/Users/minipro/quantdiff/llama.cpp/llama-b11770/llama-server -m /Users/minipro/quantdiff/models/campaign/8c2a45ff85e7/Qwen3.8-27B-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 0.00.105.725 W Setting 'enable_thinking' via --chat-template-kwargs is deprecated. Use --reasoning on / --reasoning off instead. 0.00.105.779 I srv llama_server: initializing ... 0.00.105.784 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.105.867 I srv init_listene: The UI is disabled 0.00.105.869 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.105.912 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) 0.00.107.590 I srv load_model: loading model '/Users/minipro/quantdiff/models/campaign/8c2a45ff85e7/Qwen3.8-27B-UD-Q3_K_XL.gguf' 0.00.641.019 W model has unused tensor blk.64.attn_norm.weight (size = 20480 bytes) -- ignoring 0.00.641.030 W model has unused tensor blk.64.post_attention_norm.weight (size = 20480 bytes) -- ignoring 0.00.641.037 W model has unused tensor blk.64.attn_q.weight (size = 51609600 bytes) -- ignoring 0.00.641.039 W model has unused tensor blk.64.attn_k.weight (size = 5570560 bytes) -- ignoring 0.00.641.042 W model has unused tensor blk.64.attn_v.weight (size = 5570560 bytes) -- ignoring 0.00.641.049 W model has unused tensor blk.64.attn_output.weight (size = 25804800 bytes) -- ignoring 0.00.641.052 W model has unused tensor blk.64.attn_q_norm.weight (size = 1024 bytes) -- ignoring 0.00.641.054 W model has unused tensor blk.64.attn_k_norm.weight (size = 1024 bytes) -- ignoring 0.00.641.056 W model has unused tensor blk.64.ffn_gate.weight (size = 73113600 bytes) -- ignoring 0.00.641.058 W model has unused tensor blk.64.ffn_down.weight (size = 73113600 bytes) -- ignoring 0.00.641.060 W model has unused tensor blk.64.ffn_up.weight (size = 73113600 bytes) -- ignoring 0.00.641.064 W model has unused tensor blk.64.nextn.eh_proj.weight (size = 43008000 bytes) -- ignoring 0.00.641.066 W model has unused tensor blk.64.nextn.enorm.weight (size = 20480 bytes) -- ignoring 0.00.641.068 W model has unused tensor blk.64.nextn.hnorm.weight (size = 20480 bytes) -- ignoring 0.00.641.075 W model has unused tensor blk.64.nextn.shared_head_norm.weight (size = 20480 bytes) -- ignoring 0.01.339.912 I cmn init: llama threadpool init, n_threads = 8 0.01.747.251 I srv load_model: initializing, n_slots = 4, n_ctx_slot = 4096, kv_unified = 'false' 0.01.751.112 W srv init: chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve) 0.01.751.128 I srv llama_server: model loaded 0.01.751.134 I srv llama_server: listening on http://127.0.0.1:8091 0.31.939.843 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.31.939.873 I slot launch_slot_: id 0 | task 2 | processing task, is_child = 0 0.31.939.874 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.31.939.887 I slot launch_slot_: id 1 | task 3 | processing task, is_child = 0 0.31.939.887 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.31.939.899 I slot launch_slot_: id 2 | task 0 | processing task, is_child = 0 0.31.939.900 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.31.939.911 I slot launch_slot_: id 3 | task 1 | processing task, is_child = 0 0.37.485.071 I slot print_timing: id 0 | task 2 | prompt processing, n_tokens = 118, progress = 0.97, t = 5.55 s / 21.28 tokens per second 0.37.659.570 I slot print_timing: id 1 | task 3 | prompt processing, n_tokens = 126, progress = 0.97, t = 5.55 s / 22.72 tokens per second 0.37.671.161 I slot print_timing: id 2 | task 0 | prompt processing, n_tokens = 111, progress = 0.97, t = 5.55 s / 20.02 tokens per second 0.37.682.537 I slot print_timing: id 3 | task 1 | prompt processing, n_tokens = 111, progress = 0.97, t = 5.55 s / 20.02 tokens per second 0.38.309.962 I slot print_timing: id 0 | task 2 | prompt eval time = 6164.02 ms / 122 tokens ( 50.52 ms per token, 19.79 tokens per second) 0.38.309.967 I slot print_timing: id 0 | task 2 | eval time = 206.02 ms / 2 tokens ( 206.02 ms per token, 4.85 tokens per second) 0.38.309.968 I slot print_timing: id 0 | task 2 | total time = 6370.04 ms / 124 tokens 0.38.309.968 I slot print_timing: id 0 | task 2 | graphs reused = 1 0.38.309.969 I slot print_timing: id 0 | task 2 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.309.989 I slot release: id 0 | task 2 | stop processing: n_tokens = 123, truncated = 0 0.38.310.143 I slot print_timing: id 1 | task 3 | prompt eval time = 6164.31 ms / 130 tokens ( 47.42 ms per token, 21.09 tokens per second) 0.38.310.147 I slot print_timing: id 1 | task 3 | eval time = 205.91 ms / 2 tokens ( 205.91 ms per token, 4.86 tokens per second) 0.38.310.147 I slot print_timing: id 1 | task 3 | total time = 6370.22 ms / 132 tokens 0.38.310.147 I slot print_timing: id 1 | task 3 | graphs reused = 1 0.38.310.148 I slot print_timing: id 1 | task 3 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.310.158 I slot release: id 1 | task 3 | stop processing: n_tokens = 131, truncated = 0 0.38.310.344 I slot print_timing: id 2 | task 0 | prompt eval time = 6164.62 ms / 115 tokens ( 53.61 ms per token, 18.65 tokens per second) 0.38.310.346 I slot print_timing: id 2 | task 0 | eval time = 205.79 ms / 2 tokens ( 205.79 ms per token, 4.86 tokens per second) 0.38.310.347 I slot print_timing: id 2 | task 0 | total time = 6370.41 ms / 117 tokens 0.38.310.347 I slot print_timing: id 2 | task 0 | graphs reused = 1 0.38.310.348 I slot print_timing: id 2 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.310.357 I slot release: id 2 | task 0 | stop processing: n_tokens = 116, truncated = 0 0.38.310.520 I slot print_timing: id 3 | task 1 | prompt eval time = 6165.15 ms / 115 tokens ( 53.61 ms per token, 18.65 tokens per second) 0.38.310.523 I slot print_timing: id 3 | task 1 | eval time = 205.44 ms / 2 tokens ( 205.44 ms per token, 4.87 tokens per second) 0.38.310.523 I slot print_timing: id 3 | task 1 | total time = 6370.59 ms / 117 tokens 0.38.310.524 I slot print_timing: id 3 | task 1 | graphs reused = 1 0.38.310.524 I slot print_timing: id 3 | task 1 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.310.531 I slot release: id 3 | task 1 | stop processing: n_tokens = 116, truncated = 0 0.38.319.816 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.191 (> 0.100 thold), f_keep = 0.236 0.38.342.130 I slot launch_slot_: id 0 | task 7 | processing task, is_child = 0 0.38.410.440 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.269 (> 0.100 thold), f_keep = 0.221 0.38.410.522 I slot launch_slot_: id 1 | task 8 | processing task, is_child = 0 0.38.410.558 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.241 0.38.410.603 I slot launch_slot_: id 2 | task 9 | processing task, is_child = 0 0.38.410.624 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.140 (> 0.100 thold), f_keep = 0.241 0.38.410.655 I slot launch_slot_: id 3 | task 10 | processing task, is_child = 0 0.45.331.956 I slot print_timing: id 0 | task 7 | prompt processing, n_tokens = 148, progress = 0.97, t = 6.92 s / 21.38 tokens per second 0.46.091.858 I slot print_timing: id 1 | task 8 | prompt processing, n_tokens = 104, progress = 0.96, t = 6.92 s / 15.03 tokens per second 0.46.096.280 I slot print_timing: id 2 | task 9 | prompt processing, n_tokens = 156, progress = 0.97, t = 6.92 s / 22.54 tokens per second 0.46.100.676 I slot print_timing: id 3 | task 10 | prompt processing, n_tokens = 196, progress = 0.98, t = 6.92 s / 28.32 tokens per second 0.46.649.088 I slot print_timing: id 0 | task 7 | prompt eval time = 8033.95 ms / 152 tokens ( 52.85 ms per token, 18.92 tokens per second) 0.46.649.093 I slot print_timing: id 0 | task 7 | eval time = 204.47 ms / 2 tokens ( 204.47 ms per token, 4.89 tokens per second) 0.46.649.093 I slot print_timing: id 0 | task 7 | total time = 8238.42 ms / 154 tokens 0.46.649.093 I slot print_timing: id 0 | task 7 | graphs reused = 1 0.46.649.094 I slot print_timing: id 0 | task 7 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.649.116 I slot release: id 0 | task 7 | stop processing: n_tokens = 153, truncated = 0 0.46.649.268 I slot print_timing: id 1 | task 8 | prompt eval time = 8034.09 ms / 108 tokens ( 74.39 ms per token, 13.44 tokens per second) 0.46.649.273 I slot print_timing: id 1 | task 8 | eval time = 204.50 ms / 2 tokens ( 204.50 ms per token, 4.89 tokens per second) 0.46.649.273 I slot print_timing: id 1 | task 8 | total time = 8238.59 ms / 110 tokens 0.46.649.273 I slot print_timing: id 1 | task 8 | graphs reused = 1 0.46.649.274 I slot print_timing: id 1 | task 8 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.649.285 I slot release: id 1 | task 8 | stop processing: n_tokens = 109, truncated = 0 0.46.649.450 I slot print_timing: id 2 | task 9 | prompt eval time = 8034.24 ms / 160 tokens ( 50.21 ms per token, 19.91 tokens per second) 0.46.649.455 I slot print_timing: id 2 | task 9 | eval time = 204.51 ms / 2 tokens ( 204.51 ms per token, 4.89 tokens per second) 0.46.649.456 I slot print_timing: id 2 | task 9 | total time = 8238.76 ms / 162 tokens 0.46.649.456 I slot print_timing: id 2 | task 9 | graphs reused = 1 0.46.649.456 I slot print_timing: id 2 | task 9 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.649.466 I slot release: id 2 | task 9 | stop processing: n_tokens = 161, truncated = 0 0.46.649.647 I slot print_timing: id 3 | task 10 | prompt eval time = 8034.39 ms / 200 tokens ( 40.17 ms per token, 24.89 tokens per second) 0.46.649.648 I slot print_timing: id 3 | task 10 | eval time = 204.55 ms / 2 tokens ( 204.55 ms per token, 4.89 tokens per second) 0.46.649.648 I slot print_timing: id 3 | task 10 | total time = 8238.94 ms / 202 tokens 0.46.649.648 I slot print_timing: id 3 | task 10 | graphs reused = 1 0.46.649.649 I slot print_timing: id 3 | task 10 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.649.659 I slot release: id 3 | task 10 | stop processing: n_tokens = 201, truncated = 0 0.46.655.442 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.239 (> 0.100 thold), f_keep = 0.183 0.46.679.423 I slot launch_slot_: id 0 | task 14 | processing task, is_child = 0 0.46.747.032 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.246 (> 0.100 thold), f_keep = 0.266 0.46.747.105 I slot launch_slot_: id 1 | task 15 | processing task, is_child = 0 0.46.747.143 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.224 (> 0.100 thold), f_keep = 0.174 0.46.747.176 I slot launch_slot_: id 2 | task 16 | processing task, is_child = 0 0.46.747.196 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.187 (> 0.100 thold), f_keep = 0.139 0.46.747.229 I slot launch_slot_: id 3 | task 17 | processing task, is_child = 0 0.52.627.465 I slot print_timing: id 0 | task 14 | prompt processing, n_tokens = 113, progress = 0.97, t = 5.88 s / 19.22 tokens per second 0.53.055.318 I slot print_timing: id 1 | task 15 | prompt processing, n_tokens = 114, progress = 0.97, t = 5.88 s / 19.39 tokens per second 0.53.059.877 I slot print_timing: id 2 | task 16 | prompt processing, n_tokens = 121, progress = 0.97, t = 5.88 s / 20.58 tokens per second 0.53.064.668 I slot print_timing: id 3 | task 17 | prompt processing, n_tokens = 146, progress = 0.97, t = 5.88 s / 24.83 tokens per second 0.53.613.648 I slot print_timing: id 0 | task 14 | prompt eval time = 6661.86 ms / 117 tokens ( 56.94 ms per token, 17.56 tokens per second) 0.53.613.650 I slot print_timing: id 0 | task 14 | eval time = 204.54 ms / 2 tokens ( 204.54 ms per token, 4.89 tokens per second) 0.53.613.650 I slot print_timing: id 0 | task 14 | total time = 6866.40 ms / 119 tokens 0.53.613.651 I slot print_timing: id 0 | task 14 | graphs reused = 1 0.53.613.651 I slot print_timing: id 0 | task 14 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.613.670 I slot release: id 0 | task 14 | stop processing: n_tokens = 118, truncated = 0 0.53.613.824 I slot print_timing: id 1 | task 15 | prompt eval time = 6662.02 ms / 118 tokens ( 56.46 ms per token, 17.71 tokens per second) 0.53.613.826 I slot print_timing: id 1 | task 15 | eval time = 204.55 ms / 2 tokens ( 204.55 ms per token, 4.89 tokens per second) 0.53.613.827 I slot print_timing: id 1 | task 15 | total time = 6866.57 ms / 120 tokens 0.53.613.827 I slot print_timing: id 1 | task 15 | graphs reused = 1 0.53.613.827 I slot print_timing: id 1 | task 15 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.613.842 I slot release: id 1 | task 15 | stop processing: n_tokens = 119, truncated = 0 0.53.614.026 I slot print_timing: id 2 | task 16 | prompt eval time = 6662.17 ms / 125 tokens ( 53.30 ms per token, 18.76 tokens per second) 0.53.614.029 I slot print_timing: id 2 | task 16 | eval time = 204.59 ms / 2 tokens ( 204.59 ms per token, 4.89 tokens per second) 0.53.614.029 I slot print_timing: id 2 | task 16 | total time = 6866.76 ms / 127 tokens 0.53.614.029 I slot print_timing: id 2 | task 16 | graphs reused = 1 0.53.614.030 I slot print_timing: id 2 | task 16 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.614.038 I slot release: id 2 | task 16 | stop processing: n_tokens = 126, truncated = 0 0.53.614.233 I slot print_timing: id 3 | task 17 | prompt eval time = 6662.33 ms / 150 tokens ( 44.42 ms per token, 22.51 tokens per second) 0.53.614.235 I slot print_timing: id 3 | task 17 | eval time = 204.63 ms / 2 tokens ( 204.63 ms per token, 4.89 tokens per second) 0.53.614.236 I slot print_timing: id 3 | task 17 | total time = 6866.96 ms / 152 tokens 0.53.614.236 I slot print_timing: id 3 | task 17 | graphs reused = 1 0.53.614.236 I slot print_timing: id 3 | task 17 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.614.246 I slot release: id 3 | task 17 | stop processing: n_tokens = 151, truncated = 0 0.53.619.549 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.196 (> 0.100 thold), f_keep = 0.237 0.53.642.918 I slot launch_slot_: id 0 | task 21 | processing task, is_child = 0 0.53.714.992 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.206 (> 0.100 thold), f_keep = 0.235 0.53.715.066 I slot launch_slot_: id 1 | task 22 | processing task, is_child = 0 0.53.715.100 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.235 (> 0.100 thold), f_keep = 0.222 0.53.715.135 I slot launch_slot_: id 2 | task 23 | processing task, is_child = 0 0.53.715.157 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.155 (> 0.100 thold), f_keep = 0.185 0.53.715.186 I slot launch_slot_: id 3 | task 24 | processing task, is_child = 0 1.00.067.761 I slot print_timing: id 0 | task 21 | prompt processing, n_tokens = 139, progress = 0.97, t = 6.35 s / 21.88 tokens per second 1.00.847.340 I slot print_timing: id 1 | task 22 | prompt processing, n_tokens = 132, progress = 0.97, t = 6.35 s / 20.78 tokens per second 1.00.851.799 I slot print_timing: id 2 | task 23 | prompt processing, n_tokens = 115, progress = 0.97, t = 6.35 s / 18.10 tokens per second 1.00.856.238 I slot print_timing: id 3 | task 24 | prompt processing, n_tokens = 177, progress = 0.98, t = 6.35 s / 27.86 tokens per second 1.01.405.291 I slot print_timing: id 0 | task 21 | prompt eval time = 7485.39 ms / 143 tokens ( 52.35 ms per token, 19.10 tokens per second) 1.01.405.293 I slot print_timing: id 0 | task 21 | eval time = 204.70 ms / 2 tokens ( 204.70 ms per token, 4.89 tokens per second) 1.01.405.294 I slot print_timing: id 0 | task 21 | total time = 7690.10 ms / 145 tokens 1.01.405.294 I slot print_timing: id 0 | task 21 | graphs reused = 1 1.01.405.294 I slot print_timing: id 0 | task 21 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.405.319 I slot release: id 0 | task 21 | stop processing: n_tokens = 144, truncated = 0 1.01.405.466 I slot print_timing: id 1 | task 22 | prompt eval time = 7485.57 ms / 136 tokens ( 55.04 ms per token, 18.17 tokens per second) 1.01.405.468 I slot print_timing: id 1 | task 22 | eval time = 204.69 ms / 2 tokens ( 204.69 ms per token, 4.89 tokens per second) 1.01.405.469 I slot print_timing: id 1 | task 22 | total time = 7690.26 ms / 138 tokens 1.01.405.469 I slot print_timing: id 1 | task 22 | graphs reused = 1 1.01.405.469 I slot print_timing: id 1 | task 22 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.405.481 I slot release: id 1 | task 22 | stop processing: n_tokens = 137, truncated = 0 1.01.405.642 I slot print_timing: id 2 | task 23 | prompt eval time = 7485.77 ms / 119 tokens ( 62.91 ms per token, 15.90 tokens per second) 1.01.405.644 I slot print_timing: id 2 | task 23 | eval time = 204.66 ms / 2 tokens ( 204.66 ms per token, 4.89 tokens per second) 1.01.405.645 I slot print_timing: id 2 | task 23 | total time = 7690.43 ms / 121 tokens 1.01.405.645 I slot print_timing: id 2 | task 23 | graphs reused = 1 1.01.405.645 I slot print_timing: id 2 | task 23 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.405.661 I slot release: id 2 | task 23 | stop processing: n_tokens = 120, truncated = 0 1.01.405.824 I slot print_timing: id 3 | task 24 | prompt eval time = 7485.96 ms / 181 tokens ( 41.36 ms per token, 24.18 tokens per second) 1.01.405.826 I slot print_timing: id 3 | task 24 | eval time = 204.63 ms / 2 tokens ( 204.63 ms per token, 4.89 tokens per second) 1.01.405.826 I slot print_timing: id 3 | task 24 | total time = 7690.59 ms / 183 tokens 1.01.405.826 I slot print_timing: id 3 | task 24 | graphs reused = 1 1.01.405.827 I slot print_timing: id 3 | task 24 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.405.837 I slot release: id 3 | task 24 | stop processing: n_tokens = 182, truncated = 0 1.01.411.082 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.214 (> 0.100 thold), f_keep = 0.194 1.01.441.844 I slot launch_slot_: id 0 | task 28 | processing task, is_child = 0 1.01.500.028 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.194 (> 0.100 thold), f_keep = 0.204 1.01.500.117 I slot launch_slot_: id 1 | task 29 | processing task, is_child = 0 1.01.500.155 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.157 (> 0.100 thold), f_keep = 0.233 1.01.500.191 I slot launch_slot_: id 2 | task 30 | processing task, is_child = 0 1.01.500.217 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.154 1.01.503.568 I slot launch_slot_: id 3 | task 31 | processing task, is_child = 0 1.08.008.260 I slot print_timing: id 0 | task 28 | prompt processing, n_tokens = 127, progress = 0.97, t = 6.50 s / 19.52 tokens per second 1.08.763.165 I slot print_timing: id 1 | task 29 | prompt processing, n_tokens = 140, progress = 0.97, t = 6.50 s / 21.52 tokens per second 1.08.767.571 I slot print_timing: id 2 | task 30 | prompt processing, n_tokens = 174, progress = 0.98, t = 6.50 s / 26.75 tokens per second 1.08.771.993 I slot print_timing: id 3 | task 31 | prompt processing, n_tokens = 118, progress = 0.97, t = 6.50 s / 18.14 tokens per second 1.09.319.413 I slot print_timing: id 0 | task 28 | prompt eval time = 7611.44 ms / 131 tokens ( 58.10 ms per token, 17.21 tokens per second) 1.09.319.418 I slot print_timing: id 0 | task 28 | eval time = 204.39 ms / 2 tokens ( 204.39 ms per token, 4.89 tokens per second) 1.09.319.418 I slot print_timing: id 0 | task 28 | total time = 7815.83 ms / 133 tokens 1.09.319.419 I slot print_timing: id 0 | task 28 | graphs reused = 1 1.09.319.419 I slot print_timing: id 0 | task 28 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.319.442 I slot release: id 0 | task 28 | stop processing: n_tokens = 132, truncated = 0 1.09.319.598 I slot print_timing: id 1 | task 29 | prompt eval time = 7611.62 ms / 144 tokens ( 52.86 ms per token, 18.92 tokens per second) 1.09.319.599 I slot print_timing: id 1 | task 29 | eval time = 204.38 ms / 2 tokens ( 204.38 ms per token, 4.89 tokens per second) 1.09.319.600 I slot print_timing: id 1 | task 29 | total time = 7816.00 ms / 146 tokens 1.09.319.600 I slot print_timing: id 1 | task 29 | graphs reused = 1 1.09.319.600 I slot print_timing: id 1 | task 29 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.319.611 I slot release: id 1 | task 29 | stop processing: n_tokens = 145, truncated = 0 1.09.319.780 I slot print_timing: id 2 | task 30 | prompt eval time = 7611.81 ms / 178 tokens ( 42.76 ms per token, 23.38 tokens per second) 1.09.319.784 I slot print_timing: id 2 | task 30 | eval time = 204.36 ms / 2 tokens ( 204.36 ms per token, 4.89 tokens per second) 1.09.319.784 I slot print_timing: id 2 | task 30 | total time = 7816.17 ms / 180 tokens 1.09.319.785 I slot print_timing: id 2 | task 30 | graphs reused = 1 1.09.319.785 I slot print_timing: id 2 | task 30 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.319.795 I slot release: id 2 | task 30 | stop processing: n_tokens = 179, truncated = 0 1.09.319.956 I slot print_timing: id 3 | task 31 | prompt eval time = 7612.01 ms / 122 tokens ( 62.39 ms per token, 16.03 tokens per second) 1.09.319.958 I slot print_timing: id 3 | task 31 | eval time = 204.33 ms / 2 tokens ( 204.33 ms per token, 4.89 tokens per second) 1.09.319.958 I slot print_timing: id 3 | task 31 | total time = 7816.33 ms / 124 tokens 1.09.319.958 I slot print_timing: id 3 | task 31 | graphs reused = 1 1.09.319.958 I slot print_timing: id 3 | task 31 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.319.974 I slot release: id 3 | task 31 | stop processing: n_tokens = 123, truncated = 0 1.09.326.077 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.248 (> 0.100 thold), f_keep = 0.212 1.09.344.110 I slot launch_slot_: id 0 | task 35 | processing task, is_child = 0 1.09.411.981 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.242 (> 0.100 thold), f_keep = 0.236 1.09.412.068 I slot launch_slot_: id 3 | task 36 | processing task, is_child = 0 1.09.412.104 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.201 (> 0.100 thold), f_keep = 0.162 1.09.412.139 I slot launch_slot_: id 2 | task 37 | processing task, is_child = 0 1.09.412.162 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.197 (> 0.100 thold), f_keep = 0.193 1.09.412.194 I slot launch_slot_: id 1 | task 38 | processing task, is_child = 0 1.15.751.291 I slot print_timing: id 0 | task 35 | prompt processing, n_tokens = 109, progress = 0.96, t = 6.34 s / 17.19 tokens per second 1.15.913.528 I slot print_timing: id 1 | task 38 | prompt processing, n_tokens = 138, progress = 0.97, t = 6.34 s / 21.77 tokens per second 1.15.918.189 I slot print_timing: id 2 | task 37 | prompt processing, n_tokens = 140, progress = 0.97, t = 6.34 s / 22.09 tokens per second 1.15.923.011 I slot print_timing: id 3 | task 36 | prompt processing, n_tokens = 116, progress = 0.97, t = 6.34 s / 18.30 tokens per second 1.16.471.969 I slot print_timing: id 0 | task 35 | prompt eval time = 6855.32 ms / 113 tokens ( 60.67 ms per token, 16.48 tokens per second) 1.16.471.972 I slot print_timing: id 0 | task 35 | eval time = 204.45 ms / 2 tokens ( 204.45 ms per token, 4.89 tokens per second) 1.16.471.972 I slot print_timing: id 0 | task 35 | total time = 7059.76 ms / 115 tokens 1.16.471.973 I slot print_timing: id 0 | task 35 | graphs reused = 1 1.16.471.973 I slot print_timing: id 0 | task 35 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.471.990 I slot release: id 0 | task 35 | stop processing: n_tokens = 114, truncated = 0 1.16.472.166 I slot print_timing: id 1 | task 38 | prompt eval time = 6855.46 ms / 142 tokens ( 48.28 ms per token, 20.71 tokens per second) 1.16.472.169 I slot print_timing: id 1 | task 38 | eval time = 204.49 ms / 2 tokens ( 204.49 ms per token, 4.89 tokens per second) 1.16.472.169 I slot print_timing: id 1 | task 38 | total time = 7059.95 ms / 144 tokens 1.16.472.169 I slot print_timing: id 1 | task 38 | graphs reused = 1 1.16.472.170 I slot print_timing: id 1 | task 38 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.472.181 I slot release: id 1 | task 38 | stop processing: n_tokens = 143, truncated = 0 1.16.472.351 I slot print_timing: id 2 | task 37 | prompt eval time = 6855.61 ms / 144 tokens ( 47.61 ms per token, 21.00 tokens per second) 1.16.472.353 I slot print_timing: id 2 | task 37 | eval time = 204.51 ms / 2 tokens ( 204.51 ms per token, 4.89 tokens per second) 1.16.472.353 I slot print_timing: id 2 | task 37 | total time = 7060.12 ms / 146 tokens 1.16.472.353 I slot print_timing: id 2 | task 37 | graphs reused = 1 1.16.472.354 I slot print_timing: id 2 | task 37 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.472.368 I slot release: id 2 | task 37 | stop processing: n_tokens = 145, truncated = 0 1.16.472.547 I slot print_timing: id 3 | task 36 | prompt eval time = 6855.76 ms / 120 tokens ( 57.13 ms per token, 17.50 tokens per second) 1.16.472.549 I slot print_timing: id 3 | task 36 | eval time = 204.54 ms / 2 tokens ( 204.54 ms per token, 4.89 tokens per second) 1.16.472.549 I slot print_timing: id 3 | task 36 | total time = 7060.30 ms / 122 tokens 1.16.472.549 I slot print_timing: id 3 | task 36 | graphs reused = 1 1.16.472.550 I slot print_timing: id 3 | task 36 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.472.557 I slot release: id 3 | task 36 | stop processing: n_tokens = 121, truncated = 0 1.16.478.188 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.257 (> 0.100 thold), f_keep = 0.246 1.16.504.217 I slot launch_slot_: id 0 | task 42 | processing task, is_child = 0 1.16.593.516 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.259 (> 0.100 thold), f_keep = 0.240 1.16.593.602 I slot launch_slot_: id 3 | task 43 | processing task, is_child = 0 1.16.593.641 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.196 (> 0.100 thold), f_keep = 0.196 1.16.593.679 I slot launch_slot_: id 1 | task 45 | processing task, is_child = 0 1.16.593.700 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.193 1.16.593.733 I slot launch_slot_: id 2 | task 44 | processing task, is_child = 0 1.22.391.949 I slot print_timing: id 0 | task 42 | prompt processing, n_tokens = 105, progress = 0.96, t = 5.80 s / 18.11 tokens per second 1.22.818.131 I slot print_timing: id 1 | task 45 | prompt processing, n_tokens = 139, progress = 0.97, t = 5.80 s / 23.97 tokens per second 1.22.822.550 I slot print_timing: id 2 | task 44 | prompt processing, n_tokens = 119, progress = 0.97, t = 5.80 s / 20.52 tokens per second 1.22.826.933 I slot print_timing: id 3 | task 43 | prompt processing, n_tokens = 108, progress = 0.96, t = 5.80 s / 18.63 tokens per second 1.23.374.976 I slot print_timing: id 0 | task 42 | prompt eval time = 6576.90 ms / 109 tokens ( 60.34 ms per token, 16.57 tokens per second) 1.23.374.981 I slot print_timing: id 0 | task 42 | eval time = 204.33 ms / 2 tokens ( 204.33 ms per token, 4.89 tokens per second) 1.23.374.981 I slot print_timing: id 0 | task 42 | total time = 6781.24 ms / 111 tokens 1.23.374.982 I slot print_timing: id 0 | task 42 | graphs reused = 1 1.23.374.982 I slot print_timing: id 0 | task 42 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.375.001 I slot release: id 0 | task 42 | stop processing: n_tokens = 110, truncated = 0 1.23.375.153 I slot print_timing: id 1 | task 45 | prompt eval time = 6577.08 ms / 143 tokens ( 45.99 ms per token, 21.74 tokens per second) 1.23.375.155 I slot print_timing: id 1 | task 45 | eval time = 204.31 ms / 2 tokens ( 204.31 ms per token, 4.89 tokens per second) 1.23.375.155 I slot print_timing: id 1 | task 45 | total time = 6781.39 ms / 145 tokens 1.23.375.155 I slot print_timing: id 1 | task 45 | graphs reused = 1 1.23.375.156 I slot print_timing: id 1 | task 45 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.375.165 I slot release: id 1 | task 45 | stop processing: n_tokens = 144, truncated = 0 1.23.375.339 I slot print_timing: id 2 | task 44 | prompt eval time = 6577.26 ms / 123 tokens ( 53.47 ms per token, 18.70 tokens per second) 1.23.375.341 I slot print_timing: id 2 | task 44 | eval time = 204.30 ms / 2 tokens ( 204.30 ms per token, 4.89 tokens per second) 1.23.375.342 I slot print_timing: id 2 | task 44 | total time = 6781.57 ms / 125 tokens 1.23.375.342 I slot print_timing: id 2 | task 44 | graphs reused = 1 1.23.375.342 I slot print_timing: id 2 | task 44 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.375.352 I slot release: id 2 | task 44 | stop processing: n_tokens = 124, truncated = 0 1.23.375.516 I slot print_timing: id 3 | task 43 | prompt eval time = 6577.45 ms / 112 tokens ( 58.73 ms per token, 17.03 tokens per second) 1.23.375.519 I slot print_timing: id 3 | task 43 | eval time = 204.28 ms / 2 tokens ( 204.28 ms per token, 4.90 tokens per second) 1.23.375.519 I slot print_timing: id 3 | task 43 | total time = 6781.73 ms / 114 tokens 1.23.375.519 I slot print_timing: id 3 | task 43 | graphs reused = 1 1.23.375.520 I slot print_timing: id 3 | task 43 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.375.528 I slot release: id 3 | task 43 | stop processing: n_tokens = 113, truncated = 0 1.23.381.279 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.275 (> 0.100 thold), f_keep = 0.255 1.23.417.088 I slot launch_slot_: id 0 | task 49 | processing task, is_child = 0 1.23.518.675 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.206 (> 0.100 thold), f_keep = 0.194 1.23.518.762 I slot launch_slot_: id 1 | task 51 | processing task, is_child = 0 1.23.518.797 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.259 (> 0.100 thold), f_keep = 0.257 1.23.518.833 I slot launch_slot_: id 3 | task 50 | processing task, is_child = 0 1.23.518.857 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.217 (> 0.100 thold), f_keep = 0.226 1.23.522.204 I slot launch_slot_: id 2 | task 52 | processing task, is_child = 0 1.29.473.707 I slot print_timing: id 0 | task 49 | prompt processing, n_tokens = 98, progress = 0.96, t = 5.95 s / 16.47 tokens per second 1.29.646.748 I slot print_timing: