused = 26356 24.21.789.459 I slot print_timing: id 1 | task 27856 | graph reallocs = 0 / 0 (same size) / (changed size) 24.21.789.549 I slot release: id 1 | task 27856 | stop processing: n_tokens = 2052, truncated = 0 24.21.789.843 I slot print_timing: id 3 | task 27857 | prompt eval time = 1977.45 ms / 403 tokens ( 4.91 ms per token, 203.80 tokens per second) 24.21.789.849 I slot print_timing: id 3 | task 27857 | eval time = 556.51 ms / 2 tokens ( 556.51 ms per token, 1.80 tokens per second) 24.21.789.850 I slot print_timing: id 3 | task 27857 | total time = 2533.97 ms / 405 tokens 24.21.789.850 I slot print_timing: id 3 | task 27857 | graphs reused = 26356 24.21.789.850 I slot print_timing: id 3 | task 27857 | graph reallocs = 0 / 0 (same size) / (changed size) 24.21.789.945 I slot release: id 3 | task 27857 | stop processing: n_tokens = 2092, truncated = 0 24.21.825.168 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.863 (> 0.100 thold), f_keep = 0.887 24.21.825.196 I slot launch_slot_: id 0 | task 27863 | processing task, is_child = 0 24.21.833.955 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.823 (> 0.100 thold), f_keep = 0.864 24.21.833.978 I slot launch_slot_: id 1 | task 27864 | processing task, is_child = 0 24.21.834.078 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.842 (> 0.100 thold), f_keep = 0.848 24.21.834.096 I slot launch_slot_: id 3 | task 27865 | processing task, is_child = 0 24.22.618.823 I slot print_timing: id 2 | task 27860 | prompt eval time = 591.78 ms / 358 tokens ( 1.65 ms per token, 604.95 tokens per second) 24.22.618.825 I slot print_timing: id 2 | task 27860 | eval time = 793.66 ms / 2 tokens ( 793.66 ms per token, 1.26 tokens per second) 24.22.618.826 I slot print_timing: id 2 | task 27860 | total time = 1385.44 ms / 360 tokens 24.22.618.826 I slot print_timing: id 2 | task 27860 | graphs reused = 26356 24.22.618.827 I slot print_timing: id 2 | task 27860 | graph reallocs = 0 / 0 (same size) / (changed size) 24.22.618.931 I slot release: id 2 | task 27860 | stop processing: n_tokens = 1959, truncated = 0 24.23.987.021 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.905 24.23.987.058 I slot launch_slot_: id 2 | task 27868 | processing task, is_child = 0 24.24.580.931 I slot print_timing: id 3 | task 27865 | prompt eval time = 2152.73 ms / 418 tokens ( 5.15 ms per token, 194.17 tokens per second) 24.24.580.934 I slot print_timing: id 3 | task 27865 | eval time = 593.91 ms / 2 tokens ( 593.91 ms per token, 1.68 tokens per second) 24.24.580.934 I slot print_timing: id 3 | task 27865 | total time = 2746.64 ms / 420 tokens 24.24.580.935 I slot print_timing: id 3 | task 27865 | graphs reused = 26356 24.24.580.935 I slot print_timing: id 3 | task 27865 | graph reallocs = 0 / 0 (same size) / (changed size) 24.24.581.099 I slot release: id 3 | task 27865 | stop processing: n_tokens = 2107, truncated = 0 24.24.642.245 I slot print_timing: id 0 | task 27863 | prompt eval time = 2746.09 ms / 521 tokens ( 5.27 ms per token, 189.72 tokens per second) 24.24.642.248 I slot print_timing: id 0 | task 27863 | eval time = 62.05 ms / 2 tokens ( 62.05 ms per token, 16.12 tokens per second) 24.24.642.248 I slot print_timing: id 0 | task 27863 | total time = 2808.14 ms / 523 tokens 24.24.642.249 I slot print_timing: id 0 | task 27863 | graphs reused = 26356 24.24.642.249 I slot print_timing: id 0 | task 27863 | graph reallocs = 0 / 0 (same size) / (changed size) 24.24.642.353 I slot release: id 0 | task 27863 | stop processing: n_tokens = 2055, truncated = 0 24.24.642.665 I slot print_timing: id 1 | task 27864 | prompt eval time = 2746.43 ms / 545 tokens ( 5.04 ms per token, 198.44 tokens per second) 24.24.642.668 I slot print_timing: id 1 | task 27864 | eval time = 62.04 ms / 2 tokens ( 62.04 ms per token, 16.12 tokens per second) 24.24.642.668 I slot print_timing: id 1 | task 27864 | total time = 2808.47 ms / 547 tokens 24.24.642.669 I slot print_timing: id 1 | task 27864 | graphs reused = 26356 24.24.642.669 I slot print_timing: id 1 | task 27864 | graph reallocs = 0 / 0 (same size) / (changed size) 24.24.642.769 I slot release: id 1 | task 27864 | stop processing: n_tokens = 2156, truncated = 0 24.24.643.184 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.820 (> 0.100 thold), f_keep = 0.842 24.24.643.210 I slot launch_slot_: id 3 | task 27871 | processing task, is_child = 0 24.24.652.294 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.878 (> 0.100 thold), f_keep = 0.863 24.24.652.317 I slot launch_slot_: id 0 | task 27873 | processing task, is_child = 0 24.24.652.410 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.822 24.24.652.428 I slot launch_slot_: id 1 | task 27872 | processing task, is_child = 0 24.26.576.323 I slot print_timing: id 2 | task 27868 | prompt eval time = 655.51 ms / 358 tokens ( 1.83 ms per token, 546.14 tokens per second) 24.26.576.325 I slot print_timing: id 2 | task 27868 | eval time = 1933.14 ms / 2 tokens ( 1933.14 ms per token, 0.52 tokens per second) 24.26.576.326 I slot print_timing: id 2 | task 27868 | total time = 2588.65 ms / 360 tokens 24.26.576.326 I slot print_timing: id 2 | task 27868 | graphs reused = 26356 24.26.576.326 I slot print_timing: id 2 | task 27868 | graph reallocs = 0 / 0 (same size) / (changed size) 24.26.576.436 I slot release: id 2 | task 27868 | stop processing: n_tokens = 1959, truncated = 0 24.26.668.794 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.885 (> 0.100 thold), f_keep = 0.906 24.26.668.847 I slot launch_slot_: id 2 | task 27876 | processing task, is_child = 0 24.27.266.356 I slot print_timing: id 0 | task 27873 | prompt eval time = 2015.60 ms / 481 tokens ( 4.19 ms per token, 238.64 tokens per second) 24.27.266.359 I slot print_timing: id 0 | task 27873 | eval time = 598.32 ms / 2 tokens ( 598.32 ms per token, 1.67 tokens per second) 24.27.266.360 I slot print_timing: id 0 | task 27873 | total time = 2613.92 ms / 483 tokens 24.27.266.360 I slot print_timing: id 0 | task 27873 | graphs reused = 26356 24.27.266.361 I slot print_timing: id 0 | task 27873 | graph reallocs = 0 / 0 (same size) / (changed size) 24.27.266.480 I slot release: id 0 | task 27873 | stop processing: n_tokens = 2020, truncated = 0 24.27.266.819 I slot print_timing: id 1 | task 27872 | prompt eval time = 2015.79 ms / 338 tokens ( 5.96 ms per token, 167.68 tokens per second) 24.27.266.822 I slot print_timing: id 1 | task 27872 | eval time = 598.49 ms / 2 tokens ( 598.49 ms per token, 1.67 tokens per second) 24.27.266.822 I slot print_timing: id 1 | task 27872 | total time = 2614.27 ms / 340 tokens 24.27.266.822 I slot print_timing: id 1 | task 27872 | graphs reused = 26356 24.27.266.823 I slot print_timing: id 1 | task 27872 | graph reallocs = 0 / 0 (same size) / (changed size) 24.27.266.909 I slot release: id 1 | task 27872 | stop processing: n_tokens = 1978, truncated = 0 24.27.267.283 I slot print_timing: id 3 | task 27871 | prompt eval time = 2016.12 ms / 475 tokens ( 4.24 ms per token, 235.60 tokens per second) 24.27.267.286 I slot print_timing: id 3 | task 27871 | eval time = 598.50 ms / 2 tokens ( 598.50 ms per token, 1.67 tokens per second) 24.27.267.287 I slot print_timing: id 3 | task 27871 | total time = 2614.62 ms / 477 tokens 24.27.267.287 I slot print_timing: id 3 | task 27871 | graphs reused = 26356 24.27.267.287 I slot print_timing: id 3 | task 27871 | graph reallocs = 0 / 0 (same size) / (changed size) 24.27.267.399 I slot release: id 3 | task 27871 | stop processing: n_tokens = 2164, truncated = 0 24.27.302.880 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.878 24.27.302.909 I slot launch_slot_: id 0 | task 27879 | processing task, is_child = 0 24.27.311.715 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.916 (> 0.100 thold), f_keep = 0.896 24.27.311.739 I slot launch_slot_: id 1 | task 27880 | processing task, is_child = 0 24.27.311.833 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.820 24.27.311.848 I slot launch_slot_: id 3 | task 27881 | processing task, is_child = 0 24.28.879.804 I slot print_timing: id 2 | task 27876 | prompt eval time = 634.01 ms / 404 tokens ( 1.57 ms per token, 637.21 tokens per second) 24.28.879.807 I slot print_timing: id 2 | task 27876 | eval time = 1576.93 ms / 2 tokens ( 1576.93 ms per token, 0.63 tokens per second) 24.28.879.808 I slot print_timing: id 2 | task 27876 | total time = 2210.94 ms / 406 tokens 24.28.879.808 I slot print_timing: id 2 | task 27876 | graphs reused = 26356 24.28.879.809 I slot print_timing: id 2 | task 27876 | graph reallocs = 0 / 0 (same size) / (changed