id 1 | task 51 | prompt processing, n_tokens = 132, progress = 0.97, t = 5.95 s / 22.18 tokens per second 1.29.656.942 I slot print_timing: id 2 | task 52 | prompt processing, n_tokens = 125, progress = 0.97, t = 5.95 s / 21.00 tokens per second 1.29.661.359 I slot print_timing: id 3 | task 50 | prompt processing, n_tokens = 108, progress = 0.96, t = 5.95 s / 18.15 tokens per second 1.30.209.322 I slot print_timing: id 0 | task 49 | prompt eval time = 6482.32 ms / 102 tokens ( 63.55 ms per token, 15.74 tokens per second) 1.30.209.327 I slot print_timing: id 0 | task 49 | eval time = 204.79 ms / 2 tokens ( 204.79 ms per token, 4.88 tokens per second) 1.30.209.327 I slot print_timing: id 0 | task 49 | total time = 6687.10 ms / 104 tokens 1.30.209.328 I slot print_timing: id 0 | task 49 | graphs reused = 1 1.30.209.328 I slot print_timing: id 0 | task 49 | graph reallocs = 0 / 0 (same size) / (changed size) 1.30.209.348 I slot release: id 0 | task 49 | stop processing: n_tokens = 103, truncated = 0 1.30.209.511 I slot print_timing: id 1 | task 51 | prompt eval time = 6482.50 ms / 136 tokens ( 47.67 ms per token, 20.98 tokens per second) 1.30.209.513 I slot print_timing: id 1 | task 51 | eval time = 204.78 ms / 2 tokens ( 204.78 ms per token, 4.88 tokens per second) 1.30.209.514 I slot print_timing: id 1 | task 51 | total time = 6687.28 ms / 138 tokens 1.30.209.514 I slot print_timing: id 1 | task 51 | graphs reused = 1 1.30.209.514 I slot print_timing: id 1 | task 51 | graph reallocs = 0 / 0 (same size) / (changed size) 1.30.209.525 I slot release: id 1 | task 51 | stop processing: n_tokens = 137, truncated = 0 1.30.209.698 I slot print_timing: id 2 | task 52 | prompt eval time = 6482.69 ms / 129 tokens ( 50.25 ms per token, 19.90 tokens per second) 1.30.209.699 I slot print_timing: id 2 | task 52 | eval time = 204.76 ms / 2 tokens ( 204.76 ms per token, 4.88 tokens per second) 1.30.209.699 I slot print_timing: id 2 | task 52 | total time = 6687.45 ms / 131 tokens 1.30.209.700 I slot print_timing: id 2 | task 52 | graphs reused = 1 1.30.209.700 I slot print_timing: id 2 | task 52 | graph reallocs = 0 / 0 (same size) / (changed size) 1.30.209.719 I slot release: id 2 | task 52 | stop processing: n_tokens = 130, truncated = 0 1.30.209.900 I slot print_timing: id 3 | task 50 | prompt eval time = 6482.88 ms / 112 tokens ( 57.88 ms per token, 17.28 tokens per second) 1.30.209.902 I slot print_timing: id 3 | task 50 | eval time = 204.76 ms / 2 tokens ( 204.76 ms per token, 4.88 tokens per second) 1.30.209.903 I slot print_timing: id 3 | task 50 | total time = 6687.64 ms / 114 tokens 1.30.209.903 I slot print_timing: id 3 | task 50 | graphs reused = 1 1.30.209.903 I slot print_timing: id 3 | task 50 | graph reallocs = 0 / 0 (same size) / (changed size) 1.30.209.910 I slot release: id 3 | task 50 | stop processing: n_tokens = 113, truncated = 0 1.30.215.115 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.212 (> 0.100 thold), f_keep = 0.272 1.30.223.685 I slot launch_slot_: id 0 | task 57 | processing task, is_child = 0 1.30.223.708 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.943 MiB) 1.30.252.182 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.443 MiB) 1.30.259.976 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.505 MiB) 1.30.267.704 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.169 (> 0.100 thold), f_keep = 0.204 1.30.267.789 I slot launch_slot_: id 1 | task 56 | processing task, is_child = 0 1.30.267.827 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.154 (> 0.100 thold), f_keep = 0.215 1.30.267.867 I slot launch_slot_: id 2 | task 58 | processing task, is_child = 0 1.30.267.887 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 1.30.267.926 I slot launch_slot_: id 3 | task 59 | processing task, is_child = 0 1.37.885.086 I slot print_timing: id 0 | task 57 | prompt processing, n_tokens = 128, progress = 0.97, t = 7.62 s / 16.80 tokens per second 1.38.055.026 I slot print_timing: id 1 | task 56 | prompt processing, n_tokens = 162, progress = 0.98, t = 7.62 s / 21.27 tokens per second 1.38.059.456 I slot print_timing: id 2 | task 58 | prompt processing, n_tokens = 178, progress = 0.98, t = 7.62 s / 23.37 tokens per second 1.38.063.859 I slot print_timing: id 3 | task 59 | prompt processing, n_tokens = 173, progress = 0.98, t = 7.62 s / 22.71 tokens per second 1.38.613.373 I slot print_timing: id 0 | task 57 | prompt eval time = 8140.47 ms / 132 tokens ( 61.67 ms per token, 16.22 tokens per second) 1.38.613.377 I slot print_timing: id 0 | task 57 | eval time = 204.97 ms / 2 tokens ( 204.97 ms per token, 4.88 tokens per second) 1.38.613.378 I slot print_timing: id 0 | task 57 | total time = 8345.44 ms / 134 tokens 1.38.613.378 I slot print_timing: id 0 | task 57 | graphs reused = 1 1.38.613.379 I slot print_timing: id 0 | task 57 | graph reallocs = 0 / 0 (same size) / (changed size) 1.38.613.401 I slot release: id 0 | task 57 | stop processing: n_tokens = 133, truncated = 0 1.38.613.556 I slot print_timing: id 1 | task 56 | prompt eval time = 8140.61 ms / 166 tokens ( 49.04 ms per token, 20.39 tokens per second) 1.38.613.559 I slot print_timing: id 1 | task 56 | eval time = 204.99 ms / 2 tokens ( 204.99 ms per token, 4.88 tokens per second) 1.38.613.559 I slot print_timing: id 1 | task 56 | total time = 8345.60 ms / 168 tokens 1.38.613.559 I slot print_timing: id 1 | task 56 | graphs reused = 1 1.38.613.560 I slot print_timing: id 1 | task 56 | graph reallocs = 0 / 0 (same size) / (changed size) 1.38.613.578 I slot release: id 1 | task 56 | stop processing: n_tokens = 167, truncated = 0 1.38.613.750 I slot print_timing: id 2 | task 58 | prompt eval time = 8140.79 ms / 182 tokens ( 44.73 ms per token, 22.36 tokens per second) 1.38.613.751 I slot print_timing: id 2 | task 58 | eval time = 204.98 ms / 2 tokens ( 204.98 ms per token, 4.88 tokens per second) 1.38.613.752 I slot print_timing: id 2 | task 58 | total time = 8345.77 ms / 184 tokens 1.38.613.752 I slot print_timing: id 2 | task 58 | graphs reused = 1 1.38.613.752 I slot print_timing: id 2 | task 58 | graph reallocs = 0 / 0 (same size) / (changed size) 1.38.613.767 I slot release: id 2 | task 58 | stop processing: n_tokens = 183, truncated = 0 1.38.613.958 I slot print_timing: id 3 | task 59 | prompt eval time = 8141.01 ms / 177 tokens ( 45.99 ms per token, 21.74 tokens per second) 1.38.613.959 I slot print_timing: id 3 | task 59 | eval time = 204.96 ms / 2 tokens ( 204.96 ms per token, 4.88 tokens per second) 1.38.613.960 I slot print_timing: id 3 | task 59 | total time = 8345.96 ms / 179 tokens 1.38.613.960 I slot print_timing: id 3 | task 59 | graphs reused = 1 1.38.613.960 I slot print_timing: id 3 | task 59 | graph reallocs = 0 / 0 (same size) / (changed size) 1.38.613.972 I slot release: id 3 | task 59 | stop processing: n_tokens = 178, truncated = 0 1.38.619.570 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.211 1.38.619.648 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.819 MiB) 1.38.628.244 I slot launch_slot_: id 0 | task 64 | processing task, is_child = 0 1.38.628.266 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.319 MiB) 1.38.656.115 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 311.820 MiB) 1.38.663.987 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.630 MiB) 1.38.687.083 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.166 (> 0.100 thold), f_keep = 0.168 1.38.687.178 I slot launch_slot_: id 1 | task 65 | processing task, is_child = 0 1.38.687.223 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.153 1.38.687.264 I slot launch_slot_: id 2 | task 63 | processing task, is_child = 0 1.38.687.286 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.200 (> 0.100 thold), f_keep = 0.157 1.38.690.610 I slot launch_slot_: id 3 | task 66 | processing task, is_child = 0 1.45.303.638 I slot print_timing: id 0 | task 64 | prompt processing, n_tokens = 145, progress = 0.97, t = 6.61 s / 21.93 tokens per second 1.45.728.862 I slot print_timing: id 1 | task 65 | prompt processing, n_tokens = 165, progress = 0.98, t = 6.61 s / 24.95 tokens per second 1.45.733.654 I slot print_timing: id 2 | task 63 | prompt processing, n_tokens = 119, progress = 0.97, t = 6.61 s / 17.99 tokens per second 1.45.738.055 I slot print_timing: id 3 | task 66 | prompt processing, n_tokens = 136, progress = 0.97, t = 6.61 s / 20.57 tokens per second 1.46.286.727 I slot print_timing: id 0 | task 64 | prompt eval time = 7391.21 ms / 149 tokens ( 49.61 ms per token, 20.16 tokens per second) 1.46.286.733 I slot print_timing: id 0 | task 64 | eval time = 204.90 ms / 2 tokens ( 204.90 ms per token, 4.88 tokens per second) 1.46.286.734 I slot print_timing: id 0 | task 64 | total time = 7596.10 ms / 151 tokens 1.46.286.734 I slot print_timing: id 0 | task 64 | graphs reused = 1 1.46.286.735 I slot print_timing: id 0 | task 64 | graph reallocs = 0 / 0 (same size) / (changed size) 1.46.286.754 I slot release: id 0 | task 64 | stop processing: n_tokens = 150, truncated = 0 1.46.286.910 I slot print_timing: id 1 | task 65 | prompt eval time = 7391.38 ms / 169 tokens ( 43.74 ms per token, 22.86 tokens per second) 1.46.286.913 I slot print_timing: id 1 | task 65 | eval time = 204.88 ms / 2 tokens ( 204.88 ms per token, 4.88 tokens per second) 1.46.286.913 I slot print_timing: id 1 | task 65 | total time = 7596.27 ms / 171 tokens 1.46.286.913 I slot print_timing: id 1 | task 65 | graphs reused = 1 1.46.286.914 I slot print_timing: id 1 | task 65 | graph reallocs = 0 / 0 (same size) / (changed size) 1.46.286.924 I slot release: id 1 | task 65 | stop processing: n_tokens = 170, truncated = 0 1.46.287.089 I slot print_timing: id 2 | task 63 | prompt eval time = 7391.56 ms / 123 tokens ( 60.09 ms per token, 16.64 tokens per second) 1.46.287.093 I slot print_timing: id 2 | task 63 | eval time = 204.87 ms / 2 tokens ( 204.87 ms per token, 4.88 tokens per second) 1.46.287.093 I slot print_timing: id 2 | task 63 | total time = 7596.43 ms / 125 tokens 1.46.287.094 I slot print_timing: id 2 | task 63 | graphs reused = 1 1.46.287.094 I slot print_timing: id 2 | task 63 | graph reallocs = 0 / 0 (same size) / (changed size) 1.46.287.102 I slot release: id 2 | task 63 | stop processing: n_tokens = 124, truncated = 0 1.46.287.270 I slot print_timing: id 3 | task 66 | prompt eval time = 7391.77 ms / 140 tokens ( 52.80 ms per token, 18.94 tokens per second) 1.46.287.272 I slot print_timing: id 3 | task 66 | eval time = 204.83 ms / 2 tokens ( 204.83 ms per token, 4.88 tokens per second) 1.46.287.272 I slot print_timing: id 3 | task 66 | total time = 7596.60 ms / 142 tokens 1.46.287.273 I slot print_timing: id 3 | task 66 | graphs reused = 1 1.46.287.273 I slot print_timing: id 3 | task 66 | graph reallocs = 0 / 0 (same size) / (changed size) 1.46.287.282 I slot release: id 3 | task 66 | stop processing: n_tokens = 141, truncated = 0 1.46.293.514 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.219 (> 0.100 thold), f_keep = 0.187 1.46.302.489 I slot launch_slot_: id 0 | task 70 | processing task, is_child = 0 1.46.302.511 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.693 MiB) 1.46.332.850 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.131 MiB) 1.46.342.105 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.694 MiB) 1.46.353.218 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.261 (> 0.100 thold), f_keep = 0.206 1.46.353.293 I slot launch_slot_: id 3 | task 71 | processing task, is_child = 0 1.46.353.334 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.178 (> 0.100 thold), f_keep = 0.234 1.46.353.369 I slot launch_slot_: id 2 | task 72 | processing task, is_child = 0 1.46.353.391 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.174 (> 0.100 thold), f_keep = 0.165 1.46.353.431 I slot launch_slot_: id 1 | task 73 | processing task, is_child = 0 1.53.369.752 I slot print_timing: id 0 | task 70 | prompt processing, n_tokens = 124, progress = 0.97, t = 7.02 s / 17.67 tokens per second 1.53.533.333 I slot print_timing: id 1 | task 73 | prompt processing, n_tokens = 157, progress = 0.98, t = 7.02 s / 22.38 tokens per second 1.53.537.727 I slot print_timing: id 2 | task 72 | prompt processing, n_tokens = 159, progress = 0.98, t = 7.02 s / 22.66 tokens per second 1.53.542.142 I slot print_timing: id 3 | task 71 | prompt processing, n_tokens = 107, progress = 0.96, t = 7.02 s / 15.25 tokens per second 1.54.091.132 I slot print_timing: id 0 | task 70 | prompt eval time = 7532.88 ms / 128 tokens ( 58.85 ms per token, 16.99 tokens per second) 1.54.091.135 I slot print_timing: id 0 | task 70 | eval time = 204.81 ms / 2 tokens ( 204.81 ms per token, 4.88 tokens per second) 1.54.091.135 I slot print_timing: id 0 | task 70 | total time = 7737.69 ms / 130 tokens 1.54.091.136 I slot print_timing: id 0 | task 70 | graphs reused = 1 1.54.091.136 I slot print_timing: id 0 | task 70 | graph reallocs = 0 / 0 (same size) / (changed size) 1.54.091.158 I slot release: id 0 | task 70 | stop processing: n_tokens = 129, truncated = 0 1.54.091.310 I slot print_timing: id 1 | task 73 | prompt eval time = 7533.02 ms / 161 tokens ( 46.79 ms per token, 21.37 tokens per second) 1.54.091.312 I slot print_timing: id 1 | task 73 | eval time = 204.83 ms / 2 tokens ( 204.83 ms per token, 4.88 tokens per second) 1.54.091.312 I slot print_timing: id 1 | task 73 | total time = 7737.85 ms / 163 tokens 1.54.091.313 I slot print_timing: id 1 | task 73 | graphs reused = 1 1.54.091.313 I slot print_timing: id 1 | task 73 | graph reallocs = 0 / 0 (same size) / (changed size) 1.54.091.332 I slot release: id 1 | task 73 | stop processing: n_tokens = 162, truncated = 0 1.54.091.500 I slot print_timing: id 2 | task 72 | prompt eval time = 7533.21 ms / 163 tokens ( 46.22 ms per token, 21.64 tokens per second) 1.54.091.502 I slot print_timing: id 2 | task 72 | eval time = 204.81 ms / 2 tokens ( 204.81 ms per token, 4.88 tokens per second) 1.54.091.502 I slot print_timing: id 2 | task 72 | total time = 7738.02 ms / 165 tokens 1.54.091.502 I slot print_timing: id 2 | task 72 | graphs reused = 1 1.54.091.503 I slot print_timing: id 2 | task 72 | graph reallocs = 0 / 0 (same size) / (changed size) 1.54.091.516 I slot release: id 2 | task 72 | stop processing: n_tokens = 164, truncated = 0 1.54.091.678 I slot print_timing: id 3 | task 71 | prompt eval time = 7533.39 ms / 111 tokens ( 67.87 ms per token, 14.73 tokens per second) 1.54.091.679 I slot print_timing: id 3 | task 71 | eval time = 204.79 ms / 2 tokens ( 204.79 ms per token, 4.88 tokens per second) 1.54.091.680 I slot print_timing: id 3 | task 71 | total time = 7738.18 ms / 113 tokens 1.54.091.680 I slot print_timing: id 3 | task 71 | graphs reused = 1 1.54.091.680 I slot print_timing: id 3 | task 71 | graph reallocs = 0 / 0 (same size) / (changed size) 1.54.091.695 I slot release: id 3 | task 71 | stop processing: n_tokens = 112, truncated = 0 1.54.097.808 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.266 (> 0.100 thold), f_keep = 0.179 1.54.097.838 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.256 MiB) 1.54.127.524 I slot launch_slot_: id 1 | task 77 | processing task, is_child = 0 1.54.127.555 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.818 MiB) 1.54.135.357 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.755 MiB) 1.54.157.979 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.632 MiB) 1.54.169.692 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.250 (> 0.100 thold), f_keep = 0.217 1.54.169.774 I slot launch_slot_: id 0 | task 78 | processing task, is_child = 0 1.54.169.811 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.168 (> 0.100 thold), f_keep = 0.171 1.54.169.849 I slot launch_slot_: id 2 | task 79 | processing task, is_child = 0 1.54.169.869 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.171 (> 0.100 thold), f_keep = 0.250 1.54.169.908 I slot launch_slot_: id 3 | task 80 | processing task, is_child = 0 2.00.852.210 I slot print_timing: id 0 | task 78 | prompt processing, n_tokens = 108, progress = 0.96, t = 6.68 s / 16.16 tokens per second 2.01.019.303 I slot print_timing: id 1 | task 77 | prompt processing, n_tokens = 105, progress = 0.96, t = 6.68 s / 15.71 tokens per second 2.01.023.779 I slot print_timing: id 2 | task 79 | prompt processing, n_tokens = 163, progress = 0.98, t = 6.68 s / 24.39 tokens per second 2.01.028.203 I slot print_timing: id 3 | task 80 | prompt processing, n_tokens = 160, progress = 0.98, t = 6.68 s / 23.94 tokens per second 2.01.576.866 I slot print_timing: id 0 | task 78 | prompt eval time = 7202.25 ms / 112 tokens ( 64.31 ms per token, 15.55 tokens per second) 2.01.576.871 I slot print_timing: id 0 | task 78 | eval time = 204.69 ms / 2 tokens ( 204.69 ms per token, 4.89 tokens per second) 2.01.576.872 I slot print_timing: id 0 | task 78 | total time = 7406.95 ms / 114 tokens 2.01.576.872 I slot print_timing: id 0 | task 78 | graphs reused = 1 2.01.576.873 I slot print_timing: id 0 | task 78 | graph reallocs = 0 / 0 (same size) / (changed size) 2.01.576.893 I slot release: id 0 | task 78 | stop processing: n_tokens = 113, truncated = 0 2.01.577.045 I slot print_timing: id 1 | task 77 | prompt eval time = 7202.43 ms / 109 tokens ( 66.08 ms per token, 15.13 tokens per second) 2.01.577.049 I slot print_timing: id 1 | task 77 | eval time = 204.68 ms / 2 tokens ( 204.68 ms per token, 4.89 tokens per second) 2.01.577.049 I slot print_timing: id 1 | task 77 | total time = 7407.11 ms / 111 tokens 2.01.577.050 I slot print_timing: id 1 | task 77 | graphs reused = 1 2.01.577.050 I slot print_timing: id 1 | task 77 | graph reallocs = 0 / 0 (same size) / (changed size) 2.01.577.058 I slot release: id 1 | task 77 | stop processing: n_tokens = 110, truncated = 0 2.01.577.225 I slot print_timing: id 2 | task 79 | prompt eval time = 7202.62 ms / 167 tokens ( 43.13 ms per token, 23.19 tokens per second) 2.01.577.230 I slot print_timing: id 2 | task 79 | eval time = 204.66 ms / 2 tokens ( 204.66 ms per token, 4.89 tokens per second) 2.01.577.230 I slot print_timing: id 2 | task 79 | total time = 7407.27 ms / 169 tokens 2.01.577.230 I slot print_timing: id 2 | task 79 | graphs reused = 1 2.01.577.231 I slot print_timing: id 2 | task 79 | graph reallocs = 0 / 0 (same size) / (changed size) 2.01.577.240 I slot release: id 2 | task 79 | stop processing: n_tokens = 168, truncated = 0 2.01.577.414 I slot print_timing: id 3 | task 80 | prompt eval time = 7202.81 ms / 164 tokens ( 43.92 ms per token, 22.77 tokens per second) 2.01.577.415 I slot print_timing: id 3 | task 80 | eval time = 204.63 ms / 2 tokens ( 204.63 ms per token, 4.89 tokens per second) 2.01.577.416 I slot print_timing: id 3 | task 80 | total time = 7407.45 ms / 166 tokens 2.01.577.416 I slot print_timing: id 3 | task 80 | graphs reused = 1 2.01.577.416 I slot print_timing: id 3 | task 80 | graph reallocs = 0 / 0 (same size) / (changed size) 2.01.577.428 I slot release: id 3 | task 80 | stop processing: n_tokens = 165, truncated = 0 2.01.583.117 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.190 (> 0.100 thold), f_keep = 0.248 2.01.583.142 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.506 MiB) 2.01.591.591 I slot launch_slot_: id 0 | task 84 | processing task, is_child = 0 2.01.591.615 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.318 MiB) 2.01.599.624 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.444 MiB) 2.01.609.169 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.943 MiB) 2.01.622.740 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.255 2.01.626.091 I slot launch_slot_: id 1 | task 85 | processing task, is_child = 0 2.01.626.139 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.214 (> 0.100 thold), f_keep = 0.167 2.01.626.181 I slot launch_slot_: id 2 | task 86 | processing task, is_child = 0 2.01.626.199 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.233 (> 0.100 thold), f_keep = 0.170 2.01.626.230 I slot launch_slot_: id 3 | task 87 | processing task, is_child = 0 2.07.657.908 I slot print_timing: id 0 | task 84 | prompt processing, n_tokens = 143, progress = 0.97, t = 6.03 s / 23.71 tokens per second 2.07.932.026 I slot print_timing: id 1 | task 85 | prompt processing, n_tokens = 118, progress = 0.97, t = 6.03 s / 19.56 tokens per second 2.07.937.032 I slot print_timing: id 2 | task 86 | prompt processing, n_tokens = 127, progress = 0.97, t = 6.03 s / 21.06 tokens per second 2.07.941.914 I slot print_timing: id 3 | task 87 | prompt processing, n_tokens = 116, progress = 0.97, t = 6.03 s / 19.23 tokens per second 2.08.491.384 I slot print_timing: id 0 | task 84 | prompt eval time = 6660.46 ms / 147 tokens ( 45.31 ms per token, 22.07 tokens per second) 2.08.491.386 I slot print_timing: id 0 | task 84 | eval time = 204.68 ms / 2 tokens ( 204.68 ms per token, 4.89 tokens per second) 2.08.491.387 I slot print_timing: id 0 | task 84 | total time = 6865.14 ms / 149 tokens 2.08.491.387 I slot print_timing: id 0 | task 84 | graphs reused = 1 2.08.491.388 I slot print_timing: id 0 | task 84 | graph reallocs = 0 / 0 (same size) / (changed size) 2.08.491.410 I slot release: id 0 | task 84 | stop processing: n_tokens = 148, truncated = 0 2.08.491.559 I slot print_timing: id 1 | task 85 | prompt eval time = 6660.64 ms / 122 tokens ( 54.60 ms per token, 18.32 tokens per second) 2.08.491.562 I slot print_timing: id 1 | task 85 | eval time = 204.66 ms / 2 tokens ( 204.66 ms per token, 4.89 tokens per second) 2.08.491.562 I slot print_timing: id 1 | task 85 | total time = 6865.31 ms / 124 tokens 2.08.491.562 I slot print_timing: id 1 | task 85 | graphs reused = 1 2.08.491.563 I slot print_timing: id 1 | task 85 | graph reallocs = 0 / 0 (same size) / (changed size) 2.08.491.573 I slot release: id 1 | task 85 | stop processing: n_tokens = 123, truncated = 0 2.08.491.769 I slot print_timing: id 2 | task 86 | prompt eval time = 6660.84 ms / 131 tokens ( 50.85 ms per token, 19.67 tokens per second) 2.08.491.773 I slot print_timing: id 2 | task 86 | eval time = 204.67 ms / 2 tokens ( 204.67 ms per token, 4.89 tokens per second) 2.08.491.773 I slot print_timing: id 2 | task 86 | total time = 6865.51 ms / 133 tokens 2.08.491.774 I slot print_timing: id 2 | task 86 | graphs reused = 1 2.08.491.774 I slot print_timing: id 2 | task 86 | graph reallocs = 0 / 0 (same size) / (changed size) 2.08.491.782 I slot release: id 2 | task 86 | stop processing: n_tokens = 132, truncated = 0 2.08.491.957 I slot print_timing: id 3 | task 87 | prompt eval time = 6661.04 ms / 120 tokens ( 55.51 ms per token, 18.02 tokens per second) 2.08.491.960 I slot print_timing: id 3 | task 87 | eval time = 204.64 ms / 2 tokens ( 204.64 ms per token, 4.89 tokens per second) 2.08.491.961 I slot print_timing: id 3 | task 87 | total time = 6865.68 ms / 122 tokens 2.08.491.961 I slot print_timing: id 3 | task 87 | graphs reused = 1 2.08.491.961 I slot print_timing: id 3 | task 87 | graph reallocs = 0 / 0 (same size) / (changed size) 2.08.491.969 I slot release: id 3 | task 87 | stop processing: n_tokens = 121, truncated = 0 2.08.497.755 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.201 (> 0.100 thold), f_keep = 0.236 2.08.507.637 I slot launch_slot_: id 1 | task 93 | processing task, is_child = 0 2.08.507.661 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.380 MiB) 2.08.541.398 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.193 MiB) 2.08.554.853 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.318 MiB) 2.08.569.200 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.189 2.08.572.817 I slot launch_slot_: id 0 | task 92 | processing task, is_child = 0 2.08.572.859 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.226 (> 0.100 thold), f_keep = 0.212 2.08.572.895 I slot launch_slot_: id 2 | task 91 | processing task, is_child = 0 2.08.572.915 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.214 (> 0.100 thold), f_keep = 0.231 2.08.572.956 I slot launch_slot_: id 3 | task 94 | processing task, is_child = 0 2.14.848.706 I slot print_timing: id 0 | task 92 | prompt processing, n_tokens = 137, progress = 0.97, t = 6.28 s / 21.83 tokens per second 2.15.021.707 I slot print_timing: id 1 | task 93 | prompt processing, n_tokens = 140, progress = 0.97, t = 6.28 s / 22.31 tokens per second 2.15.026.106 I slot print_timing: id 2 | task 91 | prompt processing, n_tokens = 120, progress = 0.97, t = 6.28 s / 19.12 tokens per second 2.15.030.539 I slot print_timing: id 3 | task 94 | prompt processing, n_tokens = 127, progress = 0.97, t = 6.28 s / 20.24 tokens per second 2.15.579.272 I slot print_timing: id 0 | task 92 | prompt eval time = 6801.52 ms / 141 tokens ( 48.24 ms per token, 20.73 tokens per second) 2.15.579.278 I slot print_timing: id 0 | task 92 | eval time = 204.78 ms / 2 tokens ( 204.78 ms per token, 4.88 tokens per second) 2.15.579.279 I slot print_timing: id 0 | task 92 | total time = 7006.31 ms / 143 tokens 2.15.579.279 I slot print_timing: id 0 | task 92 | graphs reused = 1 2.15.579.280 I slot print_timing: id 0 | task 92 | graph reallocs = 0 / 0 (same size) / (changed size) 2.15.579.299 I slot release: id 0 | task 92 | stop processing: n_tokens = 142, truncated = 0 2.15.579.445 I slot print_timing: id 1 | task 93 | prompt eval time = 6801.66 ms / 144 tokens ( 47.23 ms per token, 21.17 tokens per second) 2.15.579.452 I slot print_timing: id 1 | task 93 | eval time = 204.81 ms / 2 tokens ( 204.81 ms per token, 4.88 tokens per second) 2.15.579.452 I slot print_timing: id 1 | task 93 | total time = 7006.46 ms / 146 tokens 2.15.579.453 I slot print_timing: id 1 | task 93 | graphs reused = 1 2.15.579.453 I slot print_timing: id 1 | task 93 | graph reallocs = 0 / 0 (same size) / (changed size) 2.15.579.467 I slot release: id 1 | task 93 | stop processing: n_tokens = 145, truncated = 0 2.15.579.625 I slot print_timing: id 2 | task 91 | prompt eval time = 6801.81 ms / 124 tokens ( 54.85 ms per token, 18.23 tokens per second) 2.15.579.627 I slot print_timing: id 2 | task 91 | eval time = 204.82 ms / 2 tokens ( 204.82 ms per token, 4.88 tokens per second) 2.15.579.627 I slot print_timing: id 2 | task 91 | total time = 7006.63 ms / 126 tokens 2.15.579.627 I slot print_timing: id 2 | task 91 | graphs reused = 1 2.15.579.627 I slot print_timing: id 2 | task 91 | graph reallocs = 0 / 0 (same size) / (changed size) 2.15.579.640 I slot release: id 2 | task 91 | stop processing: n_tokens = 125, truncated = 0 2.15.579.807 I slot print_timing: id 3 | task 94 | prompt eval time = 6802.01 ms / 131 tokens ( 51.92 ms per token, 19.26 tokens per second) 2.15.579.809 I slot print_timing: id 3 | task 94 | eval time = 204.79 ms / 2 tokens ( 204.79 ms per token, 4.88 tokens per second) 2.15.579.810 I slot print_timing: id 3 | task 94 | total time = 7006.80 ms / 133 tokens 2.15.579.810 I slot print_timing: id 3 | task 94 | graphs reused = 1 2.15.579.810 I slot print_timing: id 3 | task 94 | graph reallocs = 0 / 0 (same size) / (changed size) 2.15.579.821 I slot release: id 3 | task 94 | stop processing: n_tokens = 132, truncated = 0 2.15.585.375 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.271 (> 0.100 thold), f_keep = 0.200 2.15.593.967 I slot launch_slot_: id 1 | task 98 | processing task, is_child = 0 2.15.593.991 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.818 MiB) 2.15.612.531 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.130 MiB) 2.15.626.298 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.256 MiB) 2.15.640.216 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.246 (> 0.100 thold), f_keep = 0.220 2.15.640.283 I slot launch_slot_: id 3 | task 100 | processing task, is_child = 0 2.15.640.323 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.231 (> 0.100 thold), f_keep = 0.197 2.15.640.365 I slot launch_slot_: id 0 | task 99 | processing task, is_child = 0 2.15.640.394 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.163 (> 0.100 thold), f_keep = 0.224 2.15.640.429 I slot launch_slot_: id 2 | task 101 | processing task, is_child = 0 2.21.092.941 I slot print_timing: id 0 | task 99 | prompt processing, n_tokens = 117, progress = 0.97, t = 5.45 s / 21.46 tokens per second 2.21.864.025 I slot print_timing: id 1 | task 98 | prompt processing, n_tokens = 103, progress = 0.96, t = 5.45 s / 18.89 tokens per second 2.21.868.414 I slot print_timing: id 2 | task 101 | prompt processing, n_tokens = 168, progress = 0.98, t = 5.45 s / 30.81 tokens per second 2.21.872.955 I slot print_timing: id 3 | task 100 | prompt processing, n_tokens = 114, progress = 0.97, t = 5.45 s / 20.91 tokens per second 2.22.421.103 I slot print_timing: id 0 | task 99 | prompt eval time = 6576.10 ms / 121 tokens ( 54.35 ms per token, 18.40 tokens per second) 2.22.421.108 I slot print_timing: id 0 | task 99 | eval time = 204.56 ms / 2 tokens ( 204.56 ms per token, 4.89 tokens per second) 2.22.421.108 I slot print_timing: id 0 | task 99 | total time = 6780.66 ms / 123 tokens 2.22.421.109 I slot print_timing: id 0 | task 99 | graphs reused = 1 2.22.421.109 I slot print_timing: id 0 | task 99 | graph reallocs = 0 / 0 (same size) / (changed size) 2.22.421.132 I slot release: id 0 | task 99 | stop processing: n_tokens = 122, truncated = 0 2.22.421.284 I slot print_timing: id 1 | task 98 | prompt eval time = 6576.24 ms / 107 tokens ( 61.46 ms per token, 16.27 tokens per second) 2.22.421.286 I slot print_timing: id 1 | task 98 | eval time = 204.58 ms / 2 tokens ( 204.58 ms per token, 4.89 tokens per second) 2.22.421.287 I slot print_timing: id 1 | task 98 | total time = 6780.82 ms / 109 