size) 24.28.879.920 I slot release: id 2 | task 27876 | stop processing: n_tokens = 2005, truncated = 0 24.28.971.204 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 2005, t_last = 339175777026 24.28.976.591 I slot launch_slot_: id 2 | task 27884 | processing task, is_child = 0 24.30.202.616 I slot print_timing: id 0 | task 27879 | prompt eval time = 1658.66 ms / 353 tokens ( 4.70 ms per token, 212.82 tokens per second) 24.30.202.619 I slot print_timing: id 0 | task 27879 | eval time = 1232.09 ms / 2 tokens ( 1232.09 ms per token, 0.81 tokens per second) 24.30.202.619 I slot print_timing: id 0 | task 27879 | total time = 2890.76 ms / 355 tokens 24.30.202.620 I slot print_timing: id 0 | task 27879 | graphs reused = 26356 24.30.202.620 I slot print_timing: id 0 | task 27879 | graph reallocs = 0 / 0 (same size) / (changed size) 24.30.202.726 I slot release: id 0 | task 27879 | stop processing: n_tokens = 1892, truncated = 0 24.30.203.064 I slot print_timing: id 1 | task 27880 | prompt eval time = 1658.84 ms / 297 tokens ( 5.59 ms per token, 179.04 tokens per second) 24.30.203.066 I slot print_timing: id 1 | task 27880 | eval time = 1232.24 ms / 2 tokens ( 1232.24 ms per token, 0.81 tokens per second) 24.30.203.067 I slot print_timing: id 1 | task 27880 | total time = 2891.08 ms / 299 tokens 24.30.203.067 I slot print_timing: id 1 | task 27880 | graphs reused = 26356 24.30.203.068 I slot print_timing: id 1 | task 27880 | graph reallocs = 0 / 0 (same size) / (changed size) 24.30.203.153 I slot release: id 1 | task 27880 | stop processing: n_tokens = 1937, truncated = 0 24.30.203.554 I slot print_timing: id 3 | task 27881 | prompt eval time = 1659.10 ms / 289 tokens ( 5.74 ms per token, 174.19 tokens per second) 24.30.203.556 I slot print_timing: id 3 | task 27881 | eval time = 1232.35 ms / 2 tokens ( 1232.35 ms per token, 0.81 tokens per second) 24.30.203.557 I slot print_timing: id 3 | task 27881 | total time = 2891.45 ms / 291 tokens 24.30.203.557 I slot print_timing: id 3 | task 27881 | graphs reused = 26356 24.30.203.557 I slot print_timing: id 3 | task 27881 | graph reallocs = 0 / 0 (same size) / (changed size) 24.30.203.655 I slot release: id 3 | task 27881 | stop processing: n_tokens = 1978, truncated = 0 24.30.893.059 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1892, t_last = 339177099832 24.30.897.264 I slot launch_slot_: id 0 | task 27888 | processing task, is_child = 0 24.30.905.452 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1937, t_last = 339177100261 24.30.905.582 I slot launch_slot_: id 1 | task 27889 | processing task, is_child = 0 24.30.905.672 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1978, t_last = 339177100760 24.30.905.802 I slot launch_slot_: id 3 | task 27890 | processing task, is_child = 0 24.33.689.609 I slot print_timing: id 2 | task 27884 | prompt eval time = 1916.46 ms / 1430 tokens ( 1.34 ms per token, 746.17 tokens per second) 24.33.689.615 I slot print_timing: id 2 | task 27884 | eval time = 2796.55 ms / 2 tokens ( 2796.55 ms per token, 0.36 tokens per second) 24.33.689.615 I slot print_timing: id 2 | task 27884 | total time = 4713.01 ms / 1432 tokens 24.33.689.616 I slot print_timing: id 2 | task 27884 | graphs reused = 26356 24.33.689.616 I slot print_timing: id 2 | task 27884 | graph reallocs = 0 / 0 (same size) / (changed size) 24.33.689.699 I slot release: id 2 | task 27884 | stop processing: n_tokens = 1431, truncated = 0 24.34.995.791 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1431, t_last = 339180586805 24.35.644.974 I slot launch_slot_: id 2 | task 27893 | processing task, is_child = 0 24.35.644.995 I slot print_timing: id 0 | task 27888 | prompt processing, n_tokens = 1494, progress = 1.00, t = 4.09 s / 365.28 tokens per second 24.35.645.272 I slot print_timing: id 1 | task 27889 | prompt processing, n_tokens = 977, progress = 1.00, t = 4.09 s / 238.89 tokens per second 24.35.645.543 I slot print_timing: id 3 | task 27890 | prompt processing, n_tokens = 1111, progress = 0.68, t = 4.09 s / 271.66 tokens per second 24.37.152.662 I slot print_timing: id 3 | task 27890 | prompt processing, n_tokens = 1623, progress = 1.00, t = 6.25 s / 259.85 tokens per second 24.37.881.973 I slot print_timing: id 0 | task 27888 | prompt eval time = 6246.49 ms / 1498 tokens ( 4.17 ms per token, 239.81 tokens per second) 24.37.881.979 I slot print_timing: id 0 | task 27888 | eval time = 729.67 ms / 2 tokens ( 729.67 ms per token, 1.37 tokens per second) 24.37.881.979 I slot print_timing: id 0 | task 27888 | total time = 6976.16 ms / 1500 tokens 24.37.881.980 I slot print_timing: id 0 | task 27888 | graphs reused = 26356 24.37.881.980 I slot print_timing: id 0 | task 27888 | graph reallocs = 0 / 0 (same size) / (changed size) 24.37.882.061 I slot release: id 0 | task 27888 | stop processing: n_tokens = 1499, truncated = 0 24.37.882.374 I slot print_timing: id 1 | task 27889 | prompt eval time = 6246.65 ms / 981 tokens ( 6.37 ms per token, 157.04 tokens per second) 24.37.882.383 I slot print_timing: id 1 | task 27889 | eval time = 729.77 ms / 2 tokens ( 729.77 ms per token, 1.37 tokens per second) 24.37.882.383 I slot print_timing: id 1 | task 27889 | total time = 6976.42 ms / 983 tokens 24.37.882.384 I slot print_timing: id 1 | task 27889 | graphs reused = 26356 24.37.882.384 I slot print_timing: id 1 | task 27889 | graph reallocs = 0 / 0 (same size) / (changed size) 24.37.882.439 I slot release: id 1 | task 27889 | stop processing: n_tokens = 982, truncated = 0 24.37.932.925 I slot print_timing: id 3 | task 27890 | prompt eval time = 6976.73 ms / 1627 tokens ( 4.29 ms per token, 233.20 tokens per second) 24.37.932.928 I slot print_timing: id 3 | task 27890 | eval time = 50.10 ms / 2 tokens ( 50.10 ms per token, 19.96 tokens per second) 24.37.932.929 I slot print_timing: id 3 | task 27890 | total time = 7026.83 ms / 1629 tokens 24.37.932.929 I slot print_timing: id 3 | task 27890 | graphs reused = 26356 24.37.932.929 I slot print_timing: id 3 | task 27890 | graph reallocs = 0 / 0 (same size) / (changed size) 24.37.933.016 I slot release: id 3 | task 27890 | stop processing: n_tokens = 1628, truncated = 0 24.37.933.037 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.878 24.37.933.062 I slot launch_slot_: id 1 | task 27898 | processing task, is_child = 0 24.37.939.938 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1499, t_last = 339184779167 24.37.940.052 I slot launch_slot_: id 0 | task 27897 | processing task, is_child = 0 24.37.940.125 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1628, t_last = 339184830123 24.37.940.218 I slot launch_slot_: id 3 | task 27899 | processing task, is_child = 0 24.39.876.116 I slot print_timing: id 2 | task 27893 | prompt eval time = 2287.20 ms / 969 tokens ( 2.36 ms per token, 423.66 tokens per second) 24.39.876.119 I slot print_timing: id 2 | task 27893 | eval time = 1943.47 ms / 2 tokens ( 1943.47 ms per token, 0.51 tokens per second) 24.39.876.120 I slot print_timing: id 2 | task 27893 | total time = 4230.67 ms / 971 tokens 24.39.876.120 I slot print_timing: id 2 | task 27893 | graphs reused = 26356 24.39.876.120 I slot print_timing: id 2 | task 27893 | graph reallocs = 0 / 0 (same size) / (changed size) 24.39.876.190 I slot release: id 2 | task 27893 | stop processing: n_tokens = 970, truncated = 0 24.41.219.823 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.888 24.41.219.858 I slot launch_slot_: id 2 | task 27902 | processing task, is_child = 0 24.41.219.865 I slot print_timing: id 0 | task 27897 | prompt processing, n_tokens = 939, progress = 1.00, t = 3.28 s / 286.35 tokens per second 24.41.220.142 I slot print_timing: id 3 | task 27899 | prompt processing, n_tokens = 960, progress = 1.00, t = 3.28 s / 292.77 tokens per second 24.41.963.170 I slot print_timing: id 1 | task 27898 | prompt eval time = 3279.47 ms / 493 tokens ( 6.65 ms per token, 150.33 tokens per second) 24.41.963.172 I slot print_timing: id 1 | task 27898 | eval time = 743.35 ms / 2 tokens ( 743.35 ms per token, 1.35 tokens per second) 24.41.963.173 I slot print_timing: id 1 | task 27898 | total time = 4022.83 ms / 495 tokens 24.41.963.174 I slot print_timing: id 1 | task 27898 | graphs reused = 26356 24.41.963.174 I slot print_timing: id 1 | task 27898 | graph reallocs = 0 / 0 (same size) / (changed size) 24.41.963.231 I slot release: id 1 | task 27898 | stop processing: n_tokens = 959, truncated = 0 24.42.027.637 I slot print_timing: id 0 | task 27897 | prompt eval time = 4022.65 ms / 943 tokens ( 4.27 ms per token, 234.42 tokens per second) 24.42.027.642 