tokens 2.22.421.287 I slot print_timing: id 1 | task 98 | graphs reused = 1 2.22.421.287 I slot print_timing: id 1 | task 98 | graph reallocs = 0 / 0 (same size) / (changed size) 2.22.421.299 I slot release: id 1 | task 98 | stop processing: n_tokens = 108, truncated = 0 2.22.421.473 I slot print_timing: id 2 | task 101 | prompt eval time = 6576.39 ms / 172 tokens ( 38.23 ms per token, 26.15 tokens per second) 2.22.421.475 I slot print_timing: id 2 | task 101 | eval time = 204.61 ms / 2 tokens ( 204.61 ms per token, 4.89 tokens per second) 2.22.421.475 I slot print_timing: id 2 | task 101 | total time = 6781.00 ms / 174 tokens 2.22.421.475 I slot print_timing: id 2 | task 101 | graphs reused = 1 2.22.421.475 I slot print_timing: id 2 | task 101 | graph reallocs = 0 / 0 (same size) / (changed size) 2.22.421.495 I slot release: id 2 | task 101 | stop processing: n_tokens = 173, truncated = 0 2.22.421.660 I slot print_timing: id 3 | task 100 | prompt eval time = 6576.57 ms / 118 tokens ( 55.73 ms per token, 17.94 tokens per second) 2.22.421.661 I slot print_timing: id 3 | task 100 | eval time = 204.60 ms / 2 tokens ( 204.60 ms per token, 4.89 tokens per second) 2.22.421.661 I slot print_timing: id 3 | task 100 | total time = 6781.17 ms / 120 tokens 2.22.421.661 I slot print_timing: id 3 | task 100 | graphs reused = 1 2.22.421.662 I slot print_timing: id 3 | task 100 | graph reallocs = 0 / 0 (same size) / (changed size) 2.22.421.669 I slot release: id 3 | task 100 | stop processing: n_tokens = 119, truncated = 0 2.22.427.563 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.213 (> 0.100 thold), f_keep = 0.269 2.22.427.587 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.005 MiB) 2.22.442.660 I slot launch_slot_: id 1 | task 105 | processing task, is_child = 0 2.22.442.681 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 305.693 MiB) 2.22.450.652 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.818 MiB) 2.22.479.374 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.381 MiB) 2.22.487.631 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.250 (> 0.100 thold), f_keep = 0.244 2.22.487.713 I slot launch_slot_: id 3 | task 106 | processing task, is_child = 0 2.22.487.752 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.158 (> 0.100 thold), f_keep = 0.230 2.22.487.810 I slot launch_slot_: id 0 | task 107 | processing task, is_child = 0 2.22.487.835 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.117 (> 0.100 thold), f_keep = 0.162 2.22.487.877 I slot launch_slot_: id 2 | task 108 | processing task, is_child = 0 2.29.067.486 I slot print_timing: id 0 | task 107 | prompt processing, n_tokens = 173, progress = 0.98, t = 6.58 s / 26.29 tokens per second 2.30.531.455 I slot print_timing: id 1 | task 105 | prompt processing, n_tokens = 132, progress = 0.97, t = 6.58 s / 20.06 tokens per second 2.30.536.523 I slot print_timing: id 2 | task 108 | prompt processing, n_tokens = 236, progress = 0.98, t = 6.58 s / 35.87 tokens per second 2.30.541.391 I slot print_timing: id 3 | task 106 | prompt processing, n_tokens = 112, progress = 0.97, t = 6.58 s / 17.02 tokens per second 2.31.090.830 I slot print_timing: id 0 | task 107 | prompt eval time = 8397.92 ms / 177 tokens ( 47.45 ms per token, 21.08 tokens per second) 2.31.090.835 I slot print_timing: id 0 | task 107 | eval time = 205.02 ms / 2 tokens ( 205.02 ms per token, 4.88 tokens per second) 2.31.090.835 I slot print_timing: id 0 | task 107 | total time = 8602.94 ms / 179 tokens 2.31.090.836 I slot print_timing: id 0 | task 107 | graphs reused = 1 2.31.090.836 I slot print_timing: id 0 | task 107 | graph reallocs = 0 / 0 (same size) / (changed size) 2.31.090.858 I slot release: id 0 | task 107 | stop processing: n_tokens = 178, truncated = 0 2.31.091.013 I slot print_timing: id 1 | task 105 | prompt eval time = 8398.08 ms / 136 tokens ( 61.75 ms per token, 16.19 tokens per second) 2.31.091.015 I slot print_timing: id 1 | task 105 | eval time = 205.03 ms / 2 tokens ( 205.03 ms per token, 4.88 tokens per second) 2.31.091.015 I slot print_timing: id 1 | task 105 | total time = 8603.11 ms / 138 tokens 2.31.091.015 I slot print_timing: id 1 | task 105 | graphs reused = 1 2.31.091.016 I slot print_timing: id 1 | task 105 | graph reallocs = 0 / 0 (same size) / (changed size) 2.31.091.028 I slot release: id 1 | task 105 | stop processing: n_tokens = 137, truncated = 0 2.31.091.198 I slot print_timing: id 2 | task 108 | prompt eval time = 8398.25 ms / 240 tokens ( 34.99 ms per token, 28.58 tokens per second) 2.31.091.200 I slot print_timing: id 2 | task 108 | eval time = 205.03 ms / 2 tokens ( 205.03 ms per token, 4.88 tokens per second) 2.31.091.200 I slot print_timing: id 2 | task 108 | total time = 8603.28 ms / 242 tokens 2.31.091.200 I slot print_timing: id 2 | task 108 | graphs reused = 1 2.31.091.201 I slot print_timing: id 2 | task 108 | graph reallocs = 0 / 0 (same size) / (changed size) 2.31.091.214 I slot release: id 2 | task 108 | stop processing: n_tokens = 241, truncated = 0 2.31.091.380 I slot print_timing: id 3 | task 106 | prompt eval time = 8398.45 ms / 116 tokens ( 72.40 ms per token, 13.81 tokens per second) 2.31.091.390 I slot print_timing: id 3 | task 106 | eval time = 205.00 ms / 2 tokens ( 205.00 ms per token, 4.88 tokens per second) 2.31.091.390 I slot print_timing: id 3 | task 106 | total time = 8603.45 ms / 118 tokens 2.31.091.390 I slot print_timing: id 3 | task 106 | graphs reused = 1 2.31.091.390 I slot print_timing: id 3 | task 106 | graph reallocs = 0 / 0 (same size) / (changed size) 2.31.091.398 I slot release: id 3 | task 106 | stop processing: n_tokens = 117, truncated = 0 2.31.097.496 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.218 (> 0.100 thold), f_keep = 0.265 2.31.097.521 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.568 MiB) 2.31.105.711 I slot launch_slot_: id 3 | task 112 | processing task, is_child = 0 2.31.105.743 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.694 MiB) 2.31.131.255 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.694 MiB) 2.31.139.324 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.382 MiB) 2.31.161.998 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.157 2.31.162.081 I slot launch_slot_: id 0 | task 114 | processing task, is_child = 0 2.31.162.122 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.187 (> 0.100 thold), f_keep = 0.212 2.31.165.478 I slot launch_slot_: id 1 | task 113 | processing task, is_child = 0 2.31.165.509 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.124 (> 0.100 thold), f_keep = 0.116 2.31.165.556 I slot launch_slot_: id 2 | task 115 | processing task, is_child = 0 2.38.664.582 I slot print_timing: id 0 | task 114 | prompt processing, n_tokens = 156, progress = 0.97, t = 7.50 s / 20.80 tokens per second 2.39.792.117 I slot print_timing: id 1 | task 113 | prompt processing, n_tokens = 151, progress = 0.97, t = 7.50 s / 20.14 tokens per second 2.39.796.534 I slot print_timing: id 2 | task 115 | prompt processing, n_tokens = 222, progress = 0.98, t = 7.50 s / 29.60 tokens per second 2.39.800.967 I slot print_timing: id 3 | task 112 | prompt processing, n_tokens = 138, progress = 0.97, t = 7.50 s / 18.40 tokens per second 2.40.349.763 I slot print_timing: id 0 | task 114 | prompt eval time = 8979.23 ms / 160 tokens ( 56.12 ms per token, 17.82 tokens per second) 2.40.349.768 I slot print_timing: id 0 | task 114 | eval time = 204.97 ms / 2 tokens ( 204.97 ms per token, 4.88 tokens per second) 2.40.349.769 I slot print_timing: id 0 | task 114 | total time = 9184.20 ms / 162 tokens 2.40.349.769 I slot print_timing: id 0 | task 114 | graphs reused = 1 2.40.349.769 I slot print_timing: id 0 | task 114 | graph reallocs = 0 / 0 (same size) / (changed size) 2.40.349.791 I slot release: id 0 | task 114 | stop processing: n_tokens = 161, truncated = 0 2.40.349.950 I slot print_timing: id 1 | task 113 | prompt eval time = 8979.42 ms / 155 tokens ( 57.93 ms per token, 17.26 tokens per second) 2.40.349.952 I slot print_timing: id 1 | task 113 | eval time = 204.95 ms / 2 tokens ( 204.95 ms per token, 4.88 tokens per second) 2.40.349.954 I slot print_timing: id 1 | task 113 | total time = 9184.36 ms / 157 tokens 2.40.349.954 I slot print_timing: id 1 | task 113 | graphs reused = 1 2.40.349.954 I slot print_timing: id 1 | task 113 | graph reallocs = 0 / 0 (same size) / (changed size) 2.40.349.965 I slot release: id 1 | task 113 | stop processing: n_tokens = 156, truncated = 0 2.40.350.115 I slot print_timing: id 2 | task 115 | prompt eval time = 8979.60 ms / 226 tokens ( 39.73 ms per token, 25.17 tokens per second) 2.40.350.120 I slot print_timing: id 2 | task 115 | eval time = 204.92 ms / 2 tokens ( 204.92 ms per token, 4.88 tokens per second) 2.40.350.120 I slot print_timing: id 2 | task 115 | total time = 9184.52 ms / 228 tokens 2.40.350.120 I slot print_timing: id 2 | task 115 | graphs reused = 1 2.40.350.121 I slot print_timing: id 2 | task 115 | graph reallocs = 0 / 0 (same size) / (changed size) 2.40.350.140 I slot release: id 2 | task 115 | stop processing: n_tokens = 227, truncated = 0 2.40.350.304 I slot print_timing: id 3 | task 112 | prompt eval time = 8979.78 ms / 142 tokens ( 63.24 ms per token, 15.81 tokens per second) 2.40.350.307 I slot print_timing: id 3 | task 112 | eval time = 204.91 ms / 2 tokens ( 204.91 ms per token, 4.88 tokens per second) 2.40.350.307 I slot print_timing: id 3 | task 112 | total time = 9184.69 ms / 144 tokens 2.40.350.307 I slot print_timing: id 3 | task 112 | graphs reused = 1 2.40.350.308 I slot print_timing: id 3 | task 112 | graph reallocs = 0 / 0 (same size) / (changed size) 2.40.350.315 I slot release: id 3 | task 112 | stop processing: n_tokens = 143, truncated = 0 2.40.355.864 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.254 (> 0.100 thold), f_keep = 0.186 2.40.364.695 I slot launch_slot_: id 1 | task 120 | processing task, is_child = 0 2.40.364.726 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.631 MiB) 2.40.372.654 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.882 MiB) 2.40.401.726 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.005 MiB) 2.40.409.537 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.295 (> 0.100 thold), f_keep = 0.217 2.40.409.614 I slot launch_slot_: id 3 | task 119 | processing task, is_child = 0 2.40.409.661 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.174 2.40.409.702 I slot launch_slot_: id 0 | task 121 | processing task, is_child = 0 2.40.409.736 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.146 (> 0.100 thold), f_keep = 0.123 2.40.413.058 I slot launch_slot_: id 2 | task 122 | processing task, is_child = 0 2.46.028.611 I slot print_timing: id 0 | task 121 | prompt processing, n_tokens = 137, progress = 0.97, t = 5.62 s / 24.40 tokens per second 2.47.165.087 I slot print_timing: id 1 | task 120 | prompt processing, n_tokens = 110, progress = 0.96, t = 5.62 s / 19.59 tokens per second 2.47.169.719 I slot print_timing: id 2 | task 122 | prompt processing, n_tokens = 188, progress = 0.98, t = 5.62 s / 33.48 tokens per second 2.47.174.163 I slot print_timing: id 3 | task 119 | prompt processing, n_tokens = 101, progress = 0.96, t = 5.62 s / 17.99 tokens per second 2.47.723.114 I slot print_timing: id 0 | task 121 | prompt eval time = 7105.15 ms / 141 tokens ( 50.39 ms per token, 19.84 tokens per second) 2.47.723.119 I slot print_timing: id 0 | task 121 | eval time = 204.89 ms / 2 tokens ( 204.89 ms per token, 4.88 tokens per second) 2.47.723.120 I slot print_timing: id 0 | task 121 | total time = 7310.04 ms / 143 tokens 2.47.723.120 I slot print_timing: id 0 | task 121 | graphs reused = 1 2.47.723.121 I slot print_timing: id 0 | task 121 | graph reallocs = 0 / 0 (same size) / (changed size) 2.47.723.143 I slot release: id 0 | task 121 | stop processing: n_tokens = 142, truncated = 0 2.47.723.289 I slot print_timing: id 1 | task 120 | prompt eval time = 7105.32 ms / 114 tokens ( 62.33 ms per token, 16.04 tokens per second) 2.47.723.291 I slot print_timing: id 1 | task 120 | eval time = 204.87 ms / 2 tokens ( 204.87 ms per token, 4.88 tokens per second) 2.47.723.292 I slot print_timing: id 1 | task 120 | total time = 7310.19 ms / 116 tokens 2.47.723.292 I slot print_timing: id 1 | task 120 | graphs reused = 1 2.47.723.292 I slot print_timing: id 1 | task 120 | graph reallocs = 0 / 0 (same size) / (changed size) 2.47.723.309 I slot release: id 1 | task 120 | stop processing: n_tokens = 115, truncated = 0 2.47.723.474 I slot print_timing: id 2 | task 122 | prompt eval time = 7105.50 ms / 192 tokens ( 37.01 ms per token, 27.02 tokens per second) 2.47.723.478 I slot print_timing: id 2 | task 122 | eval time = 204.85 ms / 2 tokens ( 204.85 ms per token, 4.88 tokens per second) 2.47.723.479 I slot print_timing: id 2 | task 122 | total time = 7310.36 ms / 194 tokens 2.47.723.479 I slot print_timing: id 2 | task 122 | graphs reused = 1 2.47.723.479 I slot print_timing: id 2 | task 122 | graph reallocs = 0 / 0 (same size) / (changed size) 2.47.723.496 I slot release: id 2 | task 122 | stop processing: n_tokens = 193, truncated = 0 2.47.723.665 I slot print_timing: id 3 | task 119 | prompt eval time = 7105.71 ms / 105 tokens ( 67.67 ms per token, 14.78 tokens per second) 2.47.723.666 I slot print_timing: id 3 | task 119 | eval time = 204.83 ms / 2 tokens ( 204.83 ms per token, 4.88 tokens per second) 2.47.723.667 I slot print_timing: id 3 | task 119 | total time = 7310.54 ms / 107 tokens 2.47.723.667 I slot print_timing: id 3 | task 119 | graphs reused = 1 2.47.723.667 I slot print_timing: id 3 | task 119 | graph reallocs = 0 / 0 (same size) / (changed size) 2.47.723.681 I slot release: id 3 | task 119 | stop processing: n_tokens = 106, truncated = 0 2.47.729.487 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.269 (> 0.100 thold), f_keep = 0.252 2.47.738.127 I slot launch_slot_: id 1 | task 126 | processing task, is_child = 0 2.47.738.148 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.068 MiB) 2.47.746.211 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.381 MiB) 2.47.754.323 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.318 MiB) 2.47.762.383 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.207 (> 0.100 thold), f_keep = 0.197 2.47.762.447 I slot launch_slot_: id 0 | task 128 | processing task, is_child = 0 2.47.762.489 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.238 (> 0.100 thold), f_keep = 0.274 2.47.762.518 I slot launch_slot_: id 3 | task 127 | processing task, is_child = 0 2.47.762.538 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.163 (> 0.100 thold), f_keep = 0.145 2.47.762.577 I slot launch_slot_: id 2 | task 129 | processing task, is_child = 0 2.53.313.628 I slot print_timing: id 0 | task 128 | prompt processing, n_tokens = 131, progress = 0.97, t = 5.55 s / 23.60 tokens per second 2.54.083.390 I slot print_timing: id 1 | task 126 | prompt processing, n_tokens = 104, progress = 0.96, t = 5.55 s / 18.74 tokens per second 2.54.087.948 I slot print_timing: id 2 | task 129 | prompt processing, n_tokens = 168, progress = 0.98, t = 5.55 s / 30.26 tokens per second 2.54.092.901 I slot print_timing: id 3 | task 127 | prompt processing, n_tokens = 118, progress = 0.97, t = 5.55 s / 21.26 tokens per second 2.54.642.751 I slot print_timing: id 0 | task 128 | prompt eval time = 6675.00 ms / 135 tokens ( 49.44 ms per token, 20.22 tokens per second) 2.54.642.753 I slot print_timing: id 0 | task 128 | eval time = 205.16 ms / 2 tokens ( 205.16 ms per token, 4.87 tokens per second) 2.54.642.754 I slot print_timing: id 0 | task 128 | total time = 6880.16 ms / 137 tokens 2.54.642.754 I slot print_timing: id 0 | task 128 | graphs reused = 1 2.54.642.755 I slot print_timing: id 0 | task 128 | graph reallocs = 0 / 0 (same size) / (changed size) 2.54.642.778 I slot release: id 0 | task 128 | stop processing: n_tokens = 136, truncated = 0 2.54.642.926 I slot print_timing: id 1 | task 126 | prompt eval time = 6675.19 ms / 108 tokens ( 61.81 ms per token, 16.18 tokens per second) 2.54.642.929 I slot print_timing: id 1 | task 126 | eval time = 205.13 ms / 2 tokens ( 205.13 ms per token, 4.87 tokens per second) 2.54.642.930 I slot print_timing: id 1 | task 126 | total time = 6880.32 ms / 110 tokens 2.54.642.931 I slot print_timing: id 1 | task 126 | graphs reused = 1 2.54.642.931 I slot print_timing: id 1 | task 126 | graph reallocs = 0 / 0 (same size) / (changed size) 2.54.642.940 I slot release: id 1 | task 126 | stop processing: n_tokens = 109, truncated = 0 2.54.643.110 I slot print_timing: id 2 | task 129 | prompt eval time = 6675.39 ms / 172 tokens ( 38.81 ms per token, 25.77 tokens per second) 2.54.643.111 I slot print_timing: id 2 | task 129 | eval time = 205.10 ms / 2 tokens ( 205.10 ms per token, 4.88 tokens per second) 2.54.643.112 I slot print_timing: id 2 | task 129 | total time = 6880.50 ms / 174 tokens 2.54.643.112 I slot print_timing: id 2 | task 129 | graphs reused = 1 2.54.643.112 I slot print_timing: id 2 | task 129 | graph reallocs = 0 / 0 (same size) / (changed size) 2.54.643.124 I slot release: id 2 | task 129 | stop processing: n_tokens = 173, truncated = 0 2.54.643.307 I slot print_timing: id 3 | task 127 | prompt eval time = 6675.59 ms / 122 tokens ( 54.72 ms per token, 18.28 tokens per second) 2.54.643.314 I slot print_timing: id 3 | task 127 | eval time = 205.09 ms / 2 tokens ( 205.09 ms per token, 4.88 tokens per second) 2.54.643.315 I slot print_timing: id 3 | task 127 | total time = 6880.68 ms / 124 tokens 2.54.643.315 I slot print_timing: id 3 | task 127 | graphs reused = 1 2.54.643.315 I slot print_timing: id 3 | task 127 | graph reallocs = 0 / 0 (same size) / (changed size) 2.54.643.323 I slot release: id 3 | task 127 | stop processing: n_tokens = 123, truncated = 0 2.54.648.834 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.207 (> 0.100 thold), f_keep = 0.206 2.54.648.856 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.506 MiB) 2.54.661.130 I slot launch_slot_: id 0 | task 133 | processing task, is_child = 0 2.54.661.150 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.756 MiB) 2.54.669.004 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.569 MiB) 2.54.677.316 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.943 MiB) 2.54.685.262 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.242 (> 0.100 thold), f_keep = 0.266 2.54.688.617 I slot launch_slot_: id 1 | task 134 | processing task, is_child = 0 2.54.688.656 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.209 (> 0.100 thold), f_keep = 0.162 2.54.688.689 I slot launch_slot_: id 2 | task 135 | processing task, is_child = 0 2.54.688.715 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.176 (> 0.100 thold), f_keep = 0.228 2.54.688.744 I slot launch_slot_: id 3 | task 136 | processing task, is_child = 0 3.00.818.966 I slot print_timing: id 0 | task 133 | prompt processing, n_tokens = 131, progress = 0.97, t = 6.13 s / 21.37 tokens per second 3.01.248.073 I slot print_timing: id 1 | task 134 | prompt processing, n_tokens = 116, progress = 0.97, t = 6.13 s / 18.92 tokens per second 3.01.253.081 I slot print_timing: id 2 | task 135 | prompt processing, n_tokens = 130, progress = 0.97, t = 6.13 s / 21.21 tokens per second 3.01.257.818 I slot print_timing: id 3 | task 136 | prompt processing, n_tokens = 155, progress = 0.97, t = 6.13 s / 25.28 tokens per second 3.01.806.437 I slot print_timing: id 0 | task 133 | prompt eval time = 6913.84 ms / 135 tokens ( 51.21 ms per token, 19.53 tokens per second) 3.01.806.439 I slot print_timing: id 0 | task 133 | eval time = 203.84 ms / 2 tokens ( 203.84 ms per token, 4.91 tokens per second) 3.01.806.440 I slot print_timing: id 0 | task 133 | total time = 7117.68 ms / 137 tokens 3.01.806.440 I slot print_timing: id 0 | task 133 | graphs reused = 1 3.01.806.440 I slot print_timing: id 0 | task 133 | graph reallocs = 0 / 0 (same size) / (changed size) 3.01.806.467 I slot release: id 0 | task 133 | stop processing: n_tokens = 136, truncated = 0 3.01.806.617 I slot print_timing: id 1 | task 134 | prompt eval time = 6914.02 ms / 120 tokens ( 57.62 ms per token, 17.36 tokens per second) 3.01.806.622 I slot print_timing: id 1 | task 134 | eval time = 203.83 ms / 2 tokens ( 203.83 ms per token, 4.91 tokens per second) 3.01.806.623 I slot print_timing: id 1 | task 134 | total time = 7117.85 ms / 122 tokens 3.01.806.623 I slot print_timing: id 1 | task 134 | graphs reused = 1 3.01.806.624 I slot print_timing: id 1 | task 134 | graph reallocs = 0 / 0 (same size) / (changed size) 3.01.806.634 I slot release: id 1 | task 134 | stop processing: n_tokens = 121, truncated = 0 3.01.806.810 I slot print_timing: id 2 | task 135 | prompt eval time = 6914.21 ms / 134 tokens ( 51.60 ms per token, 19.38 tokens per second) 3.01.806.814 I slot print_timing: id 2 | task 135 | eval time = 203.82 ms / 2 tokens ( 203.82 ms per token, 4.91 tokens per second) 3.01.806.814 I slot print_timing: id 2 | task 135 | total time = 7118.03 ms / 136 tokens 3.01.806.815 I slot print_timing: id 2 | task 135 | graphs reused = 1 3.01.806.815 I slot print_timing: id 2 | task 135 | graph reallocs = 0 / 0 (same size) / (changed size) 3.01.806.832 I slot release: id 2 | task 135 | stop processing: n_tokens = 135, truncated = 0 3.01.806.999 I slot print_timing: id 3 | task 136 | prompt eval time = 6914.40 ms / 159 tokens ( 43.49 ms per token, 23.00 tokens per second) 3.01.807.001 I slot print_timing: id 3 | task 136 | eval time = 203.81 ms / 2 tokens ( 203.81 ms per token, 4.91 tokens per second) 3.01.807.002 I slot print_timing: id 3 | task 136 | total time = 7118.20 ms / 161 tokens 3.01.807.002 I slot print_timing: id 3 | task 136 | graphs reused = 1 3.01.807.002 I slot print_timing: id 3 | task 136 | graph reallocs = 0 / 0 (same size) / (changed size) 3.01.807.010 I slot release: id 3 | task 136 | stop processing: n_tokens = 160, truncated = 0 3.01.813.045 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.215 (> 0.100 thold), f_keep = 0.206 3.01.820.872 I slot launch_slot_: id 0 | task 140 | processing task, is_child = 0 3.01.820.893 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.506 MiB) 3.01.828.788 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.506 MiB) 3.01.836.814 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.818 MiB) 3.01.845.174 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.156 (> 0.100 thold), f_keep = 0.231 3.01.845.235 I slot launch_slot_: id 1 | task 141 | processing task, is_child = 0 3.01.845.269 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.163 (> 0.100 thold), f_keep = 0.207 3.01.845.299 I slot launch_slot_: id 2 | task 142 | processing task, is_child = 0 3.01.845.319 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.160 (> 0.100 thold), f_keep = 0.175 3.01.845.351 I slot launch_slot_: id 3 | task 143 | processing task, is_child = 0 3.09.299.963 I slot print_timing: id 0 | task 140 | prompt processing, n_tokens = 126, progress = 0.97, t = 7.45 s / 16.90 tokens per second 3.09.466.389 I slot print_timing: id 1 | task 141 | prompt processing, n_tokens = 176, progress = 0.98, t = 7.45 s / 23.61 tokens per second 3.09.471.055 I slot print_timing: id 2 | task 142 | prompt processing, n_tokens = 168, progress = 0.98, t = 7.45 s / 22.54 tokens per second 3.09.476.000 I slot print_timing: id 3 | task 143 | prompt processing, n_tokens = 171, progress = 0.98, t = 7.45 s / 22.94 tokens per second 3.10.025.764 I slot print_timing: id 0 | task 140 | prompt eval time = 7975.43 ms / 130 tokens ( 61.35 ms per token, 16.30 tokens per second) 3.10.025.766 I slot print_timing: id 0 | task 140 | eval time = 204.97 ms / 2 tokens ( 204.97 ms per token, 4.88 tokens per second) 3.10.025.767 I slot print_timing: id 0 | task 140 | total time = 8180.40 ms / 132 tokens 3.10.025.767 I slot print_timing: id 0 | task 140 | graphs reused = 1 3.10.025.768 I slot print_timing: id 0 | task 140 | graph reallocs = 0 / 0 (same size) / (changed size) 3.10.025.790 I slot release: id 0 | task 140 | stop processing: n_tokens = 131, truncated = 0 3.10.025.940 I slot print_timing: id 1 | task 141 | prompt eval time = 7975.58 ms / 180 tokens ( 44.31 ms per token, 22.57 tokens per second) 3.10.025.941 I slot print_timing: id 1 | task 141 | eval time = 204.99 ms / 2 tokens ( 204.99 ms per token, 4.88 tokens per second) 3.10.025.942 I slot print_timing: id 1 | task 141 | total time = 8180.57 ms / 182 tokens 3.10.025.942 I slot print_timing: id 1 | task 141 | graphs reused = 1 3.10.025.942 I slot print_timing: id 1 | task 141 | graph reallocs = 0 / 0 (same size) / (changed size) 3.10.025.957 I slot release: id 1 | task 141 | stop processing: n_tokens = 181, truncated = 0 3.10.026.130 I slot print_timing: id 2 | task 142 | prompt eval time = 7975.76 ms / 172 tokens ( 46.37 ms per token, 21.57 tokens per second) 3.10.026.135 I slot print_timing: id 2 | task 142 | eval time = 204.99 ms / 2 tokens ( 204.99 ms per token, 4.88 tokens per second) 3.10.026.136 I slot print_timing: id 2 | task 142 | total time = 8180.75 ms / 174 tokens 3.10.026.136 I slot print_timing: id 2 | task 142 | graphs reused = 1 3.10.026.136 I slot print_timing: id 2 | task 142 | graph reallocs = 0 / 0 (same size) / (changed size) 3.10.026.147 I slot release: id 2 | task 142 | stop processing: n_tokens = 173, truncated = 0 3.10.026.317 I slot print_timing: id 3 | task 143 | prompt eval time = 7975.94 ms / 175 tokens ( 45.58 ms per token, 21.94 tokens per second) 3.10.026.318 I slot print_timing: id 3 | task 143 | eval time = 204.97 ms / 2 tokens ( 204.97 ms per token, 4.88 tokens per second) 3.10.026.319 I slot print_timing: id 3 | task 143 | total time = 8180.92 ms / 177 tokens 3.10.026.319 I slot print_timing: id 3 | task 143 | graphs reused = 1 3.10.026.319 I slot print_timing: id 3 | task 143 | graph reallocs = 0 / 0 (same size) / (changed size) 3.10.026.330 I slot release: id 3 | task 143 | stop processing: n_tokens = 176, truncated = 0 3.10.032.424 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.243 (> 0.100 thold), f_keep = 0.214 3.10.032.449 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.318 MiB) 3.10.043.912 I slot launch_slot_: id 0 | task 147 | processing task, is_child = 0 3.10.051.928 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.131 MiB) 3.10.059.966 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.068 MiB) 3.10.088.607 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.243 (> 0.100 thold), f_keep = 0.155 3.10.088.679 I slot launch_slot_: id 1 | task 148 | processing task, is_child = 0 3.10.088.718 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.162 3.10.088.752 I slot launch_slot_: id 2 | task 149 | processing task, is_child = 0 3.10.088.772 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.159 3.10.092.081 I slot launch_slot_: id 3 | task 150 | processing task, is_child = 0 3.15.175.124 I slot print_timing: id 0 | task 147 | prompt processing, n_tokens = 111, progress = 0.97, t = 5.08 s / 21.84 tokens per second 3.15.472.729 I slot print_timing: id 1 | task 148 | prompt processing, n_tokens = 111, progress = 0.97, t = 5.08 s / 21.84 tokens per second 3.15.477.332 I slot print_timing: id 2 | task 149 | prompt processing, n_tokens = 119, progress = 0.97, t = 5.08 s / 23.41 tokens per second 3.15.481.963 I slot print_timing: id 3 | task 150 | prompt processing, n_tokens = 119, progress = 0.97, t = 5.08 s / 23.41 tokens per second 3.16.031.540 I slot print_timing: id 0 | task 147 | prompt eval time = 5734.44 ms / 115 tokens ( 49.86 ms per token, 20.05 tokens per second) 3.16.031.542 I slot print_timing: id 0 | task 147 | eval time = 205.00 ms / 2 tokens ( 205.00 ms per token, 4.88 tokens per second) 3.16.031.543 I slot print_timing: id 0 | task 147 | total time = 5939.44 ms / 117 tokens 3.16.031.543 I slot print_timing: id 0 | task 147 | graphs reused = 1 3.16.031.543 I slot print_timing: id 0 | task 147 | graph reallocs = 0 / 0 (same size) / (changed size) 3.16.031.566 I slot release: id 0 | task 147 | stop processing: n_tokens = 116, truncated = 0 3.16.031.714 I slot print_timing: id 1 | task 148 | prompt eval time = 5734.63 ms / 115 tokens ( 49.87 ms per token, 20.05 tokens per second) 3.16.031.719 I slot print_timing: id 1 | task 148 | eval time = 204.98 ms / 2 tokens ( 204.98 ms per token, 4.88 tokens per second) 3.16.031.720 I slot print_timing: id 1 | task 148 | total time = 5939.61 ms / 117 tokens 3.16.031.720 I slot print_timing: id 1 | task 148 | graphs reused = 1 3.16.031.720 I slot print_timing: id 1 | task 148 | graph reallocs = 0 / 0 (same size) / (changed size) 3.16.031.729 I slot release: id 1 | task 148 | stop processing: n_tokens = 116, truncated = 0 3.16.031.904 I slot print_timing: id 2 | task 149 | prompt eval time = 5734.82 ms / 123 tokens ( 46.62 ms per token, 21.45 tokens per second) 3.16.031.905 I slot print_timing: id 2 | task 149 | eval time = 204.97 ms / 2 tokens ( 204.97 ms per token, 4.88 tokens per second) 3.16.031.905 I slot print_timing: id 2 | task 149 | total time = 5939.79 ms / 125 tokens 3.16.031.906 I slot print_timing: id 2 | task 149 | graphs reused = 1 3.16.031.906 I slot print_timing: id 2 | task 149 | graph reallocs = 0 / 0 (same size) / (changed size) 3.16.031.918 I slot release: id 2 | task 149 | stop processing: n_tokens = 124, truncated = 0 3.16.032.090 I slot print_timing: id 3 | task 150 | prompt eval time = 5735.21 ms / 123 tokens ( 46.63 ms per token, 21.45 tokens per second) 3.16.032.092 I slot print_timing: id 3 | task 150 | eval time = 