I slot print_timing: id 0 | task 27897 | eval time = 64.76 ms / 2 tokens ( 64.76 ms per token, 15.44 tokens per second) 24.42.027.643 I slot print_timing: id 0 | task 27897 | total time = 4087.41 ms / 945 tokens 24.42.027.643 I slot print_timing: id 0 | task 27897 | graphs reused = 26356 24.42.027.643 I slot print_timing: id 0 | task 27897 | graph reallocs = 0 / 0 (same size) / (changed size) 24.42.027.705 I slot release: id 0 | task 27897 | stop processing: n_tokens = 944, truncated = 0 24.42.028.425 I slot print_timing: id 3 | task 27899 | prompt eval time = 4023.07 ms / 964 tokens ( 4.17 ms per token, 239.62 tokens per second) 24.42.028.430 I slot print_timing: id 3 | task 27899 | eval time = 64.88 ms / 2 tokens ( 64.88 ms per token, 15.41 tokens per second) 24.42.028.430 I slot print_timing: id 3 | task 27899 | total time = 4087.95 ms / 966 tokens 24.42.028.430 I slot print_timing: id 3 | task 27899 | graphs reused = 26356 24.42.028.431 I slot print_timing: id 3 | task 27899 | graph reallocs = 0 / 0 (same size) / (changed size) 24.42.028.477 I slot release: id 3 | task 27899 | stop processing: n_tokens = 965, truncated = 0 24.42.028.482 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.912 24.42.028.513 I slot launch_slot_: id 0 | task 27905 | processing task, is_child = 0 24.42.131.083 I slot print_timing: id 2 | task 27902 | prompt eval time = 808.09 ms / 500 tokens ( 1.62 ms per token, 618.74 tokens per second) 24.42.131.089 I slot print_timing: id 2 | task 27902 | eval time = 102.96 ms / 2 tokens ( 102.96 ms per token, 9.71 tokens per second) 24.42.131.090 I slot print_timing: id 2 | task 27902 | total time = 911.05 ms / 502 tokens 24.42.131.090 I slot print_timing: id 2 | task 27902 | graphs reused = 26356 24.42.131.090 I slot print_timing: id 2 | task 27902 | graph reallocs = 0 / 0 (same size) / (changed size) 24.42.131.145 I slot release: id 2 | task 27902 | stop processing: n_tokens = 954, truncated = 0 24.42.131.149 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 959, t_last = 339188860336 24.42.131.238 I slot launch_slot_: id 1 | task 27906 | processing task, is_child = 0 24.42.134.059 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 965, t_last = 339188925582 24.42.134.138 I slot launch_slot_: id 3 | task 27908 | processing task, is_child = 0 24.44.630.663 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 954, t_last = 339189028250 24.44.630.788 I slot launch_slot_: id 2 | task 27910 | processing task, is_child = 0 24.47.885.621 I slot print_timing: id 1 | task 27906 | prompt processing, n_tokens = 785, progress = 0.99, t = 5.75 s / 136.50 tokens per second 24.47.885.766 I slot print_timing: id 2 | task 27910 | prompt processing, n_tokens = 1062, progress = 0.67, t = 3.02 s / 351.72 tokens per second 24.47.885.812 I slot print_timing: id 3 | task 27908 | prompt processing, n_tokens = 1577, progress = 0.97, t = 5.75 s / 274.22 tokens per second 24.48.849.793 I slot print_timing: id 0 | task 27905 | prompt eval time = 5852.74 ms / 530 tokens ( 11.04 ms per token, 90.56 tokens per second) 24.48.849.798 I slot print_timing: id 0 | task 27905 | eval time = 964.19 ms / 2 tokens ( 964.19 ms per token, 1.04 tokens per second) 24.48.849.798 I slot print_timing: id 0 | task 27905 | total time = 6816.93 ms / 532 tokens 24.48.849.799 I slot print_timing: id 0 | task 27905 | graphs reused = 26357 24.48.849.799 I slot print_timing: id 0 | task 27905 | graph reallocs = 0 / 0 (same size) / (changed size) 24.48.849.859 I slot release: id 0 | task 27905 | stop processing: n_tokens = 958, truncated = 0 24.48.850.186 I slot print_timing: id 2 | task 27910 | prompt processing, n_tokens = 1574, progress = 1.00, t = 3.98 s / 395.12 tokens per second 24.48.850.440 I slot print_timing: id 3 | task 27908 | prompt processing, n_tokens = 1619, progress = 1.00, t = 6.72 s / 241.10 tokens per second 24.48.928.783 I slot print_timing: id 1 | task 27906 | prompt eval time = 6715.93 ms / 789 tokens ( 8.51 ms per token, 117.48 tokens per second) 24.48.928.786 I slot print_timing: id 1 | task 27906 | eval time = 78.61 ms / 2 tokens ( 78.61 ms per token, 12.72 tokens per second) 24.48.928.786 I slot print_timing: id 1 | task 27906 | total time = 6794.54 ms / 791 tokens 24.48.928.787 I slot print_timing: id 1 | task 27906 | graphs reused = 26357 24.48.928.787 I slot print_timing: id 1 | task 27906 | graph reallocs = 0 / 0 (same size) / (changed size) 24.48.928.833 I slot release: id 1 | task 27906 | stop processing: n_tokens = 790, truncated = 0 24.48.929.731 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 958, t_last = 339195746964 24.48.933.733 I slot launch_slot_: id 0 | task 27914 | processing task, is_child = 0 24.48.936.120 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 790, t_last = 339195825938 24.48.936.194 I slot launch_slot_: id 1 | task 27915 | processing task, is_child = 0 24.51.640.742 I slot print_timing: id 2 | task 27910 | prompt eval time = 4063.39 ms / 1578 tokens ( 2.58 ms per token, 388.35 tokens per second) 24.51.640.745 I slot print_timing: id 2 | task 27910 | eval time = 2711.49 ms / 2 tokens ( 2711.49 ms per token, 0.37 tokens per second) 24.51.640.746 I slot print_timing: id 2 | task 27910 | total time = 6774.89 ms / 1580 tokens 24.51.640.750 I slot print_timing: id 2 | task 27910 | graphs reused = 26357 24.51.640.750 I slot print_timing: id 2 | task 27910 | graph reallocs = 0 / 0 (same size) / (changed size) 24.51.640.851 I slot release: id 2 | task 27910 | stop processing: n_tokens = 1579, truncated = 0 24.51.641.302 I slot print_timing: id 3 | task 27908 | prompt eval time = 6795.41 ms / 1623 tokens ( 4.19 ms per token, 238.84 tokens per second) 24.51.641.304 I slot print_timing: id 3 | task 27908 | eval time = 2711.57 ms / 2 tokens ( 2711.57 ms per token, 0.37 tokens per second) 24.51.641.305 I slot print_timing: id 3 | task 27908 | total time = 9506.98 ms / 1625 tokens 24.51.641.305 I slot print_timing: id 3 | task 27908 | graphs reused = 26357 24.51.641.306 I slot print_timing: id 3 | task 27908 | graph reallocs = 0 / 0 (same size) / (changed size) 24.51.641.387 I slot release: id 3 | task 27908 | stop processing: n_tokens = 1624, truncated = 0 24.52.128.105 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1579, t_last = 339198537957 24.52.616.182 I slot launch_slot_: id 2 | task 27918 | processing task, is_child = 0 24.52.622.058 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.812 (> 0.100 thold), f_keep = 0.861 24.52.622.083 I slot launch_slot_: id 3 | task 27919 | processing task, is_child = 0 24.52.622.089 I slot print_timing: id 0 | task 27914 | prompt processing, n_tokens = 1606, progress = 1.00, t = 3.19 s / 503.15 tokens per second 24.52.622.324 I slot print_timing: id 1 | task 27915 | prompt processing, n_tokens = 1117, progress = 0.68, t = 3.19 s / 349.96 tokens per second 24.54.064.655 I slot print_timing: id 1 | task 27915 | prompt processing, n_tokens = 1629, progress = 1.00, t = 5.13 s / 317.67 tokens per second 24.55.472.643 I slot print_timing: id 0 | task 27914 | prompt eval time = 5128.44 ms / 1610 tokens ( 3.19 ms per token, 313.94 tokens per second) 24.55.472.648 I slot print_timing: id 0 | task 27914 | eval time = 1407.99 ms / 2 tokens ( 1407.99 ms per token, 0.71 tokens per second) 24.55.472.649 I slot print_timing: id 0 | task 27914 | total time = 6536.44 ms / 1612 tokens 24.55.472.651 I slot print_timing: id 0 | task 27914 | graphs reused = 26357 24.55.472.652 I slot print_timing: id 0 | task 27914 | graph reallocs = 0 / 0 (same size) / (changed size) 24.55.472.741 I slot release: id 0 | task 27914 | stop processing: n_tokens = 1611, truncated = 0 24.55.551.921 I slot print_timing: id 1 | task 27915 | prompt eval time = 6536.81 ms / 1633 tokens ( 4.00 ms per token, 249.82 tokens per second) 24.55.551.923 I slot print_timing: id 1 | task 27915 | eval time = 78.83 ms / 2 tokens ( 78.83 ms per token, 12.69 tokens per second) 24.55.551.923 I slot print_timing: id 1 | task 27915 | total time = 6615.63 ms / 1635 tokens 24.55.551.924 I slot print_timing: id 1 | task 27915 | graphs reused = 26357 24.55.551.924 I slot print_timing: id 1 | task 27915 | graph reallocs = 0 / 0 (same size) / (changed size) 24.55.552.011 I slot release: id 1 | task 27915 | stop processing: n_tokens = 1634, truncated = 0 24.55.552.654 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1611, t_last = 339202369847 24.55.558.108 I slot launch_slot_: id 0 | task 27923 | processing task, is_child = 0 24.55.563.237 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1634, t_last = 339202449117 