204.75 ms / 2 tokens ( 204.75 ms per token, 4.88 tokens per second) 3.16.032.092 I slot print_timing: id 3 | task 150 | total time = 5939.96 ms / 125 tokens 3.16.032.092 I slot print_timing: id 3 | task 150 | graphs reused = 1 3.16.032.093 I slot print_timing: id 3 | task 150 | graph reallocs = 0 / 0 (same size) / (changed size) 3.16.032.098 I slot release: id 3 | task 150 | stop processing: n_tokens = 124, truncated = 0 3.16.038.385 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.219 (> 0.100 thold), f_keep = 0.241 3.16.046.548 I slot launch_slot_: id 0 | task 154 | processing task, is_child = 0 3.16.046.571 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.506 MiB) 3.16.054.395 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.880 MiB) 3.16.062.160 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.069 MiB) 3.16.069.934 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.234 3.16.073.311 I slot launch_slot_: id 3 | task 156 | processing task, is_child = 0 3.16.073.353 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.215 (> 0.100 thold), f_keep = 0.241 3.16.073.388 I slot launch_slot_: id 1 | task 155 | processing task, is_child = 0 3.16.073.408 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.226 3.16.073.444 I slot launch_slot_: id 2 | task 157 | processing task, is_child = 0 3.22.167.326 I slot print_timing: id 0 | task 154 | prompt processing, n_tokens = 124, progress = 0.97, t = 6.09 s / 20.35 tokens per second 3.22.445.920 I slot print_timing: id 1 | task 155 | prompt processing, n_tokens = 126, progress = 0.97, t = 6.09 s / 20.68 tokens per second 3.22.450.689 I slot print_timing: id 2 | task 157 | prompt processing, n_tokens = 137, progress = 0.97, t = 6.09 s / 22.48 tokens per second 3.22.455.596 I slot print_timing: id 3 | task 156 | prompt processing, n_tokens = 123, progress = 0.97, t = 6.09 s / 20.18 tokens per second 3.23.004.910 I slot print_timing: id 0 | task 154 | prompt eval time = 6726.73 ms / 128 tokens ( 52.55 ms per token, 19.03 tokens per second) 3.23.004.913 I slot print_timing: id 0 | task 154 | eval time = 204.73 ms / 2 tokens ( 204.73 ms per token, 4.88 tokens per second) 3.23.004.914 I slot print_timing: id 0 | task 154 | total time = 6931.46 ms / 130 tokens 3.23.004.914 I slot print_timing: id 0 | task 154 | graphs reused = 1 3.23.004.914 I slot print_timing: id 0 | task 154 | graph reallocs = 0 / 0 (same size) / (changed size) 3.23.004.936 I slot release: id 0 | task 154 | stop processing: n_tokens = 129, truncated = 0 3.23.005.090 I slot print_timing: id 1 | task 155 | prompt eval time = 6726.87 ms / 130 tokens ( 51.75 ms per token, 19.33 tokens per second) 3.23.005.093 I slot print_timing: id 1 | task 155 | eval time = 204.76 ms / 2 tokens ( 204.76 ms per token, 4.88 tokens per second) 3.23.005.093 I slot print_timing: id 1 | task 155 | total time = 6931.62 ms / 132 tokens 3.23.005.094 I slot print_timing: id 1 | task 155 | graphs reused = 1 3.23.005.094 I slot print_timing: id 1 | task 155 | graph reallocs = 0 / 0 (same size) / (changed size) 3.23.005.109 I slot release: id 1 | task 155 | stop processing: n_tokens = 131, truncated = 0 3.23.005.274 I slot print_timing: id 2 | task 157 | prompt eval time = 6727.01 ms / 141 tokens ( 47.71 ms per token, 20.96 tokens per second) 3.23.005.276 I slot print_timing: id 2 | task 157 | eval time = 204.78 ms / 2 tokens ( 204.78 ms per token, 4.88 tokens per second) 3.23.005.277 I slot print_timing: id 2 | task 157 | total time = 6931.80 ms / 143 tokens 3.23.005.278 I slot print_timing: id 2 | task 157 | graphs reused = 1 3.23.005.278 I slot print_timing: id 2 | task 157 | graph reallocs = 0 / 0 (same size) / (changed size) 3.23.005.289 I slot release: id 2 | task 157 | stop processing: n_tokens = 142, truncated = 0 3.23.005.444 I slot print_timing: id 3 | task 156 | prompt eval time = 6727.20 ms / 127 tokens ( 52.97 ms per token, 18.88 tokens per second) 3.23.005.446 I slot print_timing: id 3 | task 156 | eval time = 204.75 ms / 2 tokens ( 204.75 ms per token, 4.88 tokens per second) 3.23.005.446 I slot print_timing: id 3 | task 156 | total time = 6931.95 ms / 129 tokens 3.23.005.446 I slot print_timing: id 3 | task 156 | graphs reused = 1 3.23.005.447 I slot print_timing: id 3 | task 156 | graph reallocs = 0 / 0 (same size) / (changed size) 3.23.005.456 I slot release: id 3 | task 156 | stop processing: n_tokens = 128, truncated = 0 3.23.011.105 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.276 (> 0.100 thold), f_keep = 0.227 3.23.019.576 I slot launch_slot_: id 3 | task 161 | processing task, is_child = 0 3.23.019.600 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.693 MiB) 3.23.027.690 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.382 MiB) 3.23.035.579 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.818 MiB) 3.23.043.626 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.217 (> 0.100 thold), f_keep = 0.217 3.23.043.709 I slot launch_slot_: id 0 | task 162 | processing task, is_child = 0 3.23.043.746 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.214 3.23.043.785 I slot launch_slot_: id 1 | task 163 | processing task, is_child = 0 3.23.043.806 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.174 (> 0.100 thold), f_keep = 0.197 3.23.043.846 I slot launch_slot_: id 2 | task 164 | processing task, is_child = 0 3.28.757.861 I slot print_timing: id 0 | task 162 | prompt processing, n_tokens = 125, progress = 0.97, t = 5.71 s / 21.88 tokens per second 3.29.515.546 I slot print_timing: id 1 | task 163 | prompt processing, n_tokens = 119, progress = 0.97, t = 5.71 s / 20.83 tokens per second 3.29.519.992 I slot print_timing: id 2 | task 164 | prompt processing, n_tokens = 157, progress = 0.98, t = 5.71 s / 27.48 tokens per second 3.29.524.423 I slot print_timing: id 3 | task 161 | prompt processing, n_tokens = 101, progress = 0.96, t = 5.71 s / 17.68 tokens per second 3.30.072.947 I slot print_timing: id 0 | task 162 | prompt eval time = 6824.53 ms / 129 tokens ( 52.90 ms per token, 18.90 tokens per second) 3.30.072.950 I slot print_timing: id 0 | task 162 | eval time = 204.56 ms / 2 tokens ( 204.56 ms per token, 4.89 tokens per second) 3.30.072.950 I slot print_timing: id 0 | task 162 | total time = 7029.09 ms / 131 tokens 3.30.072.951 I slot print_timing: id 0 | task 162 | graphs reused = 1 3.30.072.951 I slot print_timing: id 0 | task 162 | graph reallocs = 0 / 0 (same size) / (changed size) 3.30.072.973 I slot release: id 0 | task 162 | stop processing: n_tokens = 130, truncated = 0 3.30.073.123 I slot print_timing: id 1 | task 163 | prompt eval time = 6824.66 ms / 123 tokens ( 55.49 ms per token, 18.02 tokens per second) 3.30.073.127 I slot print_timing: id 1 | task 163 | eval time = 204.59 ms / 2 tokens ( 204.59 ms per token, 4.89 tokens per second) 3.30.073.127 I slot print_timing: id 1 | task 163 | total time = 7029.25 ms / 125 tokens 3.30.073.127 I slot print_timing: id 1 | task 163 | graphs reused = 1 3.30.073.128 I slot print_timing: id 1 | task 163 | graph reallocs = 0 / 0 (same size) / (changed size) 3.30.073.140 I slot release: id 1 | task 163 | stop processing: n_tokens = 124, truncated = 0 3.30.073.306 I slot print_timing: id 2 | task 164 | prompt eval time = 6824.81 ms / 161 tokens ( 42.39 ms per token, 23.59 tokens per second) 3.30.073.308 I slot print_timing: id 2 | task 164 | eval time = 204.61 ms / 2 tokens ( 204.61 ms per token, 4.89 tokens per second) 3.30.073.308 I slot print_timing: id 2 | task 164 | total time = 7029.42 ms / 163 tokens 3.30.073.308 I slot print_timing: id 2 | task 164 | graphs reused = 1 3.30.073.309 I slot print_timing: id 2 | task 164 | graph reallocs = 0 / 0 (same size) / (changed size) 3.30.073.320 I slot release: id 2 | task 164 | stop processing: n_tokens = 162, truncated = 0 3.30.073.496 I slot print_timing: id 3 | task 161 | prompt eval time = 6824.95 ms / 105 tokens ( 65.00 ms per token, 15.38 tokens per second) 3.30.073.498 I slot print_timing: id 3 | task 161 | eval time = 204.64 ms / 2 tokens ( 204.64 ms per token, 4.89 tokens per second) 3.30.073.499 I slot print_timing: id 3 | task 161 | total time = 7029.60 ms / 107 tokens 3.30.073.499 I slot print_timing: id 3 | task 161 | graphs reused = 1 3.30.073.499 I slot print_timing: id 3 | task 161 | graph reallocs = 0 / 0 (same size) / (changed size) 3.30.073.507 I slot release: id 3 | task 161 | stop processing: n_tokens = 106, truncated = 0 3.30.079.180 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.264 (> 0.100 thold), f_keep = 0.274 3.30.079.205 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 314.321 MiB) 3.30.087.151 I slot launch_slot_: id 3 | task 168 | processing task, is_child = 0 3.30.087.174 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.006 MiB) 3.30.095.274 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.319 MiB) 3.30.103.264 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 313.445 MiB) 3.30.111.405 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.215 3.30.111.469 I slot launch_slot_: id 0 | task 169 | processing task, is_child = 0 3.30.111.503 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.182 (> 0.100 thold), f_keep = 0.226 3.30.111.533 I slot launch_slot_: id 1 | task 170 | processing task, is_child = 0 3.30.111.553 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.171 (> 0.100 thold), f_keep = 0.173 3.30.111.590 I slot launch_slot_: id 2 | task 171 | processing task, is_child = 0 3.36.760.894 I slot print_timing: id 0 | task 169 | prompt processing, n_tokens = 137, progress = 0.97, t = 6.65 s / 20.60 tokens per second 3.37.037.309 I slot print_timing: id 1 | task 170 | prompt processing, n_tokens = 150, progress = 0.97, t = 6.65 s / 22.56 tokens per second 3.37.042.253 I slot print_timing: id 2 | task 171 | prompt processing, n_tokens = 160, progress = 0.98, t = 6.65 s / 24.06 tokens per second 3.37.047.309 I slot print_timing: id 3 | task 168 | prompt processing, n_tokens = 106, progress = 0.96, t = 6.65 s / 15.94 tokens per second 3.37.596.501 I slot print_timing: id 0 | task 169 | prompt eval time = 7280.13 ms / 141 tokens ( 51.63 ms per token, 19.37 tokens per second) 3.37.596.503 I slot print_timing: id 0 | task 169 | eval time = 204.77 ms / 2 tokens ( 204.77 ms per token, 4.88 tokens per second) 3.37.596.504 I slot print_timing: id 0 | task 169 | total time = 7484.90 ms / 143 tokens 3.37.596.504 I slot print_timing: id 0 | task 169 | graphs reused = 1 3.37.596.504 I slot print_timing: id 0 | task 169 | graph reallocs = 0 / 0 (same size) / (changed size) 3.37.596.527 I slot release: id 0 | task 169 | stop processing: n_tokens = 142, truncated = 0 3.37.596.675 I slot print_timing: id 1 | task 170 | prompt eval time = 7280.27 ms / 154 tokens ( 47.27 ms per token, 21.15 tokens per second) 3.37.596.677 I slot print_timing: id 1 | task 170 | eval time = 204.79 ms / 2 tokens ( 204.79 ms per token, 4.88 tokens per second) 3.37.596.677 I slot print_timing: id 1 | task 170 | total time = 7485.06 ms / 156 tokens 3.37.596.677 I slot print_timing: id 1 | task 170 | graphs reused = 1 3.37.596.678 I slot print_timing: id 1 | task 170 | graph reallocs = 0 / 0 (same size) / (changed size) 3.37.596.689 I slot release: id 1 | task 170 | stop processing: n_tokens = 155, truncated = 0 3.37.596.867 I slot print_timing: id 2 | task 171 | prompt eval time = 7280.41 ms / 164 tokens ( 44.39 ms per token, 22.53 tokens per second) 3.37.596.868 I slot print_timing: id 2 | task 171 | eval time = 204.83 ms / 2 tokens ( 204.83 ms per token, 4.88 tokens per second) 3.37.596.869 I slot print_timing: id 2 | task 171 | total time = 7485.24 ms / 166 tokens 3.37.596.869 I slot print_timing: id 2 | task 171 | graphs reused = 1 3.37.596.869 I slot print_timing: id 2 | task 171 | graph reallocs = 0 / 0 (same size) / (changed size) 3.37.596.879 I slot release: id 2 | task 171 | stop processing: n_tokens = 165, truncated = 0 3.37.597.053 I slot print_timing: id 3 | task 168 | prompt eval time = 7280.56 ms / 110 tokens ( 66.19 ms per token, 15.11 tokens per second) 3.37.597.059 I slot print_timing: id 3 | task 168 | eval time = 204.85 ms / 2 tokens ( 204.85 ms per token, 4.88 tokens per second) 3.37.597.059 I slot print_timing: id 3 | task 168 | total time = 7485.41 ms / 112 tokens 3.37.597.059 I slot print_timing: id 3 | task 168 | graphs reused = 1 3.37.597.059 I slot print_timing: id 3 | task 168 | graph reallocs = 0 / 0 (same size) / (changed size) 3.37.597.066 I slot release: id 3 | task 168 | stop processing: n_tokens = 111, truncated = 0 3.37.603.127 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.255 (> 0.100 thold), f_keep = 0.197 3.37.603.152 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.193 MiB) 3.37.611.960 I slot launch_slot_: id 0 | task 176 | processing task, is_child = 0 3.37.611.981 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.131 MiB) 3.37.620.253 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 311.320 MiB) 3.37.628.797 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.756 MiB) 3.37.637.557 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.204 (> 0.100 thold), f_keep = 0.181 3.37.637.626 I slot launch_slot_: id 1 | task 177 | processing task, is_child = 0 3.37.637.666 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.264 (> 0.100 thold), f_keep = 0.261 3.37.637.700 I slot launch_slot_: id 3 | task 175 | processing task, is_child = 0 3.37.637.720 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.189 (> 0.100 thold), f_keep = 0.170 3.37.637.763 I slot launch_slot_: id 2 | task 178 | processing task, is_child = 0 3.43.473.243 I slot print_timing: id 0 | task 176 | prompt processing, n_tokens = 106, progress = 0.96, t = 5.84 s / 18.16 tokens per second 3.43.749.719 I slot print_timing: id 1 | task 177 | prompt processing, n_tokens = 133, progress = 0.97, t = 5.84 s / 22.79 tokens per second 3.43.754.702 I slot print_timing: id 2 | task 178 | prompt processing, n_tokens = 144, progress = 0.97, t = 5.84 s / 24.68 tokens per second 3.43.759.539 I slot print_timing: id 3 | task 175 | prompt processing, n_tokens = 106, progress = 0.96, t = 5.84 s / 18.16 tokens per second 3.44.308.929 I slot print_timing: id 0 | task 176 | prompt eval time = 6466.54 ms / 110 tokens ( 58.79 ms per token, 17.01 tokens per second) 3.44.308.931 I slot print_timing: id 0 | task 176 | eval time = 204.61 ms / 2 tokens ( 204.61 ms per token, 4.89 tokens per second) 3.44.308.932 I slot print_timing: id 0 | task 176 | total time = 6671.15 ms / 112 tokens 3.44.308.932 I slot print_timing: id 0 | task 176 | graphs reused = 1 3.44.308.933 I slot print_timing: id 0 | task 176 | graph reallocs = 0 / 0 (same size) / (changed size) 3.44.308.954 I slot release: id 0 | task 176 | stop processing: n_tokens = 111, truncated = 0 3.44.309.099 I slot print_timing: id 1 | task 177 | prompt eval time = 6466.68 ms / 137 tokens ( 47.20 ms per token, 21.19 tokens per second) 3.44.309.101 I slot print_timing: id 1 | task 177 | eval time = 204.63 ms / 2 tokens ( 204.63 ms per token, 4.89 tokens per second) 3.44.309.101 I slot print_timing: id 1 | task 177 | total time = 6671.31 ms / 139 tokens 3.44.309.102 I slot print_timing: id 1 | task 177 | graphs reused = 1 3.44.309.102 I slot print_timing: id 1 | task 177 | graph reallocs = 0 / 0 (same size) / (changed size) 3.44.309.114 I slot release: id 1 | task 177 | stop processing: n_tokens = 138, truncated = 0 3.44.309.293 I slot print_timing: id 2 | task 178 | prompt eval time = 6466.84 ms / 148 tokens ( 43.69 ms per token, 22.89 tokens per second) 3.44.309.295 I slot print_timing: id 2 | task 178 | eval time = 204.65 ms / 2 tokens ( 204.65 ms per token, 4.89 tokens per second) 3.44.309.300 I slot print_timing: id 2 | task 178 | total time = 6671.49 ms / 150 tokens 3.44.309.301 I slot print_timing: id 2 | task 178 | graphs reused = 1 3.44.309.301 I slot print_timing: id 2 | task 178 | graph reallocs = 0 / 0 (same size) / (changed size) 3.44.309.309 I slot release: id 2 | task 178 | stop processing: n_tokens = 149, truncated = 0 3.44.309.471 I slot print_timing: id 3 | task 175 | prompt eval time = 6467.00 ms / 110 tokens ( 58.79 ms per token, 17.01 tokens per second) 3.44.309.473 I slot print_timing: id 3 | task 175 | eval time = 204.66 ms / 2 tokens ( 204.66 ms per token, 4.89 tokens per second) 3.44.309.473 I slot print_timing: id 3 | task 175 | total time = 6671.66 ms / 112 tokens 3.44.309.474 I slot print_timing: id 3 | task 175 | graphs reused = 1 3.44.309.474 I slot print_timing: id 3 | task 175 | graph reallocs = 0 / 0 (same size) / (changed size) 3.44.309.483 I slot release: id 3 | task 175 | stop processing: n_tokens = 111, truncated = 0 3.44.315.627 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.259 (> 0.100 thold), f_keep = 0.261 3.44.315.651 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.068 MiB) 3.44.324.250 I slot launch_slot_: id 3 | task 182 | processing task, is_child = 0 3.44.324.273 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.069 MiB) 3.44.332.071 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.943 MiB) 3.44.340.046 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.756 MiB) 3.44.348.038 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.184 (> 0.100 thold), f_keep = 0.252 3.44.348.092 I slot launch_slot_: id 0 | task 183 | processing task, is_child = 0 3.44.348.127 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.203 3.44.348.160 I slot launch_slot_: id 1 | task 185 | processing task, is_child = 0 3.44.348.179 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.215 (> 0.100 thold), f_keep = 0.188 3.44.348.212 I slot launch_slot_: id 2 | task 184 | processing task, is_child = 0 3.50.607.399 I slot print_timing: id 0 | task 183 | prompt processing, n_tokens = 148, progress = 0.97, t = 6.26 s / 23.65 tokens per second 3.50.781.139 I slot print_timing: id 1 | task 185 | prompt processing, n_tokens = 119, progress = 0.97, t = 6.26 s / 19.01 tokens per second 3.50.786.038 I slot print_timing: id 2 | task 184 | prompt processing, n_tokens = 126, progress = 0.97, t = 6.26 s / 20.13 tokens per second 3.50.791.132 I slot print_timing: id 3 | task 182 | prompt processing, n_tokens = 108, progress = 0.96, t = 6.26 s / 17.25 tokens per second 3.51.340.056 I slot print_timing: id 0 | task 183 | prompt eval time = 6786.92 ms / 152 tokens ( 44.65 ms per token, 22.40 tokens per second) 3.51.340.059 I slot print_timing: id 0 | task 183 | eval time = 204.91 ms / 2 tokens ( 204.91 ms per token, 4.88 tokens per second) 3.51.340.059 I slot print_timing: id 0 | task 183 | total time = 6991.83 ms / 154 tokens 3.51.340.060 I slot print_timing: id 0 | task 183 | graphs reused = 1 3.51.340.060 I slot print_timing: id 0 | task 183 | graph reallocs = 0 / 0 (same size) / (changed size) 3.51.340.088 I slot release: id 0 | task 183 | stop processing: n_tokens = 153, truncated = 0 3.51.340.236 I slot print_timing: id 1 | task 185 | prompt eval time = 6787.08 ms / 123 tokens ( 55.18 ms per token, 18.12 tokens per second) 3.51.340.239 I slot print_timing: id 1 | task 185 | eval time = 204.93 ms / 2 tokens ( 204.93 ms per token, 4.88 tokens per second) 3.51.340.240 I slot print_timing: id 1 | task 185 | total time = 6992.01 ms / 125 tokens 3.51.340.241 I slot print_timing: id 1 | task 185 | graphs reused = 1 3.51.340.241 I slot print_timing: id 1 | task 185 | graph reallocs = 0 / 0 (same size) / (changed size) 3.51.340.251 I slot release: id 1 | task 185 | stop processing: n_tokens = 124, truncated = 0 3.51.340.407 I slot print_timing: id 2 | task 184 | prompt eval time = 6787.23 ms / 130 tokens ( 52.21 ms per token, 19.15 tokens per second) 3.51.340.409 I slot print_timing: id 2 | task 184 | eval time = 204.93 ms / 2 tokens ( 204.93 ms per token, 4.88 tokens per second) 3.51.340.410 I slot print_timing: id 2 | task 184 | total time = 6992.16 ms / 132 tokens 3.51.340.410 I slot print_timing: id 2 | task 184 | graphs reused = 1 3.51.340.410 I slot print_timing: id 2 | task 184 | graph reallocs = 0 / 0 (same size) / (changed size) 3.51.340.427 I slot release: id 2 | task 184 | stop processing: n_tokens = 131, truncated = 0 3.51.340.608 I slot print_timing: id 3 | task 182 | prompt eval time = 6787.39 ms / 112 tokens ( 60.60 ms per token, 16.50 tokens per second) 3.51.340.610 I slot print_timing: id 3 | task 182 | eval time = 204.96 ms / 2 tokens ( 204.96 ms per token, 4.88 tokens per second) 3.51.340.611 I slot print_timing: id 3 | task 182 | total time = 6992.35 ms / 114 tokens 3.51.340.611 I slot print_timing: id 3 | task 182 | graphs reused = 1 3.51.340.611 I slot print_timing: id 3 | task 182 | graph reallocs = 0 / 0 (same size) / (changed size) 3.51.340.619 I slot release: id 3 | task 182 | stop processing: n_tokens = 113, truncated = 0 3.51.346.819 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.227 (> 0.100 thold), f_keep = 0.221 3.51.346.846 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.693 MiB) 3.51.355.235 I slot launch_slot_: id 2 | task 189 | processing task, is_child = 0 3.51.355.262 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.256 MiB) 3.51.363.171 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.443 MiB) 3.51.370.894 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.569 MiB) 3.51.381.242 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.254 (> 0.100 thold), f_keep = 0.257 3.51.381.311 I slot launch_slot_: id 3 | task 190 | processing task, is_child = 0 3.51.381.349 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.178 (> 0.100 thold), f_keep = 0.183 3.51.381.385 I slot launch_slot_: id 0 | task 191 | processing task, is_child = 0 3.51.381.406 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.169 (> 0.100 thold), f_keep = 0.226 3.51.381.447 I slot launch_slot_: id 1 | task 192 | processing task, is_child = 0 3.58.006.721 I slot print_timing: id 0 | task 191 | prompt processing, n_tokens = 153, progress = 0.97, t = 6.63 s / 23.09 tokens per second 3.58.281.411 I slot print_timing: id 1 | task 192 | prompt processing, n_tokens = 162, progress = 0.98, t = 6.63 s / 24.45 tokens per second 3.58.285.841 I slot print_timing: id 2 | task 189 | prompt processing, n_tokens = 124, progress = 0.97, t = 6.63 s / 18.72 tokens per second 3.58.290.255 I slot print_timing: id 3 | task 190 | prompt processing, n_tokens = 110, progress = 0.96, t = 6.63 s / 16.60 tokens per second 3.58.838.885 I slot print_timing: id 0 | task 191 | prompt eval time = 7252.63 ms / 157 tokens ( 46.20 ms per token, 21.65 tokens per second) 3.58.838.887 I slot print_timing: id 0 | task 191 | eval time = 204.80 ms / 2 tokens ( 204.80 ms per token, 4.88 tokens per second) 3.58.838.888 I slot print_timing: id 0 | task 191 | total time = 7457.43 ms / 159 tokens 3.58.838.888 I slot print_timing: id 0 | task 191 | graphs reused = 1 3.58.838.889 I slot print_timing: id 0 | task 191 | graph reallocs = 0 / 0 (same size) / (changed size) 3.58.838.912 I slot release: id 0 | task 191 | stop processing: n_tokens = 158, truncated = 0 3.58.839.070 I slot print_timing: id 1 | task 192 | prompt eval time = 7252.77 ms / 166 tokens ( 43.69 ms per token, 22.89 tokens per second) 3.58.839.072 I slot print_timing: id 1 | task 192 | eval time = 204.83 ms / 2 tokens ( 204.83 ms per token, 4.88 tokens per second) 3.58.839.073 I slot print_timing: id 1 | task 192 | total time = 7457.59 ms / 168 tokens 3.58.839.073 I slot print_timing: id 1 | task 192 | graphs reused = 1 3.58.839.073 I slot print_timing: id 1 | task 192 | graph reallocs = 0 / 0 (same size) / (changed size) 3.58.839.088 I slot release: id 1 | task 192 | stop processing: n_tokens = 167, truncated = 0 3.58.839.277 I slot print_timing: id 2 | task 189 | prompt eval time = 7252.93 ms / 128 tokens ( 56.66 ms per token, 17.65 tokens per second) 3.58.839.279 I slot print_timing: id 2 | task 189 | eval time = 204.86 ms / 2 tokens ( 204.86 ms per token, 4.88 tokens per second) 3.58.839.279 I slot print_timing: id 2 | task 189 | total time = 7457.79 ms / 130 tokens 3.58.839.279 I slot print_timing: id 2 | task 189 | graphs reused = 1 3.58.839.280 I slot print_timing: id 2 | task 189 | graph reallocs = 0 / 0 (same size) / (changed size) 3.58.839.294 I slot release: id 2 | task 189 | stop processing: n_tokens = 129, truncated = 0 3.58.839.478 I slot print_timing: id 3 | task 190 | prompt eval time = 7253.10 ms / 114 tokens ( 63.62 ms per token, 15.72 tokens per second) 3.58.839.481 I slot print_timing: id 3 | task 190 | eval time = 204.88 ms / 2 tokens ( 204.88 ms per token, 4.88 tokens per second) 3.58.839.481 I slot print_timing: id 3 | task 190 | total time = 7457.98 ms / 116 tokens 3.58.839.482 I slot print_timing: id 3 | task 190 | graphs reused = 1 3.58.839.482 I slot print_timing: id 3 | task 190 | graph reallocs = 0 / 0 (same size) / (changed size) 3.58.839.492 I slot release: id 3 | task 190 | stop processing: n_tokens = 115, truncated = 0 3.58.845.320 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.259 (> 0.100 thold), f_keep = 0.177 3.58.845.348 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.069 MiB) 3.58.853.423 I slot launch_slot_: id 0 | task 196 | processing task, is_child = 0 3.58.853.451 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.257 MiB) 3.58.861.349 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.505 MiB) 3.58.869.087 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.505 MiB) 3.58.877.001 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.168 3.58.877.075 I slot launch_slot_: id 1 | task 197 | processing task, is_child = 0 3.58.877.111 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.183 (> 0.100 thold), f_keep = 0.217 3.58.877.154 I slot launch_slot_: id 2 | task 198 | processing task, is_child = 0 3.58.877.173 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.156 (> 0.100 thold), f_keep = 0.243 3.58.877.205 I slot launch_slot_: id 3 | task 199 | processing task, is_child = 0 4.05.499.201 I slot print_timing: id 0 | task 196 | prompt processing, n_tokens = 104, progress = 0.96, t = 6.62 s / 15.71 tokens per second 4.05.927.859 I slot print_timing: id 1 | task 197 | prompt processing, n_tokens = 137, progress = 0.97, t = 6.62 s / 20.69 tokens per second 4.05.932.652 I slot print_timing: id 2 | task 198 | prompt processing, n_tokens = 149, progress = 0.97, t = 6.62 s / 22.50 tokens per second 4.05.937.114 I slot print_timing: id 3 | task 199 | prompt processing, n_tokens = 175, progress = 0.98, t = 6.62 s / 26.43 tokens per second 4.06.485.957 I slot print_timing: id 0 | task 196 | prompt eval time = 7404.15 ms / 108 tokens ( 68.56 ms per token, 14.59 tokens per second) 4.06.485.962 I slot print_timing: id 0 | task 196 | eval time = 204.59 ms / 2 tokens ( 204.59 ms per token, 4.89 tokens per second) 4.06.485.962 I slot print_timing: id 0 | task 196 | total time = 7608.74 ms / 110 tokens 4.06.485.963 I slot print_timing: id 0 | task 196 | graphs reused = 1 4.06.485.963 I slot print_timing: id 0 | task 196 | graph reallocs = 0 / 0 (same size) / (changed size) 4.06.485.981 I slot release: id 0 | task 196 | stop processing: n_tokens = 109, truncated = 0 4.06.486.130 I slot print_timing: id 1 | task 197 | prompt eval time = 7404.28 ms / 141 tokens ( 52.51 ms per token, 19.04 tokens per second) 4.06.486.132 I slot print_timing: id 1 | task 197 | eval time = 204.61 ms / 2 tokens ( 204.61 ms per token, 4.89 tokens per second) 4.06.486.132 I slot print_timing: id 1 | task 197 | total time = 7608.90 ms / 143 tokens 4.06.486.133 I slot print_timing: id 1 | task 197 | graphs reused = 1 4.06.486.133 I slot print_timing: id 1 | task 197 | graph reallocs = 0 / 0 (same size) / (changed size) 4.06.486.144 I slot release: id 1 | task 197 | stop processing: n_tokens = 142, truncated = 0 4.06.486.310 I slot print_timing: id 2 | task 198 | prompt eval time = 7404.43 ms / 153 tokens ( 48.39 ms per token, 20.66 tokens per second) 4.06.486.312 I slot print_timing: id 2 | task 198 | eval time = 204.64 ms / 2 tokens ( 204.64 ms per token, 4.89 tokens per second) 4.06.486.313 I slot print_timing: id 2 | task 198 | total time = 7609.07 ms / 155 tokens 4.06.486.313 I slot print_timing: id 2 | task 198 | graphs reused = 1 4.06.486.314 I slot print_timing: id 2 | task 198 | graph reallocs = 0 / 0 (same size) / (changed size) 4.06.486.324 I slot release: id 2 | task 198 | stop processing: n_tokens = 154, truncated = 0 4.06.486.511 I slot print_timing: id 3 | task 199 | prompt eval time = 7404.59 ms / 179 tokens ( 41.37 ms per token, 24.17 tokens per second) 4.06.486.513 I slot print_timing: id 3 | task 199 | eval time = 204.66 ms / 2 tokens ( 204.66 ms per token, 4.89 tokens per second) 4.06.486.514 I slot print_timing: id 3 | task 199 | total time = 7609.25 ms / 181 tokens 4.06.486.514 I slot print_timing: id 3 | task 199 | graphs reused = 1 4.06.486.514 I slot print_timing: id 3 | task 199 | graph reallocs = 0 / 0 (same size) / (changed size) 4.06.486.530 I slot release: id 3 | task 199 | stop processing: n_tokens = 180, truncated = 0 4.06.492.518 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.209 (> 0.100 thold), f_keep = 0.257 4.06.492.544 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.005 MiB) 4.06.500.731 I slot launch_slot_: id 0 | task 203 | processing task, is_child = 0 4.06.500.755 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.005 MiB) 4.06.508.499 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.256 MiB) 4.06.516.406 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.318 MiB) 4.06.524.257 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.241 (> 0.100 thold), f_keep = 0.197 4.06.527.626 I slot launch_slot_: id 1 | task 204 | processing task, is_child = 0 4.06.527.685 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.207 (> 0.100 thold), f_keep = 0.182 4.06.527.720 I slot launch_slot_: id 2 | task 205 | processing task, is_child = 0 4.06.527.741 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.177 (> 0.100 thold), f_keep = 0.156 4.06.527.780 I slot launch_slot_: id 3 | task 206 | processing task, is_child = 0 4.12.734.621 I slot print_timing: id 0 | task 203 | prompt processing, n_tokens = 130, progress = 0.97, t = 6.21 s / 20.94 tokens per second 4.13.160.340 I slot print_timing: id 1 | task 204 | prompt processing, n_tokens = 112, progress = 0.97, t = 6.21 s / 18.04 tokens per second 4.13.164.761 I slot print_timing: id 2 | task 205 | prompt processing, n_tokens = 131, progress = 0.97, t = 6.21 s / 21.11 tokens per second 4.13.169.188 I slot print_timing: id 3 | task 206 | prompt processing, n_tokens = 154, progress = 0.97, t = 6.21 s / 24.81 tokens per second 4.13.717.939 I slot print_timing: id 0 | task 203 | prompt eval time = 6985.57 ms / 134 tokens ( 52.13 ms per token, 19.18 tokens per second) 4.13.717.944 I slot print_timing: id 0 | task 203 | eval time = 204.58 ms / 2 tokens ( 204.58 ms per token, 4.89 tokens per second) 4.13.717.945 I slot print_timing: id 0 | task 203 | total time = 7190.15 ms / 136 tokens 4.13.717.945 I slot print_timing: id 0 | task 203 | graphs reused = 1 4.13.717.946 I slot print_timing: id 0 | task 203 | graph reallocs = 0 / 0 (same size) / (changed size) 4.13.717.966 I slot release: id 0 | task 203 | stop processing: n_tokens = 135, truncated = 0 4.13.718.115 I slot print_timing: id 1 | task 204 | prompt eval time = 6985.72 ms / 116 tokens ( 60.22 ms per token, 16.61 tokens per second) 4.13.718.122 I slot print_timing: id 1 | task 204 | eval time = 204.59 ms / 2 tokens ( 204.59 ms per token, 4.89 tokens per second) 4.13.718.122 I slot print_timing: id 1 | task 204 | total time = 7190.31 ms / 118 tokens 4.13.718.123 I slot print_timing: id 1 | task 204 | graphs reused = 1 4.13.718.123 I slot print_timing: id 1 | task 204 | graph reallocs = 0 / 0 (same size) / (changed size) 4.13.718.133 I slot release: id 1 | task 204 | stop processing: n_tokens = 117, truncated = 0 4.13.718.303 I slot print_timing: id 2 | task 205 | prompt eval time = 6985.87 ms / 135 tokens ( 51.75 ms per token, 19.32 tokens per second) 4.13.718.305 I slot print_timing: id 2 | task 205 | eval time = 204.62 ms / 2 tokens ( 204.62 ms per token, 4.89 tokens per second) 4.13.718.306 I slot print_timing: id 2 | task 205 | total time = 7190.49 ms / 137 tokens 4.13.718.306 I slot print_timing: id 2 | task 205 | graphs reused = 1 4.13.718.306 I slot print_timing: id 2 | task 205 | graph reallocs = 0 / 0 (same size) / (changed size) 4.13.718.317 I slot release: id 2 | task 205 | stop processing: n_tokens = 136, truncated = 0 4.13.718.481 I slot print_timing: id 3 | task 206 | prompt eval time = 6986.03 ms / 158 tokens ( 44.22 ms per token, 22.62 tokens per second) 4.13.718.483 I slot print_timing: id 3 | task 206 | eval time = 204.62 ms / 2 tokens ( 204.62 ms per token, 4.89 tokens per second) 4.13.718.483 I slot print_timing: id 3 | task 206 | total time = 7190.65 ms / 160 tokens 4.13.718.483 I slot print_timing: id 3 | task 206 | graphs reused = 1 4.13.718.483 I slot print_timing: id 3 | task 206 | graph reallocs = 0 / 0 (same size) / (changed size) 4.13.718.493 I slot release: id 3 | task 206 | stop processing: n_tokens = 159, truncated = 0 4.13.723.640 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.238 (> 0.100 thold), f_keep = 0.248 4.13.732.438 I slot launch_slot_: id 1 | task 210 | processing task, is_child = 0 4.13.732.459 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.443 MiB) 4.13.740.745 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.131 MiB) 4.13.748.903 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.381 MiB) 4.13.757.153 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.239 (> 0.100 thold), f_keep = 0.207 4.13.760.515 I slot launch_slot_: id 0 | task 211 | processing task, is_child = 0 4.13.760.559 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.206 4.13.760.595 I slot launch_slot_: id 2 | task 212 | processing task, is_child = 0 4.13.760.632 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.178 (> 0.100 thold), f_keep = 0.176 4.13.760.665 I slot launch_slot_: id 3 | task 213 | processing task, is_child = 0 4.20.240.393 I slot print_timing: id 0 | task 211 | prompt processing, n_tokens = 113, progress = 0.97, t = 6.48 s / 17.44 tokens per second 4.20.416.005 I slot print_timing: id 1 | task 210 | prompt processing, n_tokens = 118, progress = 0.97, t = 6.48 s / 18.21 tokens per second 4.20.420.984 I slot print_timing: id 2 | task 212 | prompt processing, n_tokens = 145, progress = 0.97, t = 6.48 s / 22.38 tokens per second 4.20.425.852 I slot print_timing: id 3 | task 213 | prompt processing, n_tokens = 153, progress = 0.97, t = 6.48 s / 23.61 tokens per second 4.20.974.261 I slot print_timing: id 0 | task 211 | prompt eval time = 7009.02 ms / 117 tokens ( 59.91 ms per token, 16.69 tokens per second) 4.20.974.267 I slot print_timing: id 0 | task 211 | eval time = 204.56 ms / 2 tokens ( 204.56 ms per token, 4.89 tokens per second) 4.20.974.267 I slot print_timing: id 0 | task 211 | total time = 7213.58 ms / 119 tokens 4.20.974.268 I slot print_timing: id 0 | task 211 | graphs reused = 1 4.20.974.268 I slot print_timing: id 0 | task 211 | graph reallocs = 0 / 0 (same size) / (changed size) 4.20.974.291 I slot release: id 0 | task 211 | stop processing: n_tokens = 118, truncated = 0 4.20.974.443 I slot print_timing: id 1 | task 210 | prompt eval time = 7009.18 ms / 122 tokens ( 57.45 ms per token, 17.41 tokens per second) 4.20.974.445 I slot print_timing: id 1 | task 210 | eval time = 204.58 ms / 2 tokens ( 204.58 ms per token, 4.89 tokens per second) 4.20.974.445 I slot print_timing: id 1 | task 210 | total time = 7213.76 ms / 124 tokens 4.20.974.446 I slot print_timing: id 1 | task 210 | graphs reused = 1 4.20.974.446 I slot print_timing: id 1 | task 210 | graph reallocs = 0 / 0 (same size) / (changed size) 4.20.974.458 I slot release: id 1 | task 210 | stop processing: n_tokens = 123, truncated = 0 4.20.974.611 I slot print_timing: id 2 | task 212 | prompt eval time = 7009.33 ms / 149 tokens ( 47.04 ms per token, 21.26 tokens per second) 4.20.974.612 I slot print_timing: id 2 | task 212 | eval time = 204.58 ms / 2 tokens ( 204.58 ms per token, 4.89 tokens per second) 4.20.974.613 I slot print_timing: id 2 | task 212 | total time = 7213.92 ms / 151 tokens 4.20.974.613 I slot print_timing: id 2 | task 212 | graphs reused = 1 4.20.974.613 I slot print_timing: id 2 | task 212 | graph reallocs = 0 / 0 (same size) / (changed size) 4.20.974.629 I slot release: id 2 | task 212 | stop processing: n_tokens = 150, truncated = 0 4.20.974.796 I slot print_timing: id 3 | task 213 | prompt eval time = 7009.48 ms / 157 tokens ( 44.65 ms per token, 22.40 tokens per second) 4.20.974.799 I slot print_timing: id 3 | task 213 | eval time = 204.60 ms / 2 tokens ( 204.60 ms per token, 4.89 tokens per second) 4.20.974.799 I slot print_timing: id 3 | task 213 | total time = 7214.09 ms / 159 tokens 4.20.974.799 I slot print_timing: id 3 | task 213 | graphs reused = 1 4.20.974.799 I slot print_timing: id 3 | task 213 | graph reallocs = 0 / 0 (same size) / (changed size) 4.20.974.810 I slot release: id 3 | task 213 | stop processing: n_tokens = 158, truncated = 0 4.20.980.957 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.237 4.20.989.537 I slot launch_slot_: id 0 | task 217 | processing task, is_child = 0 4.20.989.558 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.005 MiB) 4.20.997.383 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.381 MiB) 4.21.005.297 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.131 MiB) 4.21.013.219 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.228 4.21.013.279 I slot launch_slot_: id 1 | task 218 | processing task, is_child = 0 4.21.013.320 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.181 (> 0.100 thold), f_keep = 0.187 4.21.013.354 I slot launch_slot_: id 2 | task 219 | processing task, is_child = 0 4.21.013.373 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.182 (> 0.100 thold), f_keep = 0.177 4.21.013.406 I slot launch_slot_: id 3 | task 220 | processing task, is_child = 0 4.28.335.176 I slot print_timing: id 0 | task 217 | prompt processing, n_tokens = 145, progress = 0.97, t = 7.32 s / 19.80 tokens per second 4.28.504.418 I slot print_timing: id 1 | task 218 | prompt processing, n_tokens = 156, progress = 0.97, t = 7.32 s / 21.31 tokens per second 4.28.509.160 I slot print_timing: id 2 | task 219 | prompt processing, n_tokens = 151, progress = 0.97, t = 7.32 s / 20.62 tokens per second 4.28.514.000 I slot print_timing: id 3 | task 220 | prompt processing, n_tokens = 150, progress = 0.97, t = 7.32 s / 20.49 tokens per second 4.29.063.240 I slot print_timing: id 0 | task 217 | prompt eval time = 7845.06 ms / 149 tokens ( 52.65 ms per token, 18.99 tokens per second) 4.29.063.243 I slot print_timing: id 0 | task 217 | eval time = 204.76 ms / 2 tokens ( 204.76 ms per token, 4.88 tokens per second) 4.29.063.244 I slot print_timing: id 0 | task 217 | total time = 8049.82 ms / 151 tokens 4.29.063.244 I slot print_timing: id 0 | task 217 | graphs reused = 1 4.29.063.245 I slot print_timing: id 0 | task 217 | graph reallocs = 0 / 0 (same size) / (changed size) 4.29.063.266 I slot release: id 0 | task 217 | stop processing: n_tokens = 150, truncated = 0 4.29.063.423 I slot print_timing: id 1 | task 218 | prompt eval time = 7845.22 ms / 160 tokens ( 49.03 ms per token, 20.39 tokens per second) 4.29.063.426 I slot print_timing: id 1 | task 218 | eval time = 204.78 ms / 2 tokens ( 204.78 ms per token, 4.88 tokens per second) 4.29.063.427 I slot print_timing: id 1 | task 218 | total time = 8050.00 ms / 162 tokens 4.29.063.427 I slot print_timing: id 1 | task 218 | graphs reused = 1 4.29.063.427 I slot print_timing: id 1 | task 218 | graph reallocs = 0 / 0 (same size) / (changed size) 4.29.063.439 I slot release: id 1 | task 218 | stop processing: n_tokens = 161, truncated = 0 4.29.063.605 I slot print_timing: id 2 | task 219 | prompt eval time = 7845.37 ms / 155 tokens ( 50.62 ms per token, 19.76 tokens per second) 4.29.063.611 I slot print_timing: id 2 | task 219 | eval time = 204.80 ms / 2 tokens ( 204.80 ms per token, 4.88 tokens per second) 4.29.063.611 I slot print_timing: id 2 | task 219 | total time = 8050.17 ms / 157 tokens 4.29.063.612 I slot print_timing: id 2 | task 219 | graphs reused = 1 4.29.063.612 I slot print_timing: id 2 | task 219 | graph reallocs = 0 / 0 (same size) / (changed size) 4.29.063.623 I slot release: id 2 | task 219 | stop processing: n_tokens = 156, truncated = 0 4.29.063.801 I slot print_timing: id 3 | task 220 | prompt eval time = 7845.54 ms / 154 tokens ( 50.95 ms per token, 19.63 tokens per second) 4.29.063.803 I slot print_timing: id 3 | task 220 | eval time = 204.81 ms / 2 tokens ( 204.81 ms per token, 4.88 tokens per second) 4.29.063.803 I slot print_timing: id 3 | task 220 | total time = 8050.35 ms / 156 tokens 4.29.063.803 I slot print_timing: id 3 | task 220 | graphs reused = 1 4.29.063.804 I slot print_timing: id 3 | task 220 | graph reallocs = 0 / 0 (same size) / (changed size) 4.29.063.816 I slot release: id 3 | task 220 | stop processing: n_tokens = 155, truncated = 0 4.29.069.731 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.275 (> 0.100 thold), f_keep = 0.187 4.29.069.757 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.944 MiB) 4.29.081.430 I slot launch_slot_: id 0 | task 225 | processing task, is_child = 0 4.29.089.381 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.569 MiB) 4.29.097.265 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.193 MiB) 4.29.105.432 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.262 (> 0.100 thold), f_keep = 0.174 4.29.105.496 I slot launch_slot_: id 1 | task 224 | processing task, is_child = 0 4.29.105.532 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.246 (> 0.100 thold), f_keep = 0.179 4.29.105.570 I slot launch_slot_: id 2 | task 226 | processing task, is_child = 0 4.29.105.594 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.151 (> 0.100 thold), f_keep = 0.181 4.29.105.626 I slot launch_slot_: id 3 | task 227 | processing task, is_child = 0 4.34.426.280 I slot print_timing: id 0 | task 225 | prompt processing, n_tokens = 98, progress = 0.96, t = 5.32 s / 18.42 tokens per second 4.35.555.553 I slot print_timing: id 1 | task 224 | prompt processing, n_tokens = 103, progress = 0.96, t = 5.32 s / 19.36 tokens per second 4.35.560.310 I slot print_timing: id 2 | task 226 | prompt processing, n_tokens = 110, progress = 0.96, t = 5.32 s / 20.67 tokens per second 4.35.565.163 I slot print_timing: id 3 | task 227 | prompt processing, n_tokens = 181, progress = 0.98, t = 5.32 s / 34.02 tokens per second 4.36.114.415 I slot print_timing: id 0 | task 225 | prompt eval time = 6804.13 ms / 102 tokens ( 66.71 ms per token, 14.99 tokens per second) 4.36.114.420 I slot print_timing: id 0 | task 225 | eval time = 204.65 ms / 2 tokens ( 204.65 ms per token, 4.89 tokens per second) 4.36.114.421 I slot print_timing: id 0 | task 225 | total time = 7008.78 ms / 104 tokens 4.36.114.422 I slot print_timing: id 0 | task 225 | graphs reused = 1 4.36.114.422 I slot print_timing: id 0 | task 225 | graph reallocs = 0 / 0 (same size) / (changed size) 4.36.114.447 I slot release: id 0 | task 225 | stop processing: n_tokens = 103, truncated = 0 4.36.114.601 I slot print_timing: id 1 | task 224 | prompt eval time = 6804.28 ms / 107 tokens ( 63.59 ms per token, 15.73 tokens per second) 4.36.114.604 I slot print_timing: id 1 | task 224 | eval time = 204.68 ms / 2 tokens ( 204.68 ms per token, 4.89 tokens per second) 4.36.114.605 I slot print_timing: id 1 | task 224 | total time = 7008.96 ms / 109 tokens 4.36.114.605 I slot print_timing: id 1 | task 224 | graphs reused = 1 4.36.114.606 I slot print_timing: id 1 | task 224 | graph reallocs = 0 / 0 (same size) / (changed size) 4.36.114.619 I slot release: id 1 | task 224 | stop processing: n_tokens = 108, truncated = 0 4.36.114.799 I slot print_timing: id 2 | task 226 | prompt eval time = 6804.43 ms / 114 tokens ( 59.69 ms per token, 16.75 tokens per second) 4.36.114.801 I slot print_timing: id 2 | task 226 | eval time = 204.71 ms / 2 tokens ( 204.71 ms per token, 4.89 tokens per second) 4.36.114.801 I slot print_timing: id 2 | task 226 | total time = 7009.14 ms / 116 tokens 4.36.114.802 I slot print_timing: id 2 | task 226 | graphs reused = 1 4.36.114.802 I slot print_timing: id 2 | task 226 | graph reallocs = 0 / 0 (same size) / (changed size) 4.36.114.814 I slot release: id 2 | task 226 | stop processing: n_tokens = 115, truncated = 0 4.36.114.986 I slot print_timing: id 3 | task 227 | prompt eval time = 6804.58 ms / 185 tokens ( 36.78 ms per token, 27.19 tokens per second) 4.36.114.988 I slot print_timing: id 3 | task 227 | eval time = 204.73 ms / 2 tokens ( 204.73 ms per token, 4.88 tokens per second) 4.36.114.988 I slot print_timing: id 3 | task 227 | total time = 7009.31 ms / 187 tokens 4.36.114.989 I slot print_timing: id 3 | task 227 | graphs reused = 1 4.36.114.989 I slot print_timing: id 3 | task 227 | graph reallocs = 0 / 0 (same size) / (changed size) 4.36.114.999 I slot release: id 3 | task 227 | stop processing: n_tokens = 186, truncated = 0 4.36.120.489 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.264 (> 0.100 thold), f_keep = 0.282 4.36.120.513 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.193 MiB) 4.36.128.985 I slot launch_slot_: id 0 | task 231 | processing task, is_child = 0 4.36.129.006 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.881 MiB) 4.36.136.885 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.569 MiB) 4.36.144.777 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.443 MiB) 4.36.160.856 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.259 4.36.160.927 I slot launch_slot_: id 1 | task 232 | processing task, is_child = 0 4.36.160.968 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.222 (> 0.100 thold), f_keep = 0.243 4.36.161.001 I slot launch_slot_: id 2 | task 233 | processing task, is_child = 0 4.36.161.020 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.171 (> 0.100 thold), f_keep = 0.151 4.36.161.053 I slot launch_slot_: id 3 | task 234 | processing task, is_child = 0 4.42.175.042 I slot print_timing: id 0 | task 231 | prompt processing, n_tokens = 106, progress = 0.96, t = 6.01 s / 17.63 tokens per second 4.42.934.456 I slot print_timing: id 1 | task 232 | prompt processing, n_tokens = 118, progress = 0.97, t = 6.01 s / 19.62 tokens per second 4.42.939.039 I slot print_timing: id 2 | task 233 | prompt processing, n_tokens = 122, progress = 0.97, t = 6.01 s / 20.29 tokens per second 4.42.943.829 I slot print_timing: id 3 | task 234 | prompt processing, n_tokens = 160, progress = 0.98, t = 6.01 s / 26.60 tokens per second 4.43.493.014 I slot print_timing: id 0 | task 231 | prompt eval time = 7127.36 ms / 110 tokens ( 64.79 ms per token, 15.43 tokens per second) 4.43.493.019 I slot print_timing: id 0 | task 231 | eval time = 204.59 ms / 2 tokens ( 204.59 ms per token, 4.89 tokens per second) 4.43.493.019 I slot print_timing: id 0 | task 231 | total time = 7331.95 ms / 112 tokens 4.43.493.020 I slot print_timing: id 0 | task 231 | graphs reused = 1 4.43.493.020 I slot print_timing: id 0 | task 231 | graph reallocs = 0 / 0 (same size) / (changed size) 4.43.493.042 I slot release: id 0 | task 231 | stop processing: n_tokens = 111, truncated = 0 4.43.493.191 I slot print_timing: id 1 | task 232 | prompt eval time = 7127.51 ms / 122 tokens ( 58.42 ms per token, 17.12 tokens per second) 4.43.493.194 I slot print_timing: id 1 | task 232 | eval time = 204.61 ms / 2 tokens ( 204.61 ms per token, 4.89 tokens per second) 4.43.493.195 I slot print_timing: id 1 | task 232 | total time = 7332.12 ms / 124 tokens 4.43.493.195 I slot print_timing: id 1 | task 232 | graphs reused = 1 4.43.493.195 I slot print_timing: id 1 | task 232 | graph reallocs = 0 / 0 (same size) / (changed size) 4.43.493.214 I slot release: id 1 | task 232 | stop processing: n_tokens = 123, truncated = 0 4.43.493.381 I slot print_timing: id 2 | task 233 | prompt eval time = 7127.66 ms / 126 tokens ( 56.57 ms per token, 17.68 tokens per second) 4.43.493.382 I slot print_timing: id 2 | task 233 | eval time = 204.64 ms / 2 tokens ( 204.64 ms per token, 4.89 tokens per second) 4.43.493.383 I slot print_timing: id 2 | task 233 | total time = 7332.30 ms / 128 tokens 4.43.493.383 I slot print_timing: id 2 | task 233 | graphs reused = 1 4.43.493.384 I slot print_timing: id 2 | task 233 | graph reallocs = 0 / 0 (same size) / (changed size) 4.43.493.397 I slot release: id 2 | task 233 | stop processing: n_tokens = 127, truncated = 0 4.43.493.563 I slot print_timing: id 3 | task 234 | prompt eval time = 7127.82 ms / 164 tokens ( 43.46 ms per token, 23.01 tokens per second) 4.43.493.566 I slot print_timing: id 3 | task 234 | eval time = 204.65 ms / 2 tokens ( 204.65 ms per token, 4.89 tokens per second) 4.43.493.566 I slot print_timing: id 3 | task 234 | total time = 7332.47 ms / 166 tokens 4.43.493.566 I slot print_timing: id 3 | task 234 | graphs reused = 1 4.43.493.567 I slot print_timing: id 3 | task 234 | graph reallocs = 0 / 0 (same size) / (changed size) 4.43.493.576 I slot release: id 3 | task 234 | stop processing: n_tokens = 165, truncated = 0 4.43.499.273 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.224 (> 0.100 thold), f_keep = 0.252 4.43.499.296 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.819 MiB) 4.43.507.964 I slot launch_slot_: id 0 | task 239 | processing task, is_child = 0 4.43.507.991 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.005 MiB) 4.43.516.133 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.318 MiB) 4.43.524.204 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.131 MiB) 4.43.532.470 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.228 4.43.532.528 I slot launch_slot_: id 1 | task 238 | processing task, is_child = 0 4.43.532.564 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.204 (> 0.100 thold), f_keep = 0.220 4.43.535.914 I slot launch_slot_: id 2 | task 240 | processing task, is_child = 0 4.43.535.936 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.203 (> 0.100 thold), f_keep = 0.170 4.43.539.224 I slot launch_slot_: id 3 | task 241 | processing task, is_child = 0 4.49.565.676 I slot print_timing: id 0 | task 239 | prompt processing, n_tokens = 121, progress = 0.97, t = 6.03 s / 20.08 tokens per second 4.49.660.704 I slot print_timing: id 1 | task 238 | prompt processing, n_tokens = 118, progress = 0.97, t = 6.03 s / 19.58 tokens per second 4.49.665.393 I slot print_timing: id 2 | task 240 | prompt processing, n_tokens = 133, progress = 0.97, t = 6.03 s / 22.07 tokens per second 4.49.670.337 I slot print_timing: id 3 | task 241 | prompt processing, n_tokens = 134, progress = 0.97, t = 6.03 s / 22.24 tokens per second 4.50.219.358 I slot print_timing: id 0 | task 239 | prompt eval time = 6475.59 ms / 125 tokens ( 51.80 ms per token, 19.30 tokens per second) 4.50.219.360 I slot print_timing: id 0 | task 239 | eval time = 204.53 ms / 2 tokens ( 204.53 ms per token, 4.89 tokens per second) 4.50.219.360 I slot print_timing: id 0 | task 239 | total time = 6680.12 ms / 127 tokens 4.50.219.361 I slot print_timing: id 0 | task 239 | graphs reused = 1 4.50.219.361 I slot print_timing: id 0 | task 239 | graph reallocs = 0 / 0 (same size) / (changed size) 4.50.219.383 I slot release: id 0 | task 239 | stop processing: n_tokens = 126, truncated = 0 4.50.219.530 I slot print_timing: id 1 | task 238 | prompt eval time = 6475.73 ms / 122 tokens ( 53.08 ms per token, 18.84 tokens per second) 4.50.219.535 I slot print_timing: id 1 | task 238 | eval time = 204.55 ms / 2 tokens ( 204.55 ms per token, 4.89 tokens per second) 4.50.219.535 I slot print_timing: id 1 | task 238 | total time = 6680.28 ms / 124 tokens 4.50.219.536 I slot print_timing: id 1 | task 238 | graphs reused = 1 4.50.219.536 I slot print_timing: id 1 | task 238 | graph reallocs = 0 / 0 (same size) / (changed size) 4.50.219.547 I slot release: id 1 | task 238 | stop processing: n_tokens = 123, truncated = 0 4.50.219.715 I slot print_timing: id 2 | task 240 | prompt eval time = 6475.88 ms / 137 tokens ( 47.27 ms per token, 21.16 tokens per second) 4.50.219.718 I slot print_timing: id 2 | task 240 | eval time = 204.57 ms / 2 tokens ( 204.57 ms per token, 4.89 tokens per second) 4.50.219.718 I slot print_timing: id 2 | task 240 | total time = 6680.46 ms / 139 tokens 4.50.219.718 I slot print_timing: id 2 | task 240 | graphs reused = 1 4.50.219.719 I slot print_timing: id 2 | task 240 | graph reallocs = 0 / 0 (same size) / (changed size) 4.50.219.731 I slot release: id 2 | task 240 | stop processing: n_tokens = 138, truncated = 0 4.50.219.905 I slot print_timing: id 3 | task 241 | prompt eval time = 6476.03 ms / 138 tokens ( 46.93 ms per token, 21.31 tokens per second) 4.50.219.907 I slot print_timing: id 3 | task 241 | eval time = 204.60 ms / 2 tokens ( 204.60 ms per token, 4.89 tokens per second) 4.50.219.907 I slot print_timing: id 3 | task 241 | total time = 6680.64 ms / 140 tokens 4.50.219.907 I slot print_timing: id 3 | task 241 | graphs reused = 1 4.50.219.908 I slot print_timing: id 3 | task 241 | graph reallocs = 0 / 0 (same size) / (changed size) 4.50.219.916 I slot release: id 3 | task 241 | stop processing: n_tokens = 139, truncated = 0 4.50.226.090 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.233 (> 0.100 thold), f_keep = 0.222 4.50.234.590 I slot launch_slot_: id 0 | task 245 | processing task, is_child = 0 4.50.242.637 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.694 MiB) 4.50.250.633 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.318 MiB) 4.50.258.732 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.177 (> 0.100 thold), f_keep = 0.228 4.50.262.083 I slot launch_slot_: id 1 | task 246 | processing task, is_child = 0 4.50.262.126 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.200 (> 0.100 thold), f_keep = 0.203 4.50.262.161 I slot launch_slot_: id 2 | task 247 | processing task, is_child = 0 4.50.262.183 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.167 (> 0.100 thold), f_keep = 0.201 4.50.262.215 I slot launch_slot_: id 3 | task 248 | processing task, is_child = 0 4.56.900.968 I slot print_timing: id 0 | task 245 | prompt processing, n_tokens = 116, progress = 0.97, t = 6.64 s / 17.47 tokens per second 4.57.332.254 I slot print_timing: id 1 | task 246 | prompt processing, n_tokens = 154, progress = 0.97, t = 6.64 s / 23.20 tokens per second 4.57.337.225 I slot print_timing: id 2 | task 247 | prompt processing, n_tokens = 136, progress = 0.97, t = 6.64 s / 20.49 tokens per second 4.57.341.959 I slot print_timing: id 3 | task 248 | prompt processing, n_tokens = 164, progress = 0.98, t = 6.64 s / 24.70 tokens per second 4.57.891.275 I slot print_timing: id 0 | task 245 | prompt eval time = 7424.40 ms / 120 tokens ( 61.87 ms per token, 16.16 tokens per second) 4.57.891.278 I slot print_timing: id 0 | task 245 | eval time = 204.65 ms / 2 tokens ( 204.65 ms per token, 4.89 tokens per second) 4.57.891.278 I slot print_timing: id 0 | task 245 | total time = 7629.05 ms / 122 tokens 4.57.891.279 I slot print_timing: id 0 | task 245 | graphs reused = 1 4.57.891.279 I slot print_timing: id 0 | task 245 | graph reallocs = 0 / 0 (same size) / (changed size) 4.57.891.297 I slot release: id 0 | task 245 | stop processing: n_tokens = 121, truncated = 0 4.57.891.447 I slot print_timing: id 1 | task 246 | prompt eval time = 7424.54 ms / 158 tokens ( 46.99 ms per token, 21.28 tokens per second) 4.57.891.451 I slot print_timing: id 1 | task 246 | eval time = 204.68 ms / 2 tokens ( 204.68 ms per token, 4.89 tokens per second) 4.57.891.452 I slot print_timing: id 1 | task 246 | total time = 7629.21 ms / 160 tokens 4.57.891.452 I slot print_timing: id 1 | task 246 | graphs reused = 1 4.57.891.452 I slot print_timing: id 1 | task 246 | graph reallocs = 0 / 0 (same size) / (changed size) 4.57.891.465 I slot release: id 1 | task 246 | stop processing: n_tokens = 159, truncated = 0 4.57.891.637 I slot print_timing: id 2 | task 247 | prompt eval time = 7424.70 ms / 140 tokens ( 53.03 ms per token, 18.86 tokens per second) 4.57.891.639 I slot print_timing: id 2 | task 247 | eval time = 204.69 ms / 2 tokens ( 204.69 ms per token, 4.89 tokens per second) 4.57.891.639 I slot print_timing: id 2 | task 247 | total time = 7629.39 ms / 142 tokens 4.57.891.639 I slot print_timing: id 2 | task 247 | graphs reused = 1 4.57.891.640 I slot print_timing: id 2 | task 247 | graph reallocs = 0 / 0 (same size) / (changed size) 4.57.891.651 I slot release: id 2 | task 247 | stop processing: n_tokens = 141, truncated = 0 4.57.891.816 I slot print_timing: id 3 | task 248 | prompt eval time = 7424.87 ms / 168 tokens ( 44.20 ms per token, 22.63 tokens per second) 4.57.891.818 I slot print_timing: id 3 | task 248 | eval time = 204.69 ms / 2 tokens ( 204.69 ms per token, 4.89 tokens per second) 4.57.891.819 I slot print_timing: id 3 | task 248 | total time = 7629.56 ms / 170 tokens 4.57.891.819 I slot print_timing: id 3 | task 248 | graphs reused = 1 4.57.891.819 I slot print_timing: id 3 | task 248 | graph reallocs = 0 / 0 (same size) / (changed size) 4.57.891.827 I slot release: id 3 | task 248 | stop processing: n_tokens = 169, truncated = 0 4.57.898.123 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.272 (> 0.100 thold), f_keep = 0.231 4.57.906.407 I slot launch_slot_: id 0 | task 252 | processing task, is_child = 0 4.57.906.429 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.068 MiB) 4.57.914.367 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.131 MiB) 4.57.922.296 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.881 MiB) 4.57.930.326 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.211 (> 0.100 thold), f_keep = 0.176 4.57.933.700 I slot launch_slot_: id 1 | task 253 | processing task, is_child = 0 4.57.933.740 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.154 (> 0.100 thold), f_keep = 0.199 4.57.933.771 I slot launch_slot_: id 2 | task 254 | processing task, is_child = 0 4.57.933.788 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.181 (> 0.100 thold), f_keep = 0.166 4.57.933.819 I slot launch_slot_: id 3 | task 255 | processing task, is_child = 0 5.04.577.718 I slot print_timing: id 0 | task 252 | prompt processing, n_tokens = 99, progress = 0.96, t = 6.64 s / 14.90 tokens per second 5.05.007.651 I slot print_timing: id 1 | task 253 | prompt processing, n_tokens = 129, progress = 0.97, t = 6.64 s / 19.42 tokens per second 5.05.012.647 I slot print_timing: id 2 | task 254 | prompt processing, n_tokens = 178, progress = 0.98, t = 6.64 s / 26.79 tokens per second 5.05.017.506 I slot print_timing: id 3 | task 255 | prompt processing, n_tokens = 151, progress = 0.97, t = 6.64 s / 22.73 tokens per second 5.05.566.837 I slot print_timing: id 0 | task 252 | prompt eval time = 7428.43 ms / 103 tokens ( 72.12 ms per token, 13.87 tokens per second) 5.05.566.839 I slot print_timing: id 0 | task 252 | eval time = 204.58 ms / 2 tokens ( 204.58 ms per token, 4.89 tokens per second) 