24.55.563.348 I slot launch_slot_: id 1 | task 27924 | processing task, is_child = 0 24.56.631.089 I slot print_timing: id 2 | task 27918 | prompt eval time = 2929.95 ms / 826 tokens ( 3.55 ms per token, 281.92 tokens per second) 24.56.631.091 I slot print_timing: id 2 | task 27918 | eval time = 1078.76 ms / 2 tokens ( 1078.76 ms per token, 0.93 tokens per second) 24.56.631.092 I slot print_timing: id 2 | task 27918 | total time = 4008.72 ms / 828 tokens 24.56.631.093 I slot print_timing: id 2 | task 27918 | graphs reused = 26357 24.56.631.093 I slot print_timing: id 2 | task 27918 | graph reallocs = 0 / 0 (same size) / (changed size) 24.56.631.141 I slot release: id 2 | task 27918 | stop processing: n_tokens = 827, truncated = 0 24.56.631.607 I slot print_timing: id 3 | task 27919 | prompt eval time = 2930.17 ms / 616 tokens ( 4.76 ms per token, 210.23 tokens per second) 24.56.631.609 I slot print_timing: id 3 | task 27919 | eval time = 1078.95 ms / 2 tokens ( 1078.95 ms per token, 0.93 tokens per second) 24.56.631.609 I slot print_timing: id 3 | task 27919 | total time = 4009.12 ms / 618 tokens 24.56.631.609 I slot print_timing: id 3 | task 27919 | graphs reused = 26357 24.56.631.610 I slot print_timing: id 3 | task 27919 | graph reallocs = 0 / 0 (same size) / (changed size) 24.56.631.706 I slot release: id 3 | task 27919 | stop processing: n_tokens = 1724, truncated = 0 24.57.278.572 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 827, t_last = 339203528246 24.57.925.280 I slot launch_slot_: id 2 | task 27927 | processing task, is_child = 0 24.57.933.260 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1724, t_last = 339203528812 24.57.933.384 I slot launch_slot_: id 3 | task 27928 | processing task, is_child = 0 25.00.388.291 I slot print_timing: id 0 | task 27923 | prompt eval time = 3499.88 ms / 854 tokens ( 4.10 ms per token, 244.01 tokens per second) 25.00.388.297 I slot print_timing: id 0 | task 27923 | eval time = 1325.05 ms / 2 tokens ( 1325.05 ms per token, 0.75 tokens per second) 25.00.388.298 I slot print_timing: id 0 | task 27923 | total time = 4824.93 ms / 856 tokens 25.00.388.298 I slot print_timing: id 0 | task 27923 | graphs reused = 26357 25.00.388.299 I slot print_timing: id 0 | task 27923 | graph reallocs = 0 / 0 (same size) / (changed size) 25.00.388.352 I slot release: id 0 | task 27923 | stop processing: n_tokens = 855, truncated = 0 25.00.388.696 I slot print_timing: id 1 | task 27924 | prompt eval time = 3500.09 ms / 828 tokens ( 4.23 ms per token, 236.57 tokens per second) 25.00.388.698 I slot print_timing: id 1 | task 27924 | eval time = 1325.12 ms / 2 tokens ( 1325.12 ms per token, 0.75 tokens per second) 25.00.388.699 I slot print_timing: id 1 | task 27924 | total time = 4825.21 ms / 830 tokens 25.00.388.699 I slot print_timing: id 1 | task 27924 | graphs reused = 26357 25.00.388.699 I slot print_timing: id 1 | task 27924 | graph reallocs = 0 / 0 (same size) / (changed size) 25.00.388.740 I slot release: id 1 | task 27924 | stop processing: n_tokens = 829, truncated = 0 25.00.445.889 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 855, t_last = 339207285457 25.00.448.575 I slot launch_slot_: id 0 | task 27932 | processing task, is_child = 0 25.00.450.902 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 829, t_last = 339207285845 25.00.450.977 I slot launch_slot_: id 1 | task 27933 | processing task, is_child = 0 25.01.191.418 I slot print_timing: id 2 | task 27927 | prompt eval time = 2511.83 ms / 867 tokens ( 2.90 ms per token, 345.17 tokens per second) 25.01.191.422 I slot print_timing: id 2 | task 27927 | eval time = 745.88 ms / 2 tokens ( 745.88 ms per token, 1.34 tokens per second) 25.01.191.423 I slot print_timing: id 2 | task 27927 | total time = 3257.71 ms / 869 tokens 25.01.191.423 I slot print_timing: id 2 | task 27927 | graphs reused = 26357 25.01.191.424 I slot print_timing: id 2 | task 27927 | graph reallocs = 0 / 0 (same size) / (changed size) 25.01.191.474 I slot release: id 2 | task 27927 | stop processing: n_tokens = 868, truncated = 0 25.01.191.879 I slot print_timing: id 3 | task 27928 | prompt eval time = 2512.12 ms / 847 tokens ( 2.97 ms per token, 337.17 tokens per second) 25.01.191.882 I slot print_timing: id 3 | task 27928 | eval time = 745.99 ms / 2 tokens ( 745.99 ms per token, 1.34 tokens per second) 25.01.191.882 I slot print_timing: id 3 | task 27928 | total time = 3258.11 ms / 849 tokens 25.01.191.882 I slot print_timing: id 3 | task 27928 | graphs reused = 26357 25.01.191.883 I slot print_timing: id 3 | task 27928 | graph reallocs = 0 / 0 (same size) / (changed size) 25.01.191.924 I slot release: id 3 | task 27928 | stop processing: n_tokens = 848, truncated = 0 25.01.833.072 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 868, t_last = 339208088579 25.02.476.176 I slot launch_slot_: id 2 | task 27936 | processing task, is_child = 0 25.02.479.717 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 848, t_last = 339208089029 25.02.479.798 I slot launch_slot_: id 3 | task 27937 | processing task, is_child = 0 25.04.470.302 I slot print_timing: id 0 | task 27932 | prompt eval time = 2701.90 ms / 759 tokens ( 3.56 ms per token, 280.91 tokens per second) 25.04.470.305 I slot print_timing: id 0 | task 27932 | eval time = 1317.42 ms / 2 tokens ( 1317.42 ms per token, 0.76 tokens per second) 25.04.470.306 I slot print_timing: id 0 | task 27932 | total time = 4019.31 ms / 761 tokens 25.04.470.307 I slot print_timing: id 0 | task 27932 | graphs reused = 26357 25.04.470.307 I slot print_timing: id 0 | task 27932 | graph reallocs = 0 / 0 (same size) / (changed size) 25.04.470.359 I slot release: id 0 | task 27932 | stop processing: n_tokens = 760, truncated = 0 25.04.470.778 I slot print_timing: id 1 | task 27933 | prompt eval time = 2702.27 ms / 728 tokens ( 3.71 ms per token, 269.40 tokens per second) 25.04.470.781 I slot print_timing: id 1 | task 27933 | eval time = 1317.46 ms / 2 tokens ( 1317.46 ms per token, 0.76 tokens per second) 25.04.470.781 I slot print_timing: id 1 | task 27933 | total time = 4019.73 ms / 730 tokens 25.04.470.781 I slot print_timing: id 1 | task 27933 | graphs reused = 26357 25.04.470.782 I slot print_timing: id 1 | task 27933 | graph reallocs = 0 / 0 (same size) / (changed size) 25.04.470.817 I slot release: id 1 | task 27933 | stop processing: n_tokens = 729, truncated = 0 25.04.528.592 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 760, t_last = 339211367464 25.04.530.819 I slot launch_slot_: id 0 | task 27941 | processing task, is_child = 0 25.04.850.295 I slot print_timing: id 2 | task 27936 | prompt eval time = 2048.12 ms / 700 tokens ( 2.93 ms per token, 341.78 tokens per second) 25.04.850.299 I slot print_timing: id 2 | task 27936 | eval time = 322.12 ms / 2 tokens ( 322.12 ms per token, 3.10 tokens per second) 25.04.850.300 I slot print_timing: id 2 | task 27936 | total time = 2370.24 ms / 702 tokens 25.04.850.300 I slot print_timing: id 2 | task 27936 | graphs reused = 26357 25.04.850.301 I slot print_timing: id 2 | task 27936 | graph reallocs = 0 / 0 (same size) / (changed size) 25.04.850.346 I slot release: id 2 | task 27936 | stop processing: n_tokens = 701, truncated = 0 25.04.850.746 I slot print_timing: id 3 | task 27937 | prompt eval time = 2048.47 ms / 682 tokens ( 3.00 ms per token, 332.93 tokens per second) 25.04.850.748 I slot print_timing: id 3 | task 27937 | eval time = 322.16 ms / 2 tokens ( 322.16 ms per token, 3.10 tokens per second) 25.04.850.748 I slot print_timing: id 3 | task 27937 | total time = 2370.63 ms / 684 tokens 25.04.850.749 I slot print_timing: id 3 | task 27937 | graphs reused = 26357 25.04.850.749 I slot print_timing: id 3 | task 27937 | graph reallocs = 0 / 0 (same size) / (changed size) 25.04.850.777 I slot release: id 3 | task 27937 | stop processing: n_tokens = 683, truncated = 0 25.05.546.236 I slot print_timing: id 0 | task 27941 | prompt eval time = 996.69 ms / 665 tokens ( 1.50 ms per token, 667.21 tokens per second) 25.05.546.242 I slot print_timing: id 0 | task 27941 | eval time = 16.69 ms / 2 tokens ( 16.69 ms per token, 59.92 tokens per second) 25.05.546.242 I slot print_timing: id 0 | task 27941 | total time = 1013.37 ms / 667 tokens 25.05.546.243 I slot print_timing: id 0 | task 27941 | graphs reused = 26357 25.05.546.243 I slot print_timing: id 0 | task 27941 | graph reallocs = 0 / 0 (same size) / (changed size) 25.05.546.279 I slot release: id 0 | task 27941 | stop processing: n_tokens = 666, truncated = 0 25.08.490.083 I srv operator(): operator(): cleaning up before exit...