5.05.566.839 I slot print_timing: id 0 | task 252 | total time = 7633.01 ms / 105 tokens 5.05.566.840 I slot print_timing: id 0 | task 252 | graphs reused = 1 5.05.566.840 I slot print_timing: id 0 | task 252 | graph reallocs = 0 / 0 (same size) / (changed size) 5.05.566.862 I slot release: id 0 | task 252 | stop processing: n_tokens = 104, truncated = 0 5.05.567.005 I slot print_timing: id 1 | task 253 | prompt eval time = 7428.57 ms / 133 tokens ( 55.85 ms per token, 17.90 tokens per second) 5.05.567.008 I slot print_timing: id 1 | task 253 | eval time = 204.60 ms / 2 tokens ( 204.60 ms per token, 4.89 tokens per second) 5.05.567.008 I slot print_timing: id 1 | task 253 | total time = 7633.17 ms / 135 tokens 5.05.567.008 I slot print_timing: id 1 | task 253 | graphs reused = 1 5.05.567.009 I slot print_timing: id 1 | task 253 | graph reallocs = 0 / 0 (same size) / (changed size) 5.05.567.020 I slot release: id 1 | task 253 | stop processing: n_tokens = 134, truncated = 0 5.05.567.196 I slot print_timing: id 2 | task 254 | prompt eval time = 7428.72 ms / 182 tokens ( 40.82 ms per token, 24.50 tokens per second) 5.05.567.197 I slot print_timing: id 2 | task 254 | eval time = 204.61 ms / 2 tokens ( 204.61 ms per token, 4.89 tokens per second) 5.05.567.198 I slot print_timing: id 2 | task 254 | total time = 7633.34 ms / 184 tokens 5.05.567.198 I slot print_timing: id 2 | task 254 | graphs reused = 1 5.05.567.198 I slot print_timing: id 2 | task 254 | graph reallocs = 0 / 0 (same size) / (changed size) 5.05.567.210 I slot release: id 2 | task 254 | stop processing: n_tokens = 183, truncated = 0 5.05.567.386 I slot print_timing: id 3 | task 255 | prompt eval time = 7428.89 ms / 155 tokens ( 47.93 ms per token, 20.86 tokens per second) 5.05.567.389 I slot print_timing: id 3 | task 255 | eval time = 204.64 ms / 2 tokens ( 204.64 ms per token, 4.89 tokens per second) 5.05.567.390 I slot print_timing: id 3 | task 255 | total time = 7633.52 ms / 157 tokens 5.05.567.390 I slot print_timing: id 3 | task 255 | graphs reused = 1 5.05.567.390 I slot print_timing: id 3 | task 255 | graph reallocs = 0 / 0 (same size) / (changed size) 5.05.567.400 I slot release: id 3 | task 255 | stop processing: n_tokens = 156, truncated = 0 5.05.573.211 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.194 (> 0.100 thold), f_keep = 0.269 5.05.581.510 I slot launch_slot_: id 0 | task 259 | processing task, is_child = 0 5.05.581.535 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.507 MiB) 5.05.589.430 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.568 MiB) 5.05.605.038 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.693 MiB) 5.05.612.918 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.226 (> 0.100 thold), f_keep = 0.209 5.05.612.997 I slot launch_slot_: id 1 | task 260 | processing task, is_child = 0 5.09.302.368 I slot print_timing: id 0 | task 259 | prompt eval time = 3509.52 ms / 144 tokens ( 24.37 ms per token, 41.03 tokens per second) 5.09.302.370 I slot print_timing: id 0 | task 259 | eval time = 179.80 ms / 2 tokens ( 179.80 ms per token, 5.56 tokens per second) 5.09.302.370 I slot print_timing: id 0 | task 259 | total time = 3689.32 ms / 146 tokens 5.09.302.371 I slot print_timing: id 0 | task 259 | graphs reused = 1 5.09.302.371 I slot print_timing: id 0 | task 259 | graph reallocs = 0 / 0 (same size) / (changed size) 5.09.302.391 I slot release: id 0 | task 259 | stop processing: n_tokens = 145, truncated = 0 5.09.302.524 I slot print_timing: id 1 | task 260 | prompt eval time = 3509.66 ms / 124 tokens ( 28.30 ms per token, 35.33 tokens per second) 5.09.302.525 I slot print_timing: id 1 | task 260 | eval time = 179.80 ms / 2 tokens ( 179.80 ms per token, 5.56 tokens per second) 5.09.302.526 I slot print_timing: id 1 | task 260 | total time = 3689.47 ms / 126 tokens 5.09.302.526 I slot print_timing: id 1 | task 260 | graphs reused = 1 5.09.302.526 I slot print_timing: id 1 | task 260 | graph reallocs = 0 / 0 (same size) / (changed size) 5.09.302.533 I slot release: id 1 | task 260 | stop processing: n_tokens = 125, truncated = 0 5.09.319.009 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 183, t_last = 87094383884 5.09.319.053 I slot launch_slot_: id 2 | task 264 | processing task, is_child = 0 5.09.319.074 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.756 MiB) 5.09.327.679 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.194 MiB) 5.09.336.174 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 156, t_last = 87094384074 5.09.336.224 I slot launch_slot_: id 3 | task 265 | processing task, is_child = 0 5.09.336.259 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 145, t_last = 87098119065 5.09.336.289 I slot launch_slot_: id 0 | task 266 | processing task, is_child = 0 5.09.336.307 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 125, t_last = 87098119207 5.09.336.340 I slot launch_slot_: id 1 | task 267 | processing task, is_child = 0 5.15.017.402 I slot print_timing: id 0 | task 266 | prompt processing, n_tokens = 146, progress = 0.12, t = 5.68 s / 25.70 tokens per second 5.16.194.812 I slot print_timing: id 1 | task 267 | prompt processing, n_tokens = 146, progress = 0.12, t = 5.68 s / 25.70 tokens per second 5.16.199.759 I slot print_timing: id 2 | task 264 | prompt processing, n_tokens = 146, progress = 0.12, t = 5.68 s / 25.70 tokens per second 5.16.204.216 I slot print_timing: id 3 | task 265 | prompt processing, n_tokens = 146, progress = 0.12, t = 5.68 s / 25.70 tokens per second 5.16.214.207 I slot print_timing: id 0 | task 266 | prompt processing, n_tokens = 257, progress = 0.21, t = 6.88 s / 37.37 tokens per second 5.16.214.228 I slot print_timing: id 1 | task 267 | prompt processing, n_tokens = 257, progress = 0.21, t = 6.88 s / 37.37 tokens per second 5.16.214.240 I slot print_timing: id 2 | task 264 | prompt processing, n_tokens = 257, progress = 0.21, t = 6.88 s / 37.37 tokens per second 5.16.214.253 I slot print_timing: id 3 | task 265 | prompt processing, n_tokens = 257, progress = 0.21, t = 6.88 s / 37.37 tokens per second 5.42.256.944 I slot print_timing: id 0 | task 266 | prompt processing, n_tokens = 727, progress = 0.58, t = 32.92 s / 22.08 tokens per second 5.42.532.174 I slot print_timing: id 1 | task 267 | prompt processing, n_tokens = 718, progress = 0.58, t = 32.92 s / 21.81 tokens per second 5.42.536.596 I slot print_timing: id 2 | task 264 | prompt processing, n_tokens = 714, progress = 0.58, t = 32.92 s / 21.69 tokens per second 5.42.541.049 I slot print_timing: id 3 | task 265 | prompt processing, n_tokens = 699, progress = 0.58, t = 32.92 s / 21.23 tokens per second 6.01.211.203 I slot print_timing: id 0 | task 266 | prompt processing, n_tokens = 1125, progress = 0.91, t = 51.87 s / 21.69 tokens per second 6.01.500.959 I slot print_timing: id 1 | task 267 | prompt processing, n_tokens = 1125, progress = 0.91, t = 51.87 s / 21.69 tokens per second 6.01.512.531 I slot print_timing: id 2 | task 264 | prompt processing, n_tokens = 1125, progress = 0.91, t = 51.87 s / 21.69 tokens per second 6.01.525.699 I slot print_timing: id 3 | task 265 | prompt processing, n_tokens = 1125, progress = 0.93, t = 51.87 s / 21.69 tokens per second 6.06.564.057 I slot print_timing: id 0 | task 266 | prompt processing, n_tokens = 1239, progress = 1.00, t = 57.23 s / 21.65 tokens per second 6.06.843.655 I slot print_timing: id 1 | task 267 | prompt processing, n_tokens = 1230, progress = 1.00, t = 57.23 s / 21.49 tokens per second 6.06.857.398 I slot print_timing: id 2 | task 264 | prompt processing, n_tokens = 1226, progress = 1.00, t = 57.23 s / 21.42 tokens per second 6.06.871.047 I slot print_timing: id 3 | task 265 | prompt processing, n_tokens = 1211, progress = 1.00, t = 57.23 s / 21.16 tokens per second 6.21.330.448 I slot print_timing: id 2 | task 264 | prompt eval time = 57894.00 ms / 1230 tokens ( 47.07 ms per token, 21.25 tokens per second) 6.21.330.451 I slot print_timing: id 2 | task 264 | eval time = 14100.06 ms / 70 tokens ( 204.35 ms per token, 4.89 tokens per second) 6.21.330.451 I slot print_timing: id 2 | task 264 | total time = 71994.06 ms / 1300 tokens 6.21.330.452 I slot print_timing: id 2 | task 264 | graphs reused = 70 6.21.330.452 I slot print_timing: id 2 | task 264 | graph reallocs = 0 / 0 (same size) / (changed size) 6.21.330.497 I slot release: id 2 | task 264 | stop processing: n_tokens = 1299, truncated = 0 6.21.610.236 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.882 6.21.610.270 I slot launch_slot_: id 2 | task 344 | processing task, is_child = 0 6.24.292.348 I slot print_timing: id 3 | task 265 | prompt eval time = 57894.15 ms / 1215 tokens ( 47.65 ms per token, 20.99 tokens per second) 6.24.292.353 I slot print_timing: id 3 | task 265 | eval time = 17061.80 ms / 75 tokens ( 230.56 ms per token, 4.34 tokens per second) 6.24.292.354 I slot print_timing: id 3 | task 265 | total time = 74955.94 ms / 1290 tokens 6.24.292.354 I slot print_timing: id 3 | task 265 | graphs reused = 71 6.24.292.355 I slot print_timing: id 3 | task 265 | graph reallocs = 0 / 0 (same size) / (changed size) 6.24.292.399 I slot release: id 3 | task 265 | stop processing: n_tokens = 1289, truncated = 0 6.24.486.803 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.889 6.24.486.831 I slot launch_slot_: id 3 | task 350 | processing task, is_child = 0 6.31.428.331 I slot print_timing: id 0 | task 266 | n_gen = 100, tg = 4.09 t/s, tg_3s = 4.13 t/s 6.31.428.475 I slot print_timing: id 1 | task 267 | n_gen = 100, tg = 4.09 t/s, tg_3s = 4.13 t/s 6.34.495.722 I slot print_timing: id 0 | task 266 | n_gen = 115, tg = 4.18 t/s, tg_3s = 4.89 t/s 6.34.495.868 I slot print_timing: id 1 | task 267 | n_gen = 115, tg = 4.18 t/s, tg_3s = 4.89 t/s 6.37.562.604 I slot print_timing: id 0 | task 266 | n_gen = 130, tg = 4.25 t/s, tg_3s = 4.89 t/s 6.37.562.748 I slot print_timing: id 1 | task 267 | n_gen = 130, tg = 4.25 t/s, tg_3s = 4.89 t/s 6.39.812.593 I slot print_timing: id 0 | task 266 | prompt eval time = 57893.69 ms / 1243 tokens ( 46.58 ms per token, 21.47 tokens per second) 6.39.812.598 I slot print_timing: id 0 | task 266 | eval time = 32582.55 ms / 141 tokens ( 232.73 ms per token, 4.30 tokens per second) 6.39.812.599 I slot print_timing: id 0 | task 266 | total time = 90476.24 ms / 1384 tokens 6.39.812.599 I slot print_timing: id 0 | task 266 | graphs reused = 133 6.39.812.599 I slot print_timing: id 0 | task 266 | graph reallocs = 0 / 0 (same size) / (changed size) 6.39.812.646 I slot release: id 0 | task 266 | stop processing: n_tokens = 1383, truncated = 0 6.40.007.521 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.829 6.40.007.558 I slot launch_slot_: id 0 | task 417 | processing task, is_child = 0 6.42.044.979 I slot print_timing: id 1 | task 267 | n_gen = 143, tg = 4.08 t/s, tg_3s = 2.90 t/s 6.45.081.633 I slot print_timing: id 1 | task 267 | n_gen = 157, tg = 4.12 t/s, tg_3s = 4.61 t/s 6.45.695.683 I slot print_timing: id 3 | task 350 | prompt eval time = 2442.76 ms / 139 tokens ( 17.57 ms per token, 56.90 tokens per second) 6.45.695.688 I slot print_timing: id 3 | task 350 | eval time = 18766.08 ms / 83 tokens ( 228.85 ms per token, 4.37 tokens per second) 6.45.695.689 I slot print_timing: id 3 | task 350 | total time = 21208.84 ms / 222 tokens 6.45.695.689 I slot print_timing: id 3 | task 350 | graphs reused = 149 6.45.695.690 I slot print_timing: id 3 | task 350 | graph reallocs = 0 / 0 (same size) / (changed size) 6.45.695.747 I slot release: id 3 | task 350 | stop processing: n_tokens = 1346, truncated = 0 6.45.890.331 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.851 6.45.890.361 I slot launch_slot_: id 3 | task 437 | processing task, is_child = 0 6.48.175.152 I slot print_timing: id 1 | task 267 | n_gen = 164, tg = 3.98 t/s, tg_3s = 2.26 t/s 6.49.811.225 I slot print_timing: id 2 | task 344 | n_gen = 100, tg = 3.82 t/s, tg_3s = 3.86 t/s 6.50.424.501 I slot print_timing: id 2 | task 344 | prompt eval time = 2270.99 ms / 132 tokens ( 17.20 ms per token, 58.12 tokens per second) 6.50.424.506 I slot print_timing: id 2 | task 344 | eval time = 26543.23 ms / 103 tokens ( 260.23 ms per token, 3.84 tokens per second) 6.50.424.507 I slot print_timing: id 2 | task 344 | total time = 28814.22 ms / 235 tokens 6.50.424.507 I slot print_timing: id 2 | task 344 | graphs reused = 160 6.50.424.508 I slot print_timing: id 2 | task 344 | graph reallocs = 0 / 0 (same size) / (changed size) 6.50.424.551 I slot release: id 2 | task 344 | stop processing: n_tokens = 1359, truncated = 0 6.50.704.547 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.843 6.50.704.579 I slot launch_slot_: id 2 | task 453 | processing task, is_child = 0 6.52.845.210 I slot print_timing: id 1 | task 267 | n_gen = 177, tg = 3.86 t/s, tg_3s = 2.78 t/s 6.55.979.558 I slot print_timing: id 1 | task 267 | n_gen = 191, tg = 3.90 t/s, tg_3s = 4.47 t/s 6.59.047.501 I slot print_timing: id 1 | task 267 | n_gen = 206, tg = 3.96 t/s, tg_3s = 4.89 t/s 7.02.115.497 I slot print_timing: id 1 | task 267 | n_gen = 221, tg = 4.01 t/s, tg_3s = 4.89 t/s 7.05.183.309 I slot print_timing: id 1 | task 267 | n_gen = 236, tg = 4.06 t/s, tg_3s = 4.89 t/s 7.06.614.724 I slot print_timing: id 0 | task 417 | n_gen = 100, tg = 4.09 t/s, tg_3s = 4.13 t/s 7.08.250.912 I slot print_timing: id 1 | task 267 | n_gen = 251, tg = 4.10 t/s, tg_3s = 4.89 t/s 7.09.273.815 I slot print_timing: id 1 | task 267 | prompt eval time = 57893.84 ms / 1234 tokens ( 46.92 ms per token, 21.31 tokens per second) 7.09.273.817 I slot print_timing: id 1 | task 267 | eval time = 62043.61 ms / 256 tokens ( 243.31 ms per token, 4.11 tokens per second) 7.09.273.818 I slot print_timing: id 1 | task 267 | total time = 119937.44 ms / 1490 tokens 7.09.273.819 I slot print_timing: id 1 | task 267 | graphs reused = 237 7.09.273.819 I slot print_timing: id 1 | task 267 | graph reallocs = 0 / 0 (same size) / (changed size) 7.09.273.863 I slot release: id 1 | task 267 | stop processing: n_tokens = 1489, truncated = 0 7.09.553.976 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.886 (> 0.100 thold), f_keep = 0.770 7.09.554.013 I slot launch_slot_: id 1 | task 535 | processing task, is_child = 0 7.12.110.297 I slot print_timing: id 0 | task 417 | n_gen = 115, tg = 3.84 t/s, tg_3s = 2.73 t/s 7.13.261.275 I slot print_timing: id 3 | task 437 | n_gen = 100, tg = 3.91 t/s, tg_3s = 3.95 t/s 7.14.898.017 I slot print_timing: id 3 | task 437 | prompt eval time = 2078.33 ms / 114 tokens ( 18.23 ms per token, 54.85 tokens per second) 7.14.898.022 I slot print_timing: id 3 | task 437 | eval time = 26929.32 ms / 108 tokens ( 251.68 ms per token, 3.97 tokens per second) 7.14.898.023 I slot print_timing: id 3 | task 437 | total time = 29007.65 ms / 222 tokens 7.14.898.023 I slot print_timing: id 3 | task 437 | graphs reused = 247 7.14.898.024 I slot print_timing: id 3 | task 437 | graph reallocs = 0 / 0 (same size) / (changed size) 7.14.898.068 I slot release: id 3 | task 437 | stop processing: n_tokens = 1346, truncated = 0 7.15.092.306 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.851 7.15.092.339 I slot launch_slot_: id 3 | task 550 | processing task, is_child = 0 7.16.797.033 I slot print_timing: id 0 | task 417 | n_gen = 129, tg = 3.72 t/s, tg_3s = 2.99 t/s 7.18.004.043 I slot print_timing: id 2 | task 453 | n_gen = 100, tg = 4.01 t/s, tg_3s = 4.05 t/s 7.19.844.260 I slot print_timing: id 0 | task 417 | n_gen = 143, tg = 3.79 t/s, tg_3s = 4.59 t/s 7.20.048.958 I slot print_timing: id 2 | task 453 | prompt eval time = 2614.45 ms / 141 tokens ( 18.54 ms per token, 53.93 tokens per second) 7.20.048.963 I slot print_timing: id 2 | task 453 | eval time = 26729.92 ms / 110 tokens ( 245.23 ms per token, 4.08 tokens per second) 7.20.048.964 I slot print_timing: id 2 | task 453 | total time = 29344.37 ms / 251 tokens 7.20.048.964 I slot print_timing: id 2 | task 453 | graphs reused = 260 7.20.048.965 I slot print_timing: id 2 | task 453 | graph reallocs = 0 / 0 (same size) / (changed size) 7.20.049.013 I slot release: id 2 | task 453 | stop processing: n_tokens = 1375, truncated = 0 7.20.327.893 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.833 7.20.327.930 I slot launch_slot_: id 2 | task 568 | processing task, is_child = 0 7.22.858.282 I slot print_timing: id 0 | task 417 | n_gen = 150, tg = 3.68 t/s, tg_3s = 2.32 t/s 7.25.924.694 I slot print_timing: id 0 | task 417 | n_gen = 165, tg = 3.77 t/s, tg_3s = 4.89 t/s 7.28.991.971 I slot print_timing: id 0 | task 417 | n_gen = 180, tg = 3.84 t/s, tg_3s = 4.89 t/s 7.32.059.510 I slot print_timing: id 0 | task 417 | n_gen = 195, tg = 3.91 t/s, tg_3s = 4.89 t/s 7.35.127.240 I slot print_timing: id 0 | task 417 | n_gen = 210, tg = 3.97 t/s, tg_3s = 4.89 t/s 7.36.150.294 I slot print_timing: id 1 | task 535 | n_gen = 100, tg = 4.21 t/s, tg_3s = 4.25 t/s 7.37.173.047 I slot print_timing: id 3 | task 550 | prompt eval time = 2091.61 ms / 125 tokens ( 16.73 ms per token, 59.76 tokens per second) 7.37.173.053 I slot print_timing: id 3 | task 550 | eval time = 19989.09 ms / 91 tokens ( 222.10 ms per token, 4.50 tokens per second) 7.37.173.054 I slot print_timing: id 3 | task 550 | total time = 22080.70 ms / 216 tokens 7.37.173.054 I slot print_timing: id 3 | task 550 | graphs reused = 332 7.37.173.055 I slot print_timing: id 3 | task 550 | graph reallocs = 0 / 0 (same size) / (changed size) 7.37.173.103 I slot release: id 3 | task 550 | stop processing: n_tokens = 1340, truncated = 0 7.37.367.421 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.855 7.37.367.450 I slot launch_slot_: id 3 | task 645 | processing task, is_child = 0 7.38.725.674 I slot print_timing: id 0 | task 417 | n_gen = 222, tg = 3.93 t/s, tg_3s = 3.33 t/s 7.39.318.393 I slot print_timing: id 1 | task 535 | n_gen = 109, tg = 4.05 t/s, tg_3s = 2.84 t/s 7.41.568.897 I slot print_timing: id 2 | task 568 | prompt eval time = 1914.50 ms / 101 tokens ( 18.96 ms per token, 52.76 tokens per second) 7.41.568.903 I slot print_timing: id 2 | task 568 | eval time = 19326.46 ms / 89 tokens ( 219.62 ms per token, 4.55 tokens per second) 7.41.568.903 I slot print_timing: id 2 | task 568 | total time = 21240.96 ms / 190 tokens 7.41.568.904 I slot print_timing: id 2 | task 568 | graphs reused = 343 7.41.568.904 I slot print_timing: id 2 | task 568 | graph reallocs = 0 / 0 (same size) / (changed size) 7.41.568.946 I slot release: id 2 | task 568 | stop processing: n_tokens = 1314, truncated = 0 7.41.848.936 I slot print_timing: id 0 | task 417 | n_gen = 236, tg = 3.95 t/s, tg_3s = 4.48 t/s 7.41.849.237 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.872 7.41.849.268 I slot launch_slot_: id 2 | task 661 | processing task, is_child = 0 7.43.306.533 I slot print_timing: id 1 | task 535 | n_gen = 122, tg = 3.95 t/s, tg_3s = 3.26 t/s 7.45.007.991 I slot print_timing: id 0 | task 417 | n_gen = 244, tg = 3.88 t/s, tg_3s = 2.53 t/s 7.46.440.036 I slot print_timing: id 1 | task 535 | n_gen = 136, tg = 3.99 t/s, tg_3s = 4.47 t/s 7.48.075.752 I slot print_timing: id 0 | task 417 | n_gen = 259, tg = 3.93 t/s, tg_3s = 4.89 t/s 7.49.508.628 I slot print_timing: id 1 | task 535 | n_gen = 151, tg = 4.07 t/s, tg_3s = 4.89 t/s 7.51.148.167 I slot print_timing: id 0 | task 417 | n_gen = 274, tg = 3.97 t/s, tg_3s = 4.88 t/s 7.52.580.416 I slot print_timing: id 1 | task 535 | n_gen = 166, tg = 4.13 t/s, tg_3s = 4.88 t/s 7.54.217.498 I slot print_timing: id 0 | task 417 | n_gen = 289, tg = 4.01 t/s, tg_3s = 4.89 t/s 7.55.649.784 I slot print_timing: id 1 | task 535 | n_gen = 181, tg = 4.19 t/s, tg_3s = 4.89 t/s 7.57.082.700 I slot print_timing: id 3 | task 645 | prompt eval time = 1744.06 ms / 101 tokens ( 17.27 ms per token, 57.91 tokens per second) 7.57.082.705 I slot print_timing: id 3 | task 645 | eval time = 17971.18 ms / 81 tokens ( 224.64 ms per token, 4.45 tokens per second) 7.57.082.706 I slot print_timing: id 3 | task 645 | total time = 19715.24 ms / 182 tokens 7.57.082.706 I slot print_timing: id 3 | task 645 | graphs reused = 406 7.57.082.706 I slot print_timing: id 3 | task 645 | graph reallocs = 0 / 0 (same size) / (changed size) 7.57.082.751 I slot release: id 3 | task 645 | stop processing: n_tokens = 1306, truncated = 0 7.57.276.709 I slot print_timing: id 0 | task 417 | n_gen = 304, tg = 4.05 t/s, tg_3s = 4.90 t/s 7.57.276.998 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.877 7.57.277.028 I slot launch_slot_: id 3 | task 730 | processing task, is_child = 0 7.58.980.074 I slot print_timing: id 1 | task 535 | n_gen = 190, tg = 4.08 t/s, tg_3s = 2.70 t/s 8.00.390.112 I slot print_timing: id 0 | task 417 | n_gen = 311, tg = 3.98 t/s, tg_3s = 2.25 t/s 8.01.617.483 I slot print_timing: id 0 | task 417 | prompt eval time = 2413.35 ms / 139 tokens ( 17.36 ms per token, 57.60 tokens per second) 8.01.617.488 I slot print_timing: id 0 | task 417 | eval time = 79196.57 ms / 317 tokens ( 250.62 ms per token, 3.99 tokens per second) 8.01.617.489 I slot print_timing: id 0 | task 417 | total time = 81609.92 ms / 456 tokens 8.01.617.489 I slot print_timing: id 0 | task 417 | graphs reused = 416 8.01.617.490 I slot print_timing: id 0 | task 417 | graph reallocs = 0 / 0 (same size) / (changed size) 8.01.617.537 I slot release: id 0 | task 417 | stop processing: n_tokens = 1580, truncated = 0 8.01.811.999 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.725 8.01.812.033 I slot launch_slot_: id 0 | task 745 | processing task, is_child = 0 8.03.857.073 I slot print_timing: id 1 | task 535 | n_gen = 204, tg = 3.96 t/s, tg_3s = 2.87 t/s 8.06.893.161 I slot print_timing: id 1 | task 535 | n_gen = 218, tg = 4.00 t/s, tg_3s = 4.61 t/s 8.07.711.395 I slot print_timing: id 2 | task 661 | n_gen = 100, tg = 4.14 t/s, tg_3s = 4.18 t/s 8.09.961.305 I slot print_timing: id 1 | task 535 | n_gen = 233, tg = 4.05 t/s, tg_3s = 4.89 t/s 8.10.779.947 I slot print_timing: id 2 | task 661 | n_gen = 115, tg = 4.22 t/s, tg_3s = 4.89 t/s 8.13.032.497 I slot print_timing: id 1 | task 535 | n_gen = 248, tg = 4.09 t/s, tg_3s = 4.88 t/s 8.13.646.342 I slot print_timing: id 2 | task 661 | prompt eval time = 1929.09 ms / 95 tokens ( 20.31 ms per token, 49.25 tokens per second) 8.13.646.347 I slot print_timing: id 2 | task 661 | eval time = 29867.97 ms / 129 tokens ( 233.34 ms per token, 4.29 tokens per second) 8.13.646.348 I slot print_timing: id 2 | task 661 | total time = 31797.06 ms / 224 tokens 8.13.646.348 I slot print_timing: id 2 | task 661 | graphs reused = 461 8.13.646.349 I slot print_timing: id 2 | task 661 | graph reallocs = 0 / 0 (same size) / (changed size) 8.13.646.391 I slot release: id 2 | task 661 | stop processing: n_tokens = 1348, truncated = 0 8.13.926.157 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.850 8.13.926.199 I slot launch_slot_: id 2 | task 795 | processing task, is_child = 0 8.16.052.073 I slot print_timing: id 1 | task 535 | n_gen = 255, tg = 4.01 t/s, tg_3s = 2.32 t/s 8.17.688.788 I slot print_timing: id 3 | task 730 | prompt eval time = 2087.82 ms / 120 tokens ( 17.40 ms per token, 57.48 tokens per second) 8.17.688.794 I slot print_timing: id 3 | task 730 | eval time = 18323.94 ms / 73 tokens ( 254.50 ms per token, 3.93 tokens per second) 8.17.688.795 I slot print_timing: id 3 | task 730 | total time = 20411.75 ms / 193 tokens 8.17.688.795 I slot print_timing: id 3 | task 730 | graphs reused = 469 8.17.688.796 I slot print_timing: id 3 | task 730 | graph reallocs = 0 / 0 (same size) / (changed size) 8.17.688.842 I slot release: id 3 | task 730 | stop processing: n_tokens = 1317, truncated = 0 8.17.882.838 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.911 (> 0.100 thold), f_keep = 0.870 8.17.882.869 I slot launch_slot_: id 3 | task 808 | processing task, is_child = 0 8.19.580.954 I slot print_timing: id 1 | task 535 | n_gen = 265, tg = 3.94 t/s, tg_3s = 2.83 t/s 8.22.628.070 I slot print_timing: id 1 | task 535 | n_gen = 279, tg = 3.97 t/s, tg_3s = 4.59 t/s 8.25.696.847 I slot print_timing: id 1 | task 535 | n_gen = 294, tg = 4.01 t/s, tg_3s = 4.89 t/s 8.27.743.590 I slot print_timing: id 0 | task 745 | n_gen = 100, tg = 4.21 t/s, tg_3s = 4.25 t/s 8.28.767.132 I slot print_timing: id 1 | task 535 | n_gen = 309, tg = 4.05 t/s, tg_3s = 4.89 t/s 8.30.813.204 I slot print_timing: id 0 | task 745 | n_gen = 115, tg = 4.29 t/s, tg_3s = 4.89 t/s 8.31.836.506 I slot print_timing: id 1 | task 535 | n_gen = 324, tg = 4.08 t/s, tg_3s = 4.89 t/s 8.33.883.122 I slot print_timing: id 0 | task 745 | n_gen = 130, tg = 4.35 t/s, tg_3s = 4.89 t/s 8.34.906.094 I slot print_timing: id 1 | task 535 | n_gen = 339, tg = 4.11 t/s, tg_3s = 4.89 t/s 8.36.952.656 I slot print_timing: id 0 | task 745 | n_gen = 145, tg = 4.40 t/s, tg_3s = 4.89 t/s 8.37.771.587 I slot print_timing: id 2 | task 795 | n_gen = 100, tg = 4.52 t/s, tg_3s = 4.56 t/s 8.37.976.146 I slot print_timing: id 1 | task 535 | n_gen = 354, tg = 4.14 t/s, tg_3s = 4.89 t/s 8.40.023.263 I slot print_timing: id 0 | task 745 | n_gen = 160, tg = 4.44 t/s, tg_3s = 4.89 t/s 8.40.228.333 I slot print_timing: id 3 | task 808 | n_gen = 100, tg = 4.89 t/s, tg_3s = 4.94 t/s 8.40.842.220 I slot print_timing: id 2 | task 795 | n_gen = 115, tg = 4.56 t/s, tg_3s = 4.88 t/s 8.41.046.819 I slot print_timing: id 1 | task 535 | n_gen = 369, tg = 4.16 t/s, tg_3s = 4.88 t/s 8.43.094.137 I slot print_timing: id 0 | task 745 | n_gen = 175, tg = 4.48 t/s, tg_3s = 4.88 t/s 8.43.299.265 I slot print_timing: id 3 | task 808 | n_gen = 115, tg = 4.89 t/s, tg_3s = 4.88 t/s 8.43.913.250 I slot print_timing: id 2 | task 795 | n_gen = 130, tg = 4.60 t/s, tg_3s = 4.88 t/s 8.44.117.930 I slot print_timing: id 1 | task 535 | n_gen = 384, tg = 4.19 t/s, tg_3s = 4.88 t/s 8.44.732.345 I slot print_timing: id 2 | task 795 | prompt eval time = 1918.75 ms / 86 tokens ( 22.31 ms per token, 44.82 tokens per second) 8.44.732.350 I slot print_timing: id 2 | task 795 | eval time = 28887.39 ms / 134 tokens ( 217.20 ms per token, 4.60 tokens per second) 8.44.732.351 I slot print_timing: id 2 | task 795 | total time = 30806.14 ms / 220 tokens 8.44.732.351 I slot print_timing: id 2 | task 795 | graphs reused = 589 8.44.732.352 I slot print_timing: id 2 | task 795 | graph reallocs = 0 / 0 (same size) / (changed size) 8.44.732.401 I slot release: id 2 | task 795 | stop processing: n_tokens = 1344, truncated = 0 8.45.012.537 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.853 8.45.012.576 I slot launch_slot_: id 2 | task 933 | processing task, is_child = 0 8.46.469.849 I slot print_timing: id 0 | task 745 | n_gen = 185, tg = 4.36 t/s, tg_3s = 2.96 t/s 8.46.470.150 I slot print_timing: id 3 | task 808 | n_gen = 124, tg = 4.64 t/s, tg_3s = 2.84 t/s 8.47.148.199 I slot print_timing: id 1 | task 535 | n_gen = 391, tg = 4.13 t/s, tg_3s = 2.31 t/s 8.48.990.875 I slot print_timing: id 1 | task 535 | prompt eval time = 3090.47 ms / 169 tokens ( 18.29 ms per token, 54.68 tokens per second) 8.48.990.878 I slot print_timing: id 1 | task 535 | eval time = 96346.38 ms / 400 tokens ( 241.47 ms per token, 4.14 tokens per second) 8.48.990.879 I slot print_timing: id 1 | task 535 | total time = 99436.85 ms / 569 tokens 8.48.990.879 I slot print_timing: id 1 | task 535 | graphs reused = 598 8.48.990.880 I slot print_timing: id 1 | task 535 | graph reallocs = 0 / 0 (same size) / (changed size) 8.48.990.927 I slot release: id 1 | task 535 | stop processing: n_tokens = 1693, truncated = 0 8.49.270.924 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.948 (> 0.100 thold), f_keep = 0.677 8.49.270.959 I slot launch_slot_: id 1 | task 947 | processing task, is_child = 0 8.50.780.348 I slot print_timing: id 0 | task 745 | n_gen = 198, tg = 4.23 t/s, tg_3s = 3.02 t/s 8.50.780.639 I slot print_timing: id 3 | task 808 | n_gen = 137, tg = 4.41 t/s, tg_3s = 3.02 t/s 8.53.362.590 I slot print_timing: id 3 | task 808 | prompt eval time = 2083.24 ms / 133 tokens ( 15.66 ms per token, 63.84 tokens per second) 8.53.362.593 I slot print_timing: id 3 | task 808 | eval time = 33396.46 ms / 148 tokens ( 227.19 ms per token, 4.40 tokens per second) 8.53.362.594 I slot print_timing: id 3 | task 808 | total time = 35479.71 ms / 281 tokens 8.53.362.594 I slot print_timing: id 3 | task 808 | graphs reused = 607 8.53.362.594 I slot print_timing: id 3 | task 808 | graph reallocs = 0 / 0 (same size) / (changed size) 8.53.362.643 I slot release: id 3 | task 808 | stop processing: n_tokens = 1405, truncated = 0 8.53.556.696 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.816 8.53.556.732 I slot launch_slot_: id 3 | task 961 | processing task, is_child = 0 8.54.916.286 I slot print_timing: id 0 | task 745 | n_gen = 211, tg = 4.14 t/s, tg_3s = 3.14 t/s 8.57.961.580 I slot print_timing: id 0 | task 745 | n_gen = 225, tg = 4.17 t/s, tg_3s = 4.60 t/s 9.01.028.124 I slot print_timing: id 0 | task 745 | n_gen = 240, tg = 4.21 t/s, tg_3s = 4.89 t/s 9.04.096.023 I slot print_timing: id 0 | task 745 | n_gen = 255, tg = 4.24 t/s, tg_3s = 4.89 t/s 9.04.301.035 I slot print_timing: id 2 | task 933 | prompt eval time = 1928.84 ms / 97 tokens ( 19.88 ms per token, 50.29 tokens per second) 9.04.301.041 I slot print_timing: id 2 | task 933 | eval time = 17359.62 ms / 71 tokens ( 247.99 ms per token, 4.03 tokens per second) 9.04.301.042 I slot print_timing: id 2 | task 933 | total time = 19288.45 ms / 168 tokens 9.04.301.042 I slot print_timing: id 2 | task 933 | graphs reused = 650 9.04.301.043 I slot print_timing: id 2 | task 933 | graph reallocs = 0 / 0 (same size) / (changed size) 9.04.301.087 I slot release: id 2 | task 933 | stop processing: n_tokens = 1292, truncated = 0 9.04.580.169 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.887 9.04.580.202 I slot launch_slot_: id 2 | task 1009 | processing task, is_child = 0 9.07.124.242 I slot print_timing: id 0 | task 745 | n_gen = 262, tg = 4.15 t/s, tg_3s = 2.31 t/s 9.10.194.998 I slot print_timing: id 0 | task 745 | n_gen = 277, tg = 4.18 t/s, tg_3s = 4.88 t/s 9.10.399.664 I slot print_timing: id 1 | task 947 | prompt eval time = 2043.33 ms / 84 tokens ( 24.33 ms per token, 41.11 tokens per second) 9.10.399.669 I slot print_timing: id 1 | task 947 | eval time = 19085.37 ms / 80 tokens ( 241.59 ms per token, 4.14 tokens per second) 9.10.399.670 I slot print_timing: id 1 | task 947 | total time = 21128.70 ms / 164 tokens 9.10.399.670 I slot print_timing: id 1 | task 947 | graphs reused = 667 9.10.399.671 I slot print_timing: id 1 | task 947 | graph reallocs = 0 / 0 (same size) / (changed size) 9.10.399.718 I slot release: id 1 | task 947 | stop processing: n_tokens = 1288, truncated = 0 9.10.679.289 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.890 9.10.679.319 I slot launch_slot_: id 1 | task 1032 | processing task, is_child = 0 9.13.279.014 I slot print_timing: id 0 | task 745 | n_gen = 282, tg = 4.07 t/s, tg_3s = 1.62 t/s 9.16.346.861 I slot print_timing: id 0 | task 745 | n_gen = 297, tg = 4.10 t/s, tg_3s = 4.89 t/s 9.19.211.030 I slot print_timing: id 3 | task 961 | n_gen = 100, tg = 4.14 t/s, tg_3s = 4.18 t/s 9.19.415.298 I slot print_timing: id 0 | task 745 | n_gen = 312, tg = 4.14 t/s, tg_3s = 4.89 t/s 9.21.461.581 I slot print_timing: id 2 | task 1009 | prompt eval time = 1927.74 ms / 95 tokens ( 20.29 ms per token, 49.28 tokens per second) 9.21.461.585 I slot print_timing: id 2 | task 1009 | eval time = 14953.63 ms / 64 tokens ( 237.36 ms per token, 4.21 tokens per second) 9.21.461.585 I slot print_timing: id 2 | task 1009 | total time = 16881.37 ms / 159 tokens 9.21.461.586 I slot print_timing: id 2 | task 1009 | graphs reused = 707 9.21.461.586 I slot print_timing: id 2 | task 1009 | graph reallocs = 0 / 0 (same size) / (changed size) 9.21.461.631 I slot release: id 2 | task 1009 | stop processing: n_tokens = 1283, truncated = 0 9.21.741.740 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.943 (> 0.100 thold), f_keep = 0.893 9.21.741.785 I slot launch_slot_: id 2 | task 1077 | processing task, is_child = 0 9.23.195.413 I slot print_timing: id 0 | task 745 | n_gen = 324, tg = 4.09 t/s, tg_3s = 3.17 t/s 9.23.195.741 I slot print_timing: id 3 | task 961 | n_gen = 113, tg = 4.02 t/s, tg_3s = 3.26 t/s 9.26.328.452 I slot print_timing: id 0 | task 745 | n_gen = 338, tg = 4.10 t/s, tg_3s = 4.47 t/s 9.26.328.903 I slot print_timing: id 3 | task 961 | n_gen = 127, tg = 4.06 t/s, tg_3s = 4.47 t/s 9.27.555.535 I slot print_timing: id 3 | task 961 | prompt eval time = 1744.02 ms / 101 tokens ( 17.27 ms per token, 57.91 tokens per second) 9.27.555.538 I slot print_timing: id 3 | task 961 | eval time = 32254.77 ms / 133 tokens ( 244.35 ms per token, 4.09 tokens per second) 9.27.555.538 I slot print_timing: id 3 | task 961 | total time = 33998.79 ms / 234 tokens 9.27.555.539 I slot print_timing: id 3 | task 961 | graphs reused = 725 9.27.555.539 I slot print_timing: id 3 | task 961 | graph reallocs = 0 / 0 (same size) / (changed size) 9.27.555.588 I slot release: id 3 | task 961 | stop processing: n_tokens = 1358, truncated = 0 9.27.749.708 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.844 9.27.749.738 I slot launch_slot_: id 3 | task 1100 | processing task, is_child = 0 9.29.507.214 I slot print_timing: id 0 | task 745 | n_gen = 347, tg = 4.06 t/s, tg_3s = 2.83 t/s 9.30.327.949 I slot print_timing: id 0 | task 745 | prompt eval time = 2419.83 ms / 148 tokens ( 16.35 ms per token, 61.16 tokens per second) 9.30.327.954 I slot print_timing: id 0 | task 745 | eval time = 86096.08 ms / 351 tokens ( 245.99 ms per token, 4.07 tokens per second) 9.30.327.955 I slot print_timing: id 0 | task 745 | total time = 88515.91 ms / 499 tokens 9.30.327.955 I slot print_timing: id 0 | task 745 | graphs reused = 728 9.30.327.956 I slot print_timing: id 0 | task 745 | graph reallocs = 0 / 0 (same size) / (changed size) 9.30.328.001 I slot release: id 0 | task 745 | stop processing: n_tokens = 1623, truncated = 0 9.30.523.178 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.706 9.30.523.210 I slot launch_slot_: id 0 | task 1108 | processing task, is_child = 0 9.37.550.549 I slot print_timing: id 1 | task 1032 | n_gen = 100, tg = 4.04 t/s, tg_3s = 4.09 t/s 9.40.617.377 I slot print_timing: id 1 | task 1032 | n_gen = 115, tg = 4.14 t/s, tg_3s = 4.89 t/s 9.43.684.269 I slot print_timing: id 1 | task 1032 | n_gen = 130, tg = 4.21 t/s, tg_3s = 4.89 t/s 9.45.933.444 I slot print_timing: id 2 | task 1077 | prompt eval time = 1924.75 ms / 90 tokens ( 21.39 ms per token, 46.76 tokens per second) 9.45.933.447 I slot print_timing: id 2 | task 1077 | eval time = 22266.90 ms / 97 tokens ( 231.95 ms per token, 4.31 tokens per second) 9.45.933.447 I slot print_timing: id 2 | task 1077 | total time = 24191.65 ms / 187 tokens 9.45.933.448 I slot print_timing: id 2 | task 1077 | graphs reused = 795 9.45.933.448 I slot print_timing: id 2 | task 1077 | graph reallocs = 0 / 0 (same size) / (changed size) 9.45.933.494 I slot release: id 2 | task 1077 | stop processing: n_tokens = 1311, truncated = 0 9.46.213.058 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.875 9.46.213.096 I slot launch_slot_: id 2 | task 1179 | processing task, is_child = 0 9.48.010.300 I slot print_timing: id 1 | task 1032 | n_gen = 143, tg = 4.06 t/s, tg_3s = 3.01 t/s 9.51.140.586 I slot print_timing: id 1 | task 1032 | n_gen = 157, tg = 4.10 t/s, tg_3s = 4.47 t/s 9.51.140.877 I slot print_timing: id 3 | task 1100 | prompt eval time = 1757.98 ms / 96 tokens ( 18.31 ms per token, 54.61 tokens per second) 9.51.140.880 I slot print_timing: id 3 | task 1100 | eval time = 21633.15 ms / 91 tokens ( 240.37 ms per token, 4.16 tokens per second) 9.51.140.881 I slot print_timing: id 3 | task 1100 | total time = 23391.13 ms / 187 tokens 9.51.140.882 I slot print_timing: id 3 | task 1100 | graphs reused = 807 9.51.140.882 I slot print_timing: id 3 | task 1100 | graph reallocs = 0 / 0 (same size) / (changed size) 9.51.140.927 I slot release: id 3 | task 1100 | stop processing: n_tokens = 1311, truncated = 0 9.51.334.809 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.874 9.51.334.836 I slot launch_slot_: id 3 | task 1196 | processing task, is_child = 0 9.54.185.206 I slot print_timing: id 1 | task 1032 | n_gen = 162, tg = 3.92 t/s, tg_3s = 1.64 t/s 9.56.434.185 I slot print_timing: id 0 | task 1108 | n_gen = 100, tg = 4.09 t/s, tg_3s = 4.13 t/s 9.57.252.612 I slot print_timing: id 1 | task 1032 | n_gen = 177, tg = 3.98 t/s, tg_3s = 4.89 t/s 9.59.502.179 I slot print_timing: id 0 | task 1108 | n_gen = 115, tg = 4.18 t/s, tg_3s = 4.89 t/s 9.59.502.326 I slot print_timing: id 1 | task 1032 | prompt eval time = 2393.19 ms / 130 tokens ( 18.41 ms per token, 54.32 tokens per second) 9.59.502.328 I slot print_timing: id 1 | task 1032 | eval time = 46429.81 ms / 188 tokens ( 248.29 ms per token, 4.03 tokens per second) 9.59.502.328 I slot print_timing: id 1 | task 1032 | total time = 48823.00 ms / 318 tokens 9.59.502.329 I slot print_timing: id 1 | task 1032 | graphs reused = 834 9.59.502.329 I slot print_timing: id 1 | task 1032 | graph reallocs = 0 / 0 (same size) / (changed size) 9.59.502.381 I slot release: id 1 | task 1032 | stop processing: n_tokens = 1442, truncated = 0 9.59.782.458 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.795 9.59.782.488 I slot launch_slot_: id 1 | task 1228 | processing task, is_child = 0 10.02.530.910 I slot print_timing: id 0 | task 1108 | n_gen = 118, tg = 3.86 t/s, tg_3s = 0.99 t/s 10.03.759.953 I slot print_timing: id 0 | task 1108 | prompt eval time = 1724.37 ms / 87 tokens ( 19.82 ms per token, 50.45 tokens per second) 10.03.759.955 I slot print_timing: id 0 | task 1108 | eval time = 31512.37 ms / 124 tokens ( 256.20 ms per token, 3.90 tokens per second) 10.03.759.956 I slot print_timing: id 0 | task 1108 | total time = 33236.74 ms / 211 tokens 10.03.759.956 I slot print_timing: id 0 | task 1108 | graphs reused = 839 10.03.759.957 I slot print_timing: id 0 | task 1108 | graph reallocs = 0 / 0 (same size) / (changed size) 10.03.759.999 I slot release: id 0 | task 1108 | stop processing: n_tokens = 1335, truncated = 0 10.03.954.887 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.941 (> 0.100 thold), f_keep = 0.858 10.03.954.926 I slot launch_slot_: id 0 | task 1238 | processing task, is_child = 0 10.11.415.403 I slot print_timing: id 2 | task 1179 | prompt eval time = 2267.45 ms / 131 tokens ( 17.31 ms per token, 57.77 tokens per second) 10.11.415.406 I slot print_timing: id 2 | task 1179 | eval time = 22934.85 ms / 85 tokens ( 273.03 ms per token, 3.66 tokens per second) 10.11.415.407 I slot print_timing: id 2 | task 1179 | total time = 25202.30 ms / 216 tokens 10.11.415.407 I slot print_timing: id 2 | task 1179 | graphs reused = 867 10.11.415.408 I slot print_timing: id 2 | task 1179 | graph reallocs = 0 / 0 (same size) / (changed size) 10.11.415.454 I slot release: id 2 | task 1179 | stop processing: n_tokens = 1340, truncated = 0 10.11.694.618 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.855 10.11.694.651 I slot launch_slot_: id 2 | task 1270 | processing task, is_child = 0 10.19.339.597 I slot print_timing: id 3 | task 1196 | n_gen = 100, tg = 3.87 t/s, tg_3s = 3.91 t/s 10.22.405.312 I slot print_timing: id 3 | task 1196 | n_gen = 115, tg = 3.98 t/s, tg_3s = 4.89 t/s 10.23.018.215 I slot print_timing: id 0 | task 1238 | prompt eval time = 1735.41 ms / 93 tokens ( 18.66 ms per token, 53.59 tokens per second) 10.23.018.220 I slot print_timing: id 0 | task 1238 | eval time = 17327.88 ms / 78 tokens ( 225.04 ms per token, 4.44 tokens per second) 10.23.018.221 I slot print_timing: id 0 | task 1238 | total time = 19063.28 ms / 171 tokens 10.23.018.221 I slot print_timing: id 0 | task 1238 | graphs reused = 912 10.23.018.222 I slot print_timing: id 0 | task 1238 | graph reallocs = 0 / 0 (same size) / (changed size) 10.23.018.266 I slot release: id 0 | task 1238 | stop processing: n_tokens = 1295, truncated = 0 10.23.212.559 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.885 10.23.212.591 I slot launch_slot_: id 0 | task 1320 | processing task, is_child = 0 10.25.565.971 I slot print_timing: id 3 | task 1196 | n_gen = 124, tg = 3.87 t/s, tg_3s = 2.85 t/s 10.26.792.415 I slot print_timing: id 2 | task 1270 | prompt eval time = 1918.99 ms / 87 tokens ( 22.06 ms per token, 45.34 tokens per second) 10.26.792.421 I slot print_timing: id 2 | task 1270 | eval time = 13178.77 ms / 59 tokens ( 227.22 ms per token, 4.40 tokens per second) 10.26.792.422 I slot print_timing: id 2 | task 1270 | total time = 15097.76 ms / 146 tokens 10.26.792.422 I slot print_timing: id 2 | task 1270 | graphs reused = 921 10.26.792.423 I slot print_timing: id 2 | task 1270 | graph reallocs = 0 / 0 (same size) / (changed size) 10.26.792.470 I slot release: id 2 | task 1270 | stop processing: n_tokens = 1270, truncated = 0 10.27.071.539 I slot print_timing: id 1 | task 1228 | n_gen = 100, tg = 4.03 t/s, tg_3s = 4.07 t/s 10.27.071.701 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.902 10.27.071.732 I slot launch_slot_: id 2 | task 1333 | processing task, is_child = 0 10.28.843.187 I slot print_timing: id 3 | task 1196 | n_gen = 132, tg = 3.74 t/s, tg_3s = 2.44 t/s 10.30.133.185 I slot print_timing: id 1 | task 1228 | n_gen = 106, tg = 3.80 t/s, tg_3s = 1.96 t/s 10.31.973.882 I slot print_timing: id 3 | task 1196 | n_gen = 146, tg = 3.80 t/s, tg_3s = 4.47 t/s 10.33.201.247 I slot print_timing: id 1 | task 1228 | n_gen = 121, tg = 3.91 t/s, tg_3s = 4.89 t/s 10.35.042.655 I slot print_timing: id 3 | task 1196 | n_gen = 161, tg = 3.88 t/s, tg_3s = 4.89 t/s 10.36.269.631 I slot print_timing: id 1 | task 1228 | n_gen = 136, tg = 4.00 t/s, tg_3s = 4.89 t/s 10.38.110.624 I slot print_timing: id 3 | task 1196 | n_gen = 176, tg = 3.95 t/s, tg_3s = 4.89 t/s 10.39.337.501 I slot print_timing: id 1 | task 1228 | n_gen = 151, tg = 4.08 t/s, tg_3s = 4.89 t/s 10.40.564.960 I slot print_timing: id 0 | task 1320 | prompt eval time = 1737.24 ms / 98 tokens ( 17.73 ms per token, 56.41 tokens per second) 10.40.564.965 I slot print_timing: id 0 | task 1320 | eval time = 15615.13 ms / 68 tokens ( 233.06 ms per token, 4.29 tokens per second) 10.40.564.966 I slot print_timing: id 0 | task 1320 | total time = 17352.36 ms / 166 tokens 10.40.564.966 I slot print_timing: id 0 | task 1320 | graphs reused = 975 10.40.564.967 I slot print_timing: id 0 | task 1320 | graph reallocs = 0 / 0 (same size) / (changed size) 10.40.565.013 I slot release: id 0 | task 1320 | stop processing: n_tokens = 1290, truncated = 0 10.40.760.243 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.888 10.40.760.274 I slot launch_slot_: id 0 | task 1392 | processing task, is_child = 0 10.42.439.291 I slot print_timing: id 1 | task 1228 | n_gen = 159, tg = 3.96 t/s, tg_3s = 2.58 t/s 10.42.439.722 I slot print_timing: id 3 | task 1196 | n_gen = 190, tg = 3.88 t/s, tg_3s = 3.23 t/s 10.45.476.872 I slot print_timing: id 1 | task 1228 | n_gen = 173, tg = 4.01 t/s, tg_3s = 4.61 t/s 10.45.477.149 I slot print_timing: id 3 | task 1196 | n_gen = 204, tg = 3.93 t/s, tg_3s = 4.61 t/s 10.48.545.540 I slot print_timing: id 1 | task 1228 | n_gen = 188, tg = 4.06 t/s, tg_3s = 4.89 t/s 10.48.545.824 I slot print_timing: id 3 | task 1196 | n_gen = 219, tg = 3.98 t/s, tg_3s = 4.89 t/s 10.51.204.901 I slot print_timing: id 2 | task 1333 | n_gen = 100, tg = 4.52 t/s, tg_3s = 4.57 t/s 10.51.614.127 I slot print_timing: id 1 | task 1228 | n_gen = 203, tg = 4.12 t/s, tg_3s = 4.89 t/s 10.51.614.397 I slot print_timing: id 3 | task 1196 | n_gen = 234, tg = 4.03 t/s, tg_3s = 4.89 t/s 10.54.274.832 I slot print_timing: id 2 | task 1333 | n_gen = 115, tg = 4.57 t/s, tg_3s = 4.89 t/s 10.54.683.921 I slot print_timing: id 1 | task 1228 | n_gen = 218, tg = 4.16 t/s, tg_3s = 4.89 t/s 10.54.684.195 I slot print_timing: id 3 | task 1196 | n_gen = 249, tg = 4.07 t/s, tg_3s = 4.89 t/s 10.57.344.702 I slot print_timing: id 2 | task 1333 | n_gen = 130, tg = 4.60 t/s, tg_3s = 4.89 t/s 10.57.753.742 I slot print_timing: id 1 | task 1228 | n_gen = 233, tg = 4.20 t/s, tg_3s = 4.89 t/s 10.57.754.029 I slot print_timing: id 3 | task 1196 | n_gen = 264, tg = 4.11 t/s, tg_3s = 4.89 t/s 11.00.416.872 I slot print_timing: id 2 | task 1333 | n_gen = 145, tg = 4.63 t/s, tg_3s = 4.88 t/s 11.00.826.017 I slot print_timing: id 1 | task 1228 | n_gen = 248, tg = 4.24 t/s, tg_3s = 4.88 t/s 11.00.826.301 I slot print_timing: id 3 | task 1196 | n_gen = 279, tg = 4.15 t/s, tg_3s = 4.88 t/s 11.03.077.792 I slot print_timing: id 0 | task 1392 | n_gen = 100, tg = 4.89 t/s, tg_3s = 4.94 t/s 11.03.487.691 I slot print_timing: id 2 | task 1333 | n_gen = 160, tg = 4.65 t/s, tg_3s = 4.88 t/s 11.03.897.285 I slot print_timing: id 1 | task 1228 | n_gen = 263, tg = 4.27 t/s, tg_3s = 4.88 t/s 11.03.897.580 I slot print_timing: id 3 | task 1196 | n_gen = 294, tg = 4.18 t/s, tg_3s = 4.88 t/s 11.05.330.375 I slot print_timing: id 2 | task 1333 | prompt eval time = 2240.98 ms / 105 tokens ( 21.34 ms per token, 46.85 tokens per second) 11.05.330.380 I slot print_timing: id 2 | task 1333 | eval time = 36017.66 ms / 169 tokens ( 214.39 ms per token, 4.66 tokens per second) 11.05.330.381 I slot print_timing: id 2 | task 1333 | total time = 38258.63 ms / 274 tokens 11.05.330.381 I slot print_timing: id 2 | task 1333 | graphs reused = 1084 11.05.330.382 I slot print_timing: id 2 | task 1333 | graph reallocs = 0 / 0 (same size) / (changed size) 11.05.330.424 I slot release: id 2 | task 1333 | stop processing: n_tokens = 1398, truncated = 0 11.05.610.672 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.820 11.05.610.723 I slot launch_slot_: id 2 | task 1506 | processing task, is_child = 0 11.07.398.300 I slot print_timing: id 0 | task 1392 | n_gen = 113, tg = 4.56 t/s, tg_3s = 3.01 t/s 11.07.398.492 I slot print_timing: id 1 | task 1228 | n_gen = 272, tg = 4.18 t/s, tg_3s = 2.57 t/s 11.07.398.651 I slot print_timing: id 3 | task 1196 | n_gen = 303, tg = 4.10 t/s, tg_3s = 2.57 t/s 11.10.530.867 I slot print_timing: id 0 | task 1392 | n_gen = 127, tg = 4.55 t/s, tg_3s = 4.47 t/s 11.10.531.015 I slot print_timing: id 1 | task 1228 | n_gen = 286, tg = 4.19 t/s, tg_3s = 4.47 t/s 11.10.531.310 I slot print_timing: id 3 | task 1196 | n_gen = 317, tg = 4.12 t/s, tg_3s = 4.47 t/s 11.11.350.212 I slot print_timing: id 1 | task 1228 | prompt eval time = 2748.64 ms / 153 tokens ( 17.96 ms per token, 55.66 tokens per second) 11.11.350.215 I slot print_timing: id 1 | task 1228 | eval time = 68819.07 ms / 290 tokens ( 238.13 ms per token, 4.20 tokens per second) 11.11.350.215 I slot print_timing: id 1 | task 1228 | total time = 71567.72 ms / 443 tokens 11.11.350.216 I slot print_timing: id 1 | task 1228 | graphs reused = 1100 11.11.350.216 I slot print_timing: id 1 | task 1228 | graph reallocs = 0 / 0 (same size) / (changed size) 11.11.350.268 I slot release: id 1 | task 1228 | stop processing: n_tokens = 1567, truncated = 0 11.11.629.870 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.731 11.11.629.902 I slot launch_slot_: id 1 | task 1527 | processing task, is_child = 0 11.13.680.449 I slot print_timing: id 0 | task 1392 | n_gen = 134, tg = 4.31 t/s, tg_3s = 2.22 t/s 11.13.680.910 I slot print_timing: id 3 | task 1196 | n_gen = 324, tg = 4.04 t/s, tg_3s = 2.22 t/s 11.16.751.996 I slot print_timing: id 0 | task 1392 | n_gen = 149, tg = 4.36 t/s, tg_3s = 4.88 t/s 11.16.752.403 I slot print_timing: id 3 | task 1196 | n_gen = 339, tg = 4.07 t/s, tg_3s = 4.88 t/s 11.19.821.494 I slot print_timing: id 0 | task 1392 | n_gen = 164, tg = 4.40 t/s, tg_3s = 4.89 t/s 11.19.821.889 I slot print_timing: id 3 | task 1196 | n_gen = 354, tg = 4.10 t/s, tg_3s = 4.89 t/s 11.22.888.718 I slot print_timing: id 0 | task 1392 | n_gen = 179, tg = 4.44 t/s, tg_3s = 4.89 t/s 11.22.889.136 I slot print_timing: id 3 | task 1196 | n_gen = 369, tg = 4.13 t/s, tg_3s = 4.89 t/s 11.25.957.779 I slot print_timing: id 0 | task 1392 | n_gen = 194, tg = 4.47 t/s, tg_3s = 4.89 t/s 11.25.958.209 I slot print_timing: id 3 | task 1196 | n_gen = 384, tg = 4.15 t/s, tg_3s = 4.89 t/s 11.29.027.560 I slot print_timing: id 0 | task 1392 | n_gen = 209, tg = 4.50 t/s, tg_3s = 4.89 t/s 11.29.027.992 I slot print_timing: id 3 | task 1196 | n_gen = 399, tg = 4.18 t/s, tg_3s = 4.89 t/s 11.29.846.733 I slot print_timing: id 2 | task 1506 | n_gen = 100, tg = 4.50 t/s, tg_3s = 4.55 t/s 11.30.869.172 I slot print_timing: id 0 | task 1392 | prompt eval time = 2055.21 ms / 113 tokens ( 18.19 ms per token, 54.98 tokens per second) 11.30.869.174 I slot print_timing: id 0 | task 1392 | eval time = 48053.68 ms / 218 tokens ( 221.45 ms per token, 4.52 tokens per second) 11.30.869.175 I slot print_timing: id 0 | task 1392 | total time = 50108.89 ms / 331 tokens 11.30.869.175 I slot print_timing: id 0 | task 1392 | graphs reused = 1183 11.30.869.176 I slot print_timing: id 0 | task 1392 | graph reallocs = 0 / 0 (same size) / (changed size) 11.30.869.221 I slot release: id 0 | task 1392 | stop processing: n_tokens = 1455, truncated = 0 11.31.063.920 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.788 11.31.063.971 I slot launch_slot_: id 0 | task 1615 | processing task, is_child = 0 11.32.745.147 I slot print_timing: id 2 | task 1506 | prompt eval time = 2258.32 ms / 122 tokens ( 18.51 ms per token, 54.02 tokens per second) 11.32.745.149 I slot print_timing: id 2 | task 1506 | eval time = 24876.10 ms / 107 tokens ( 234.68 ms per token, 4.26 tokens per second) 11.32.745.149 I slot print_timing: id 2 | task 1506 | total time = 27134.41 ms / 229 tokens 11.32.745.150 I slot print_timing: id 2 | task 1506 | graphs reused = 1184 11.32.745.150 I slot print_timing: id 2 | task 1506 | graph reallocs = 0 / 0 (same size) / (changed size) 11.32.745.198 I slot release: id 2 | task 1506 | stop processing: n_tokens = 1353, truncated = 0 11.32.745.419 I slot print_timing: id 3 | task 1196 | n_gen = 410, tg = 4.13 t/s, tg_3s = 2.96 t/s 11.33.125.968 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.847 11.33.126.003 I slot launch_slot_: id 2 | task 1618 | processing task, is_child = 0 11.35.949.282 I slot print_timing: id 3 | task 1196 | n_gen = 414, tg = 4.04 t/s, tg_3s = 1.25 t/s 11.37.790.308 I slot print_timing: id 1 | task 1527 | n_gen = 100, tg = 4.11 t/s, tg_3s = 4.15 t/s 11.39.017.419 I slot print_timing: id 3 | task 1196 | n_gen = 429, tg = 4.07 t/s, tg_3s = 4.89 t/s 11.40.858.406 I slot print_timing: id 1 | task 1527 | n_gen = 115, tg = 4.19 t/s, tg_3s = 4.89 t/s 11.42.086.734 I slot print_timing: id 3 | task 1196 | n_gen = 444, tg = 4.09 t/s, tg_3s = 4.89 t/s 11.43.927.761 I slot print_timing: id 1 | task 1527 | n_gen = 130, tg = 4.26 t/s, tg_3s = 4.89 t/s 11.45.156.037 I slot print_timing: id 3 | task 1196 | n_gen = 459, tg = 4.11 t/s, tg_3s = 4.89 t/s 11.45.770.089 I slot print_timing: id 3 | task 1196 | prompt eval time = 2439.21 ms / 137 tokens ( 17.80 ms per token, 56.17 tokens per second) 11.45.770.094 I slot print_timing: id 3 | task 1196 | eval time = 111996.03 ms / 462 tokens ( 242.94 ms per token, 4.12 tokens per second) 11.45.770.094 I slot print_timing: id 3 | task 1196 | total time = 114435.25 ms / 599 tokens 11.45.770.095 I slot print_timing: id 3 | task 1196 | graphs reused = 1232 11.45.770.095 I slot print_timing: id 3 | task 1196 | graph reallocs = 0 / 0 (same size) / (changed size) 11.45.770.142 I slot release: id 3 | task 1196 | stop processing: n_tokens = 1723, truncated = 0 11.45.964.435 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.665 11.45.964.466 I slot launch_slot_: id 3 | task 1671 | processing task, is_child = 0 11.47.676.134 I slot print_timing: id 1 | task 1527 | n_gen = 141, tg = 4.12 t/s, tg_3s = 2.93 t/s 11.50.720.880 I slot print_timing: id 1 | task 1527 | n_gen = 155, tg = 4.16 t/s, tg_3s = 4.60 t/s 11.53.788.470 I slot print_timing: id 1 | task 1527 | n_gen = 170, tg = 4.21 t/s, tg_3s = 4.89 t/s 11.56.856.220 I slot print_timing: id 1 | task 1527 | n_gen = 185, tg = 4.26 t/s, tg_3s = 4.89 t/s 11.57.265.111 I slot print_timing: id 0 | task 1615 | n_gen = 100, tg = 4.10 t/s, tg_3s = 4.14 t/s 11.57.674.542 I slot print_timing: id 2 | task 1618 | n_gen = 100, tg = 4.51 t/s, tg_3s = 4.56 t/s 11.59.925.699 I slot print_timing: id 1 | task 1527 | n_gen = 200, tg = 4.30 t/s, tg_3s = 4.89 t/s 12.00.334.743 I slot print_timing: id 0 | task 1615 | n_gen = 115, tg = 4.19 t/s, tg_3s = 4.89 t/s 12.00.742.218 I slot print_timing: id 1 | task 1527 | prompt eval time = 2050.72 ms / 96 tokens ( 21.36 ms per token, 46.81 tokens per second) 12.00.742.223 I slot print_timing: id 1 | task 1527 | eval time = 47061.59 ms / 204 tokens ( 231.83 ms per token, 4.31 tokens per second) 12.00.742.223 I slot print_timing: id 1 | task 1527 | total time = 49112.31 ms / 300 tokens 12.00.742.224 I slot print_timing: id 1 | task 1527 | graphs reused = 1293 12.00.742.224 I slot print_timing: id 1 | task 1527 | graph reallocs = 0 / 0 (same size) / (changed size) 12.00.742.270 I slot release: id 1 | task 1527 | stop processing: n_tokens = 1424, truncated = 0 12.00.742.428 I slot print_timing: id 2 | task 1618 | n_gen = 115, tg = 4.56 t/s, tg_3s = 4.89 t/s 12.01.022.502 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.805 12.01.022.535 I slot launch_slot_: id 1 | task 1737 | processing task, is_child = 0 12.03.402.677 I slot print_timing: id 0 | task 1615 | n_gen = 120, tg = 3.93 t/s, tg_3s = 1.63 t/s 12.03.814.191 I slot print_timing: id 2 | task 1618 | n_gen = 120, tg = 4.24 t/s, tg_3s = 1.63 t/s 12.06.473.419 I slot print_timing: id 0 | task 1615 | prompt eval time = 2061.69 ms / 113 tokens ( 18.25 ms per token, 54.81 tokens per second) 12.06.473.424 I slot print_timing: id 0 | task 1615 | eval time = 33347.75 ms / 135 tokens ( 248.86 ms per token, 4.02 tokens per second) 12.06.473.425 I slot print_timing: id 0 | task 1615 | total time = 35409.44 ms / 248 tokens 12.06.473.425 I slot print_timing: id 0 | task 1615 | graphs reused = 1307 12.06.473.425 I slot print_timing: id 0 | task 1615 | graph reallocs = 0 / 0 (same size) / (changed size) 12.06.473.468 I slot release: id 0 | task 1615 | stop processing: n_tokens = 1372, truncated = 0 12.06.668.456 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.835 12.06.668.492 I slot launch_slot_: id 0 | task 1756 | processing task, is_child = 0 12.08.362.528 I slot print_timing: id 2 | task 1618 | n_gen = 135, tg = 4.11 t/s, tg_3s = 3.30 t/s 12.11.397.050 I slot print_timing: id 2 | task 1618 | n_gen = 149, tg = 4.15 t/s, tg_3s = 4.61 t/s 12.12.010.770 I slot print_timing: id 3 | task 1671 | n_gen = 100, tg = 4.13 t/s, tg_3s = 4.18 t/s 12.14.464.715 I slot print_timing: id 2 | task 1618 | n_gen = 164, tg = 4.21 t/s, tg_3s = 4.89 t/s 12.15.077.991 I slot print_timing: id 3 | task 1671 | n_gen = 115, tg = 4.22 t/s, tg_3s = 4.89 t/s 12.17.532.681 I slot print_timing: id 2 | task 1618 | n_gen = 179, tg = 4.26 t/s, tg_3s = 4.89 t/s 12.18.146.457 I slot print_timing: id 3 | task 1671 | n_gen = 130, tg = 4.29 t/s, tg_3s = 4.89 t/s 12.20.601.435 I slot print_timing: id 2 | task 1618 | n_gen = 194, tg = 4.30 t/s, tg_3s = 4.89 t/s 12.21.214.743 I slot print_timing: id 3 | task 1671 | n_gen = 145, tg = 4.34 t/s, tg_3s = 4.89 t/s 12.23.670.184 I slot print_timing: id 2 | task 1618 | n_gen = 209, tg = 4.34 t/s, tg_3s = 4.89 t/s 12.24.284.363 I slot print_timing: id 3 | task 1671 | n_gen = 160, tg = 4.39 t/s, tg_3s = 4.89 t/s 12.25.306.966 I slot print_timing: id 1 | task 1737 | n_gen = 100, tg = 4.52 t/s, tg_3s = 4.57 t/s 12.26.739.723 I slot print_timing: id 2 | task 1618 | n_gen = 224, tg = 4.37 t/s, tg_3s = 4.89 t/s 12.27.353.683 I slot print_timing: id 3 | task 1671 | n_gen = 175, tg = 4.43 t/s, tg_3s = 4.89 t/s 12.28.376.356 I slot print_timing: id 1 | task 1737 | n_gen = 115, tg = 4.56 t/s, tg_3s = 4.89 t/s 12.28.990.126 I slot print_timing: id 0 | task 1756 | n_gen = 100, tg = 4.89 t/s, tg_3s = 4.94 t/s 12.29.809.223 I slot print_timing: id 2 | task 1618 | n_gen = 239, tg = 4.40 t/s, tg_3s = 4.89 t/s 12.30.423.569 I slot print_timing: id 3 | task 1671 | n_gen = 190, tg = 4.46 t/s, tg_3s = 4.89 t/s 12.31.446.973 I slot print_timing: id 1 | task 1737 | n_gen = 130, tg = 4.60 t/s, tg_3s = 4.89 t/s 12.32.061.292 I slot print_timing: id 0 | task 1756 | n_gen = 115, tg = 4.89 t/s, tg_3s = 4.88 t/s 12.32.880.684 I slot print_timing: id 2 | task 1618 | n_gen = 254, tg = 4.43 t/s, tg_3s = 4.88 t/s 12.33.495.072 I slot print_timing: id 3 | task 1671 | n_gen = 205, tg = 4.49 t/s, tg_3s = 4.88 t/s 12.34.518.540 I slot print_timing: id 1 | task 1737 | n_gen = 145, tg = 4.63 t/s, tg_3s = 4.88 t/s 12.35.135.082 I slot print_timing: id 0 | task 1756 | n_gen = 130, tg = 4.89 t/s, tg_3s = 4.88 t/s 12.35.954.481 I slot print_timing: id 2 | task 1618 | n_gen = 269, tg = 4.45 t/s, tg_3s = 4.88 t/s 12.36.568.559 I slot print_timing: id 3 | task 1671 | n_gen = 220, tg = 4.51 t/s, tg_3s = 4.88 t/s 12.37.592.011 I slot print_timing: id 1 | task 1737 | n_gen = 160, tg = 4.65 t/s, tg_3s = 4.88 t/s 12.38.206.174 I slot print_timing: id 0 | task 1756 | n_gen = 145, tg = 4.89 t/s, tg_3s = 4.88 t/s 12.39.025.112 I slot print_timing: id 2 | task 1618 | n_gen = 284, tg = 4.47 t/s, tg_3s = 4.88 t/s 12.39.639.664 I slot print_timing: id 3 | task 1671 | n_gen = 235, tg = 4.54 t/s, tg_3s = 4.88 t/s 12.40.662.926 I slot print_timing: id 1 | task 1737 | n_gen = 175, tg = 4.67 t/s, tg_3s = 4.88 t/s 12.41.276.963 I slot print_timing: id 0 | task 1756 | n_gen = 160, tg = 4.89 t/s, tg_3s = 4.88 t/s 12.42.096.396 I slot print_timing: id 2 | task 1618 | n_gen = 299, tg = 4.49 t/s, tg_3s = 4.88 t/s 12.42.710.666 I slot print_timing: id 3 | task 1671 | n_gen = 250, tg = 4.56 t/s, tg_3s = 4.88 t/s 12.43.734.194 I slot print_timing: id 1 | task 1737 | n_gen = 190, tg = 4.69 t/s, tg_3s = 4.88 t/s 12.44.348.780 I slot print_timing: id 0 | task 1756 | n_gen = 175, tg = 4.89 t/s, tg_3s = 4.88 t/s 12.45.168.179 I slot print_timing: id 2 | task 1618 | n_gen = 314, tg = 4.51 t/s, tg_3s = 4.88 t/s 12.45.782.641 I slot print_timing: id 3 | task 1671 | n_gen = 265, tg = 4.57 t/s, tg_3s = 4.88 t/s 12.46.806.087 I slot print_timing: id 1 | task 1737 | n_gen = 205, tg = 4.70 t/s, tg_3s = 4.88 t/s 12.47.420.400 I slot print_timing: id 0 | task 1756 | n_gen = 190, tg = 4.89 t/s, tg_3s = 4.88 t/s 12.48.239.751 I slot print_timing: id 2 | task 1618 | n_gen = 329, tg = 4.52 t/s, tg_3s = 4.88 t/s 12.48.854.309 I slot print_timing: id 3 | task 1671 | n_gen = 280, tg = 4.59 t/s, tg_3s = 4.88 t/s 12.49.877.903 I slot print_timing: id 1 | task 1737 | n_gen = 220, tg = 4.71 t/s, tg_3s = 4.88 t/s 12.50.491.990 I slot print_timing: id 0 | task 1756 | n_gen = 205, tg = 4.89 t/s, tg_3s = 4.88 t/s 12.51.310.831 I slot print_timing: id 2 | task 1618 | n_gen = 344, tg = 4.54 t/s, tg_3s = 4.88 t/s 12.51.925.596 I slot print_timing: id 3 | task 1671 | n_gen = 295, tg = 4.60 t/s, tg_3s = 4.88 t/s 12.52.949.781 I slot print_timing: id 1 | task 1737 | n_gen = 235, tg = 4.72 t/s, tg_3s = 4.88 t/s 12.53.564.518 I slot print_timing: id 0 | task 1756 | n_gen = 220, tg = 4.89 t/s, tg_3s = 4.88 t/s 12.54.384.396 I slot print_timing: id 2 | task 1618 | n_gen = 359, tg = 4.55 t/s, tg_3s = 4.88 t/s 12.54.998.962 I slot print_timing: id 3 | task 1671 | n_gen = 310, tg = 4.62 t/s, tg_3s = 4.88 t/s 12.56.022.621 I slot print_timing: id 1 | task 1737 | n_gen = 250, tg = 4.73 t/s, tg_3s = 4.88 t/s 12.56.636.927 I slot print_timing: id 0 | task 1756 | n_gen = 235, tg = 4.89 t/s, tg_3s = 4.88 t/s 12.57.250.508 I slot print_timing: id 1 | task 1737 | prompt eval time = 2380.32 ms / 117 tokens ( 20.34 ms per token, 49.15 tokens per second) 12.57.250.511 I slot print_timing: id 1 | task 1737 | eval time = 53847.65 ms / 256 tokens ( 211.17 ms per token, 4.74 tokens per second) 12.57.250.512 I slot print_timing: id 1 | task 1737 | total time = 56227.97 ms / 373 tokens 12.57.250.512 I slot print_timing: id 1 | task 1737 | graphs reused = 1543 12.57.250.513 I slot print_timing: id 1 | task 1737 | graph reallocs = 0 / 0 (same size) / (changed size) 12.57.250.556 I slot release: id 1 | task 1737 | stop processing: n_tokens = 1497, truncated = 0 12.57.530.665 I slot print_timing: id 2 | task 1618 | n_gen = 374, tg = 4.56 t/s, tg_3s = 4.77 t/s 12.57.530.816 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.766 12.57.530.851 I slot launch_slot_: id 1 | task 1997 | processing task, is_child = 0 12.59.729.477 I slot print_timing: id 0 | task 1756 | n_gen = 240, tg = 4.69 t/s, tg_3s = 1.62 t/s 12.59.729.841 I slot print_timing: id 3 | task 1671 | n_gen = 323, tg = 4.49 t/s, tg_3s = 2.75 t/s 13.00.675.861 I slot print_timing: id 2 | task 1618 | n_gen = 378, tg = 4.44 t/s, tg_3s = 1.27 t/s 13.02.927.834 I slot print_timing: id 0 | task 1756 | n_gen = 254, tg = 4.67 t/s, tg_3s = 4.38 t/s 13.02.928.273 I slot print_timing: id 3 | task 1671 | n_gen = 337, tg = 4.49 t/s, tg_3s = 4.38 t/s 13.03.747.340 I slot print_timing: id 2 | task 1618 | n_gen = 393, tg = 4.45 t/s, tg_3s = 4.88 t/s 13.04.157.026 I slot print_timing: id 2 | task 1618 | prompt eval time = 2616.19 ms / 149 tokens ( 17.56 ms per token, 56.95 tokens per second) 13.04.157.031 I slot print_timing: id 2 | task 1618 | eval time = 88414.83 ms / 395 tokens ( 224.40 ms per token, 4.46 tokens per second) 13.04.157.032 I slot print_timing: id 2 | task 1618 | total time = 91031.01 ms / 544 tokens 13.04.157.033 I slot print_timing: id 2 | task 1618 | graphs reused = 1561 13.04.157.033 I slot print_timing: id 2 | task 1618 | graph reallocs = 0 / 0 (same size) / (changed size) 13.04.157.080 I slot release: id 2 | task 1618 | stop processing: n_tokens = 1668, truncated = 0 13.04.436.737 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.687 13.04.436.770 I slot launch_slot_: id 2 | task 2020 | processing task, is_child = 0 13.06.364.639 I slot print_timing: id 0 | task 1756 | n_gen = 263, tg = 4.55 t/s, tg_3s = 2.62 t/s 13.06.365.198 I slot print_timing: id 3 | task 1671 | n_gen = 346, tg = 4.41 t/s, tg_3s = 2.62 t/s 13.09.436.494 I slot print_timing: id 0 | task 1756 | n_gen = 278, tg = 4.56 t/s, tg_3s = 4.88 t/s 13.09.436.903 I slot print_timing: id 3 | task 1671 | n_gen = 361, tg = 4.42 t/s, tg_3s = 4.88 t/s 13.12.506.502 I slot print_timing: id 0 | task 1756 | n_gen = 293, tg = 4.58 t/s, tg_3s = 4.89 t/s 13.12.506.924 I slot print_timing: id 3 | task 1671 | n_gen = 376, tg = 4.44 t/s, tg_3s = 4.89 t/s 13.15.577.213 I slot print_timing: id 0 | task 1756 | n_gen = 308, tg = 4.59 t/s, tg_3s = 4.88 t/s 13.15.577.649 I slot print_timing: id 3 | task 1671 | n_gen = 391, tg = 4.46 t/s, tg_3s = 4.88 t/s 13.18.647.394 I slot print_timing: id 0 | task 1756 | n_gen = 323, tg = 4.61 t/s, tg_3s = 4.89 t/s 13.18.647.823 I slot print_timing: id 3 | task 1671 | n_gen = 406, tg = 4.47 t/s, tg_3s = 4.89 t/s 13.20.899.450 I slot print_timing: id 0 | task 1756 | prompt eval time = 2067.70 ms / 127 tokens ( 16.28 ms per token, 61.42 tokens per second) 13.20.899.455 I slot print_timing: id 0 | task 1756 | eval time = 72163.25 ms / 334 tokens ( 216.71 ms per token, 4.61 tokens per second) 13.20.899.456 I slot print_timing: id 0 | task 1756 | total time = 74230.95 ms / 461 tokens 13.20.899.457 I slot print_timing: id 0 | task 1756 | graphs reused = 1631 13.20.899.457 I slot print_timing: id 0 | task 1756 | graph reallocs = 0 / 0 (same size) / (changed size) 13.20.899.504 I slot release: id 0 | task 1756 | stop processing: n_tokens = 1585, truncated = 0 13.21.093.988 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.723 13.21.094.027 I slot launch_slot_: id 0 | task 2095 | processing task, is_child = 0 13.22.764.782 I slot print_timing: id 3 | task 1671 | n_gen = 419, tg = 4.41 t/s, tg_3s = 3.16 t/s 13.23.756.783 I slot print_timing: id 1 | task 1997 | n_gen = 100, tg = 4.21 t/s, tg_3s = 4.26 t/s 13.25.394.269 I slot print_timing: id 3 | task 1671 | prompt eval time = 2097.89 ms / 131 tokens ( 16.01 ms per token, 62.44 tokens per second) 13.25.394.271 I slot print_timing: id 3 | task 1671 | eval time = 97331.91 ms / 431 tokens ( 226.35 ms per token, 4.42 tokens per second) 13.25.394.272 I slot print_timing: id 3 | task 1671 | total time = 99429.79 ms / 562 tokens 13.25.394.272 I slot print_timing: id 3 | task 1671 | graphs reused = 1642 13.25.394.273 I slot print_timing: id 3 | task 1671 | graph reallocs = 0 / 0 (same size) / (changed size) 13.25.394.321 I slot release: id 3 | task 1671 | stop processing: n_tokens = 1686, truncated = 0 13.25.589.139 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.680 13.25.589.174 I slot launch_slot_: id 3 | task 2110 | processing task, is_child = 0 13.26.962.374 I slot print_timing: id 1 | task 1997 | n_gen = 110, tg = 4.08 t/s, tg_3s = 3.12 t/s 13.29.598.619 I slot print_timing: id 2 | task 2020 | n_gen = 100, tg = 4.26 t/s, tg_3s = 4.30 t/s 13.30.007.390 I slot print_timing: id 1 | task 1997 | n_gen = 124, tg = 4.14 t/s, tg_3s = 4.60 t/s 13.32.665.565 I slot print_timing: id 2 | task 2020 | n_gen = 115, tg = 4.33 t/s, tg_3s = 4.89 t/s 13.33.074.143 I slot print_timing: id 1 | task 1997 | n_gen = 139, tg = 4.21 t/s, tg_3s = 4.89 t/s 13.35.730.824 I slot print_timing: id 2 | task 2020 | n_gen = 130, tg = 4.39 t/s, tg_3s = 4.89 t/s 13.36.139.774 I slot print_timing: id 1 | task 1997 | n_gen = 154, tg = 4.26 t/s, tg_3s = 4.89 t/s 13.37.776.251 I slot print_timing: id 1 | task 1997 | prompt eval time = 2732.79 ms / 137 tokens ( 19.95 ms per token, 50.13 tokens per second) 13.37.776.256 I slot print_timing: id 1 | task 1997 | eval time = 37512.60 ms / 162 tokens ( 233.00 ms per token, 4.29 tokens per second) 13.37.776.257 I slot print_timing: id 1 | task 1997 | total time = 40245.39 ms / 299 tokens 13.37.776.257 I slot print_timing: id 1 | task 1997 | graphs reused = 1692 13.37.776.257 I slot print_timing: id 1 | task 1997 | graph reallocs = 0 / 0 (same size) / (changed size) 13.37.776.308 I slot release: id 1 | task 1997 | stop processing: n_tokens = 1423, truncated = 0 13.38.056.571 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.805 13.38.056.603 I slot launch_slot_: id 1 | task 2165 | processing task, is_child = 0 13.39.888.917 I slot print_timing: id 2 | task 2020 | n_gen = 142, tg = 4.21 t/s, tg_3s = 2.89 t/s 13.43.081.403 I slot print_timing: id 2 | task 2020 | n_gen = 156, tg = 4.22 t/s, tg_3s = 4.39 t/s 13.44.307.616 I slot print_timing: id 0 | task 2095 | prompt eval time = 2046.15 ms / 104 tokens ( 19.67 ms per token, 50.83 tokens per second) 13.44.307.621 I slot print_timing: id 0 | task 2095 | eval time = 21167.44 ms / 88 tokens ( 243.30 ms per token, 4.11 tokens per second) 13.44.307.622 I slot print_timing: id 0 | task 2095 | total time = 23213.58 ms / 192 tokens 13.44.307.622 I slot print_timing: id 0 | task 2095 | graphs reused = 1710 13.44.307.623 I slot print_timing: id 0 | task 2095 | graph reallocs = 0 / 0 (same size) / (changed size) 13.44.307.665 I slot release: id 0 | task 2095 | stop processing: n_tokens = 1316, truncated = 0 13.44.502.384 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.871 13.44.502.414 I slot launch_slot_: id 0 | task 2188 | processing task, is_child = 0 13.46.176.600 I slot print_timing: id 2 | task 2020 | n_gen = 164, tg = 4.09 t/s, tg_3s = 2.58 t/s 13.49.211.667 I slot print_timing: id 2 | task 2020 | n_gen = 178, tg = 4.13 t/s, tg_3s = 4.61 t/s 13.49.416.322 I slot print_timing: id 3 | task 2110 | prompt eval time = 1758.23 ms / 98 tokens ( 17.94 ms per token, 55.74 tokens per second) 13.49.416.327 I slot print_timing: id 3 | task 2110 | eval time = 22068.91 ms / 91 tokens ( 245.21 ms per token, 4.08 tokens per second) 13.49.416.327 I slot print_timing: id 3 | task 2110 | total time = 23827.14 ms / 189 tokens 13.49.416.328 I slot print_timing: id 3 | task 2110 | graphs reused = 1724 13.49.416.328 I slot print_timing: id 3 | task 2110 | graph reallocs = 0 / 0 (same size) / (changed size) 13.49.416.375 I slot release: id 3 | task 2110 | stop processing: n_tokens = 1313, truncated = 0 13.49.610.433 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.873 13.49.610.463 I slot launch_slot_: id 3 | task 2206 | processing task, is_child = 0 13.52.311.892 I slot print_timing: id 2 | task 2020 | n_gen = 185, tg = 4.00 t/s, tg_3s = 2.26 t/s 13.55.378.432 I slot print_timing: id 2 | task 2020 | n_gen = 200, tg = 4.06 t/s, tg_3s = 4.89 t/s 13.57.218.235 I slot print_timing: id 2 | task 2020 | prompt eval time = 1928.28 ms / 96 tokens ( 20.09 ms per token, 49.79 tokens per second) 13.57.218.238 I slot print_timing: id 2 | task 2020 | eval time = 50853.18 ms / 209 tokens ( 244.49 ms per token, 4.09 tokens per second) 13.57.218.239 I slot print_timing: id 2 | task 2020 | total time = 52781.46 ms / 305 tokens 13.57.218.239 I slot print_timing: id 2 | task 2020 | graphs reused = 1750 13.57.218.240 I slot print_timing: id 2 | task 2020 | graph reallocs = 0 / 0 (same size) / (changed size) 13.57.218.281 I slot release: id 2 | task 2020 | stop processing: n_tokens = 1429, truncated = 0 13.57.498.125 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.918 (> 0.100 thold), f_keep = 0.802 13.57.498.162 I slot launch_slot_: id 2 | task 2237 | processing task, is_child = 0 13.59.966.019 I slot print_timing: id 1 | task 2165 | prompt eval time = 2364.91 ms / 102 tokens ( 23.19 ms per token, 43.13 tokens per second) 13.59.966.024 I slot print_timing: id 1 | task 2165 | eval time = 19544.50 ms / 71 tokens ( 279.21 ms per token, 3.58 tokens per second) 13.59.966.024 I slot print_timing: id 1 | task 2165 | total time = 21909.41 ms / 173 tokens 13.59.966.025 I slot print_timing: id 1 | task 2165 | graphs reused = 1750 13.59.966.025 I slot print_timing: id 1 | task 2165 | graph reallocs = 0 / 0 (same size) / (changed size) 13.59.966.069 I slot release: id 1 | task 2165 | stop processing: n_tokens = 1297, truncated = 0 14.00.245.596 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.884 14.00.245.630 I slot launch_slot_: id 1 | task 2242 | processing task, is_child = 0 14.12.434.909 I slot print_timing: id 0 | task 2188 | n_gen = 100, tg = 3.82 t/s, tg_3s = 3.86 t/s 14.13.866.136 I slot print_timing: id 0 | task 2188 | prompt eval time = 2048.20 ms / 108 tokens ( 18.96 ms per token, 52.73 tokens per second) 14.13.866.140 I slot print_timing: id 0 | task 2188 | eval time = 27315.51 ms / 107 tokens ( 257.69 ms per token, 3.88 tokens per second) 14.13.866.141 I slot print_timing: id 0 | task 2188 | total time = 29363.71 ms / 215 tokens 14.13.866.142 I slot print_timing: id 0 | task 2188 | graphs reused = 1804 14.13.866.142 I slot print_timing: id 0 | task 2188 | graph reallocs = 0 / 0 (same size) / (changed size) 14.13.866.191 I slot release: id 0 | task 2188 | stop processing: n_tokens = 1339, truncated = 0 14.14.060.945 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.856 14.14.060.991 I slot launch_slot_: id 0 | task 2301 | processing task, is_child = 0 14.17.218.153 I slot print_timing: id 3 | task 2206 | n_gen = 100, tg = 3.88 t/s, tg_3s = 3.92 t/s 14.19.262.485 I slot print_timing: id 3 | task 2206 | prompt eval time = 2086.59 ms / 122 tokens ( 17.10 ms per token, 58.47 tokens per second) 14.19.262.488 I slot print_timing: id 3 | task 2206 | eval time = 27565.42 ms / 110 tokens ( 252.89 ms per token, 3.95 tokens per second) 14.19.262.488 I slot print_timing: id 3 | task 2206 | total time = 29652.01 ms / 232 tokens 14.19.262.489 I slot print_timing: id 3 | task 2206 | graphs reused = 1821 14.19.262.489 I slot print_timing: id 3 | task 2206 | graph reallocs = 0 / 0 (same size) / (changed size) 14.19.262.543 I slot release: id 3 | task 2206 | stop processing: n_tokens = 1356, truncated = 0 14.19.456.704 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.931 (> 0.100 thold), f_keep = 0.845 14.19.456.736 I slot launch_slot_: id 3 | task 2322 | processing task, is_child = 0 14.22.759.066 I slot print_timing: id 2 | task 2237 | prompt eval time = 2261.16 ms / 124 tokens ( 18.24 ms per token, 54.84 tokens per second) 14.22.759.071 I slot print_timing: id 2 | task 2237 | eval time = 22999.74 ms / 89 tokens ( 261.36 ms per token, 3.83 tokens per second) 14.22.759.072 I slot print_timing: id 2 | task 2237 | total time = 25260.90 ms / 213 tokens 14.22.759.072 I slot print_timing: id 2 | task 2237 | graphs reused = 1826 14.22.759.073 I slot print_timing: id 2 | task 2237 | graph reallocs = 0 / 0 (same size) / (changed size) 14.22.759.117 I slot release: id 2 | task 2237 | stop processing: n_tokens = 1337, truncated = 0 14.23.037.660 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.857 14.23.037.701 I slot launch_slot_: id 2 | task 2332 | processing task, is_child = 0 14.27.420.200 I slot print_timing: id 1 | task 2242 | n_gen = 100, tg = 3.99 t/s, tg_3s = 4.03 t/s 14.30.075.955 I slot print_timing: id 0 | task 2301 | prompt eval time = 1723.76 ms / 86 tokens ( 20.04 ms per token, 49.89 tokens per second) 14.30.075.960 I slot print_timing: id 0 | task 2301 | eval time = 14291.20 ms / 55 tokens ( 264.65 ms per token, 3.78 tokens per second) 14.30.075.960 I slot print_timing: id 0 | task 2301 | total time = 16014.95 ms / 141 tokens 14.30.075.961 I slot print_timing: id 0 | task 2301 | graphs reused = 1850 14.30.075.961 I slot print_timing: id 0 | task 2301 | graph reallocs = 0 / 0 (same size) / (changed size) 14.30.076.002 I slot release: id 0 | task 2301 | stop processing: n_tokens = 1265, truncated = 0 14.30.270.233 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.942 (> 0.100 thold), f_keep = 0.906 14.30.270.266 I slot launch_slot_: id 0 | task 2361 | processing task, is_child = 0 14.31.623.678 I slot print_timing: id 1 | task 2242 | n_gen = 115, tg = 3.93 t/s, tg_3s = 3.57 t/s 14.34.248.454 I slot print_timing: id 1 | task 2242 | prompt eval time = 2374.66 ms / 111 tokens ( 21.39 ms per token, 46.74 tokens per second) 14.34.248.460 I slot print_timing: id 1 | task 2242 | eval time = 31628.15 ms / 127 tokens ( 251.02 ms per token, 3.98 tokens per second) 14.34.248.460 I slot print_timing: id 1 | task 2242 | total time = 34002.81 ms / 238 tokens 14.34.248.461 I slot print_timing: id 1 | task 2242 | graphs reused = 1861 14.34.248.461 I slot print_timing: id 1 | task 2242 | graph reallocs = 0 / 0 (same size) / (changed size) 14.34.248.504 I slot release: id 1 | task 2242 | stop processing: n_tokens = 1362, truncated = 0 14.34.528.309 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.841 14.34.528.348 I slot launch_slot_: id 1 | task 2376 | processing task, is_child = 0 14.46.718.043 I slot print_timing: id 3 | task 2322 | n_gen = 100, tg = 3.93 t/s, tg_3s = 3.97 t/s 14.48.557.777 I slot print_timing: id 2 | task 2332 | n_gen = 100, tg = 4.20 t/s, tg_3s = 4.24 t/s 14.49.784.556 I slot print_timing: id 3 | task 2322 | n_gen = 115, tg = 4.03 t/s, tg_3s = 4.89 t/s 14.51.418.639 I slot print_timing: id 1 | task 2376 | prompt eval time = 2379.74 ms / 121 tokens ( 19.67 ms per token, 50.85 tokens per second) 14.51.418.645 I slot print_timing: id 1 | task 2376 | eval time = 14510.55 ms / 72 tokens ( 204.37 ms per token, 4.89 tokens per second) 14.51.418.646 I slot print_timing: id 1 | task 2376 | total time = 16890.28 ms / 193 tokens 14.51.418.647 I slot print_timing: id 1 | task 2376 | graphs reused = 1931 14.51.418.647 I slot print_timing: id 1 | task 2376 | graph reallocs = 0 / 0 (same size) / (changed size) 14.51.418.699 I slot release: id 1 | task 2376 | stop processing: n_tokens = 1317, truncated = 0 14.51.698.173 I slot print_timing: id 2 | task 2332 | n_gen = 115, tg = 4.26 t/s, tg_3s = 4.78 t/s 14.51.698.328 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.870 14.51.698.360 I slot launch_slot_: id 1 | task 2451 | processing task, is_child = 0 14.53.532.284 I slot print_timing: id 3 | task 2322 | n_gen = 125, tg = 3.87 t/s, tg_3s = 2.67 t/s 14.54.885.405 I slot print_timing: id 2 | task 2332 | n_gen = 121, tg = 4.01 t/s, tg_3s = 1.88 t/s 14.55.498.408 I slot print_timing: id 0 | task 2361 | prompt eval time = 1727.69 ms / 91 tokens ( 18.99 ms per token, 52.67 tokens per second) 14.55.498.413 I slot print_timing: id 0 | task 2361 | eval time = 23500.44 ms / 96 tokens ( 247.37 ms per token, 4.04 tokens per second) 14.55.498.414 I slot print_timing: id 0 | task 2361 | total time = 25228.13 ms / 187 tokens 14.55.498.414 I slot print_timing: id 0 | task 2361 | graphs reused = 1937 14.55.498.415 I slot print_timing: id 0 | task 2361 | graph reallocs = 0 / 0 (same size) / (changed size) 14.55.498.461 I slot release: id 0 | task 2361 | stop processing: n_tokens = 1311, truncated = 0 14.55.692.842 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.874 14.55.692.876 I slot launch_slot_: id 0 | task 2462 | processing task, is_child = 0 14.57.050.301 I slot print_timing: id 3 | task 2322 | n_gen = 135, tg = 3.77 t/s, tg_3s = 2.84 t/s 14.57.631.374 I slot print_timing: id 2 | task 2332 | prompt eval time = 1928.06 ms / 98 tokens ( 19.67 ms per token, 50.83 tokens per second) 14.57.631.380 I slot print_timing: id 2 | task 2332 | eval time = 32665.60 ms / 128 tokens ( 257.21 ms per token, 3.89 tokens per second) 14.57.631.380 I slot print_timing: id 2 | task 2332 | total time = 34593.67 ms / 226 tokens 14.57.631.380 I slot print_timing: id 2 | task 2332 | graphs reused = 1938 14.57.631.381 I slot print_timing: id 2 | task 2332 | graph reallocs = 0 / 0 (same size) / (changed size) 14.57.631.425 I slot release: id 2 | task 2332 | stop processing: n_tokens = 1350, truncated = 0 14.57.910.156 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.849 14.57.910.194 I slot launch_slot_: id 2 | task 2467 | processing task, is_child = 0 15.00.053.558 I slot print_timing: id 3 | task 2322 | n_gen = 139, tg = 3.58 t/s, tg_3s = 1.33 t/s 15.03.184.930 I slot print_timing: id 3 | task 2322 | n_gen = 153, tg = 3.65 t/s, tg_3s = 4.47 t/s 15.06.249.233 I slot print_timing: id 3 | task 2322 | n_gen = 168, tg = 3.73 t/s, tg_3s = 4.90 t/s 15.09.316.010 I slot print_timing: id 3 | task 2322 | n_gen = 183, tg = 3.81 t/s, tg_3s = 4.89 t/s 15.12.382.112 I slot print_timing: id 3 | task 2322 | n_gen = 198, tg = 3.87 t/s, tg_3s = 4.89 t/s 15.14.835.770 I slot print_timing: id 1 | task 2451 | prompt eval time = 2366.47 ms / 105 tokens ( 22.54 ms per token, 44.37 tokens per second) 15.14.835.773 I slot print_timing: id 1 | task 2451 | eval time = 20770.93 ms / 85 tokens ( 247.27 ms per token, 4.04 tokens per second) 15.14.835.773 I slot print_timing: id 1 | task 2451 | total time = 23137.40 ms / 190 tokens 15.14.835.774 I slot print_timing: id 1 | task 2451 | graphs reused = 2007 15.14.835.774 I slot print_timing: id 1 | task 2451 | graph reallocs = 0 / 0 (same size) / (changed size) 15.14.835.828 I slot release: id 1 | task 2451 | stop processing: n_tokens = 1314, truncated = 0 15.15.115.582 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.872 15.15.115.621 I slot launch_slot_: id 1 | task 2541 | processing task, is_child = 0 15.16.952.119 I slot print_timing: id 3 | task 2322 | n_gen = 212, tg = 3.81 t/s, tg_3s = 3.06 t/s 15.20.145.352 I slot print_timing: id 3 | task 2322 | n_gen = 226, tg = 3.84 t/s, tg_3s = 4.38 t/s 15.20.759.133 I slot print_timing: id 3 | task 2322 | prompt eval time = 2074.45 ms / 106 tokens ( 19.57 ms per token, 51.10 tokens per second) 15.20.759.138 I slot print_timing: id 3 | task 2322 | eval time = 59227.94 ms / 229 tokens ( 259.77 ms per token, 3.85 tokens per second) 15.20.759.138 I slot print_timing: id 3 | task 2322 | total time = 61302.39 ms / 335 tokens 15.20.759.139 I slot print_timing: id 3 | task 2322 | graphs reused = 2022 15.20.759.139 I slot print_timing: id 3 | task 2322 | graph reallocs = 0 / 0 (same size) / (changed size) 15.20.759.191 I slot release: id 3 | task 2322 | stop processing: n_tokens = 1459, truncated = 0 15.20.952.368 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.893 (> 0.100 thold), f_keep = 0.785 15.20.952.411 I slot launch_slot_: id 3 | task 2561 | processing task, is_child = 0 15.23.816.327 I slot print_timing: id 0 | task 2462 | prompt eval time = 1731.51 ms / 95 tokens ( 18.23 ms per token, 54.87 tokens per second) 15.23.816.333 I slot print_timing: id 0 | task 2462 | eval time = 26391.94 ms / 99 tokens ( 269.31 ms per token, 3.71 tokens per second) 15.23.816.334 I slot print_timing: id 0 | task 2462 | total time = 28123.45 ms / 194 tokens 15.23.816.334 I slot print_timing: id 0 | task 2462 | graphs reused = 2023 15.23.816.335 I slot print_timing: id 0 | task 2462 | graph reallocs = 0 / 0 (same size) / (changed size) 15.23.816.384 I slot release: id 0 | task 2462 | stop processing: n_tokens = 1318, truncated = 0 15.24.009.890 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.924 (> 0.100 thold), f_keep = 0.869 15.24.009.927 I slot launch_slot_: id 0 | task 2567 | processing task, is_child = 0 15.26.477.813 I slot print_timing: id 2 | task 2467 | n_gen = 100, tg = 3.81 t/s, tg_3s = 3.85 t/s 15.29.543.552 I slot print_timing: id 2 | task 2467 | n_gen = 115, tg = 3.93 t/s, tg_3s = 4.89 t/s 15.32.609.899 I slot print_timing: id 2 | task 2467 | n_gen = 130, tg = 4.02 t/s, tg_3s = 4.89 t/s 15.35.676.750 I slot print_timing: id 2 | task 2467 | n_gen = 145, tg = 4.10 t/s, tg_3s = 4.89 t/s 15.38.743.113 I slot print_timing: id 2 | task 2467 | n_gen = 160, tg = 4.16 t/s, tg_3s = 4.89 t/s 15.41.400.327 I slot print_timing: id 1 | task 2541 | n_gen = 100, tg = 4.14 t/s, tg_3s = 4.18 t/s 15.41.809.611 I slot print_timing: id 2 | task 2467 | n_gen = 175, tg = 4.21 t/s, tg_3s = 4.89 t/s 15.44.467.389 I slot print_timing: id 1 | task 2541 | n_gen = 115, tg = 4.22 t/s, tg_3s = 4.89 t/s 15.44.876.499 I slot print_timing: id 2 | task 2467 | n_gen = 190, tg = 4.26 t/s, tg_3s = 4.89 t/s 15.45.285.382 I slot print_timing: id 3 | task 2561 | n_gen = 100, tg = 4.52 t/s, tg_3s = 4.57 t/s 15.46.306.392 I slot print_timing: id 0 | task 2567 | n_gen = 100, tg = 4.89 t/s, tg_3s = 4.94 t/s 15.47.533.963 I slot print_timing: id 1 | task 2541 | n_gen = 130, tg = 4.29 t/s, tg_3s = 4.89 t/s 15.47.943.369 I slot print_timing: id 2 | task 2467 | n_gen = 205, tg = 4.30 t/s, tg_3s = 4.89 t/s 15.48.352.326 I slot print_timing: id 3 | task 2561 | n_gen = 115, tg = 4.57 t/s, tg_3s = 4.89 t/s 15.49.374.523 I slot print_timing: id 0 | task 2567 | n_gen = 115, tg = 4.89 t/s, tg_3s = 4.89 t/s 15.49.784.021 I slot print_timing: id 1 | task 2541 | prompt eval time = 2368.87 ms / 110 tokens ( 21.54 ms per token, 46.44 tokens per second) 15.49.784.024 I slot print_timing: id 1 | task 2541 | eval time = 32299.53 ms / 141 tokens ( 230.71 ms per token, 4.33 tokens per second) 15.49.784.024 I slot print_timing: id 1 | task 2541 | total time = 34668.39 ms / 251 tokens 15.49.784.025 I slot print_timing: id 1 | task 2541 | graphs reused = 2139 15.49.784.025 I slot print_timing: id 1 | task 2541 | graph reallocs = 0 / 0 (same size) / (changed size) 15.49.784.072 I slot release: id 1 | task 2541 | stop processing: n_tokens = 1375, truncated = 0 15.50.063.392 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.833 15.50.063.431 I slot launch_slot_: id 1 | task 2687 | processing task, is_child = 0 15.51.917.567 I slot print_timing: id 2 | task 2467 | n_gen = 216, tg = 4.18 t/s, tg_3s = 2.77 t/s 15.51.917.762 I slot print_timing: id 3 | task 2561 | n_gen = 124, tg = 4.31 t/s, tg_3s = 2.52 t/s 15.52.451.198 I slot print_timing: id 0 | task 2567 | n_gen = 120, tg = 4.51 t/s, tg_3s = 1.63 t/s 15.55.112.373 I slot print_timing: id 2 | task 2467 | n_gen = 230, tg = 4.20 t/s, tg_3s = 4.38 t/s 15.55.112.531 I slot print_timing: id 3 | task 2561 | n_gen = 138, tg = 4.32 t/s, tg_3s = 4.38 t/s 15.55.521.478 I slot print_timing: id 0 | task 2567 | n_gen = 135, tg = 4.55 t/s, tg_3s = 4.89 t/s 15.58.180.123 I slot print_timing: id 2 | task 2467 | n_gen = 245, tg = 4.23 t/s, tg_3s = 4.89 t/s 15.58.180.282 I slot print_timing: id 3 | task 2561 | n_gen = 153, tg = 4.37 t/s, tg_3s = 4.89 t/s 15.58.589.412 I slot print_timing: id 0 | task 2567 | n_gen = 150, tg = 4.58 t/s, tg_3s = 4.89 t/s 16.01.250.078 I slot print_timing: id 2 | task 2467 | n_gen = 260, tg = 4.27 t/s, tg_3s = 4.89 t/s 16.01.250.221 I slot print_timing: id 3 | task 2561 | n_gen = 168, tg = 4.41 t/s, tg_3s = 4.89 t/s 16.01.454.572 I slot print_timing: id 0 | task 2567 | prompt eval time = 2055.59 ms / 115 tokens ( 17.87 ms per token, 55.94 tokens per second) 16.01.454.577 I slot print_timing: id 0 | task 2567 | eval time = 35389.05 ms / 164 tokens ( 217.11 ms per token, 4.61 tokens per second) 16.01.454.578 I slot print_timing: id 0 | task 2567 | total time = 37444.64 ms / 279 tokens 16.01.454.578 I slot print_timing: id 0 | task 2567 | graphs reused = 2182 16.01.454.579 I slot print_timing: id 0 | task 2567 | graph reallocs = 0 / 0 (same size) / (changed size) 16.01.454.624 I slot release: id 0 | task 2567 | stop processing: n_tokens = 1403, truncated = 0 16.01.649.344 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.950 (> 0.100 thold), f_keep = 0.817 16.01.649.378 I slot launch_slot_: id 0 | task 2735 | processing task, is_child = 0 16.04.396.312 I slot print_timing: id 2 | task 2467 | n_gen = 269, tg = 4.20 t/s, tg_3s = 2.86 t/s 16.04.396.466 I slot print_timing: id 3 | task 2561 | n_gen = 177, tg = 4.29 t/s, tg_3s = 2.86 t/s 16.07.464.062 I slot print_timing: id 2 | task 2467 | n_gen = 284, tg = 4.23 t/s, tg_3s = 4.89 t/s 16.07.464.221 I slot print_timing: id 3 | task 2561 | n_gen = 192, tg = 4.34 t/s, tg_3s = 4.89 t/s 16.09.509.572 I slot print_timing: id 2 | task 2467 | prompt eval time = 2615.71 ms / 144 tokens ( 18.16 ms per token, 55.05 tokens per second) 16.09.509.578 I slot print_timing: id 2 | task 2467 | eval time = 68983.66 ms / 294 tokens ( 235.44 ms per token, 4.25 tokens per second) 16.09.509.578 I slot print_timing: id 2 | task 2467 | total time = 71599.37 ms / 438 tokens 16.09.509.579 I slot print_timing: id 2 | task 2467 | graphs reused = 2211 16.09.509.579 I slot print_timing: id 2 | task 2467 | graph reallocs = 0 / 0 (same size) / (changed size) 16.09.509.627 I slot release: id 2 | task 2467 | stop processing: n_tokens = 1562, truncated = 0 16.09.789.009 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.734 16.09.789.044 I slot launch_slot_: id 2 | task 2769 | processing task, is_child = 0 16.11.559.031 I slot print_timing: id 3 | task 2561 | n_gen = 204, tg = 4.22 t/s, tg_3s = 2.93 t/s 16.14.575.462 I slot print_timing: id 3 | task 2561 | n_gen = 217, tg = 4.22 t/s, tg_3s = 4.31 t/s 16.16.061.394 I slot print_timing: id 1 | task 2687 | n_gen = 100, tg = 4.19 t/s, tg_3s = 4.24 t/s 16.16.918.760 I slot print_timing: id 0 | task 2735 | prompt eval time = 1719.37 ms / 81 tokens ( 21.23 ms per token, 47.11 tokens per second) 16.16.918.772 I slot print_timing: id 0 | task 2735 | eval time = 13549.99 ms / 57 tokens ( 241.96 ms per token, 4.13 tokens per second) 16.16.918.774 I slot print_timing: id 0 | task 2735 | total time = 15269.35 ms / 138 tokens 16.16.918.777 I slot print_timing: id 0 | task 2735 | graphs reused = 2233 16.16.918.785 I slot print_timing: id 0 | task 2735 | graph reallocs = 0 / 0 (same size) / (changed size) 16.16.919.036 I slot release: id 0 | task 2735 | stop processing: n_tokens = 1262, truncated = 0 16.17.123.669 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.908 16.17.123.903 I slot launch_slot_: id 0 | task 2796 | processing task, is_child = 0 16.18.837.526 I slot print_timing: id 3 | task 2561 | n_gen = 230, tg = 4.13 t/s, tg_3s = 3.05 t/s 16.19.224.035 I slot print_timing: id 1 | task 2687 | n_gen = 107, tg = 3.96 t/s, tg_3s = 2.21 t/s 16.22.009.313 I slot print_timing: id 3 | task 2561 | n_gen = 244, tg = 4.15 t/s, tg_3s = 4.41 t/s 16.22.432.087 I slot print_timing: id 1 | task 2687 | n_gen = 122, tg = 4.04 t/s, tg_3s = 4.68 t/s 16.25.217.445 I slot print_timing: id 3 | task 2561 | n_gen = 259, tg = 4.17 t/s, tg_3s = 4.68 t/s 16.25.648.645 I slot print_timing: id 1 | task 2687 | n_gen = 137, tg = 4.10 t/s, tg_3s = 4.66 t/s 16.28.426.927 I slot print_timing: id 3 | task 2561 | n_gen = 274, tg = 4.20 t/s, tg_3s = 4.67 t/s 16.28.845.231 I slot print_timing: id 1 | task 2687 | n_gen = 152, tg = 4.15 t/s, tg_3s = 4.69 t/s 16.30.343.533 I slot print_timing: id 2 | task 2769 | prompt eval time = 2242.00 ms / 104 tokens ( 21.56 ms per token, 46.39 tokens per second) 16.30.343.548 I slot print_timing: id 2 | task 2769 | eval time = 18312.46 ms / 79 tokens ( 234.78 ms per token, 4.26 tokens per second) 16.30.343.550 I slot print_timing: id 2 | task 2769 | total time = 20554.46 ms / 183 tokens 16.30.343.553 I slot print_timing: id 2 | task 2769 | graphs reused = 2284 16.30.343.555 I slot print_timing: id 2 | task 2769 | graph reallocs = 0 / 0 (same size) / (changed size) 16.30.343.770 I slot release: id 2 | task 2769 | stop processing: n_tokens = 1307, truncated = 0 16.30.633.529 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.877 16.30.633.684 I slot launch_slot_: id 2 | task 2852 | processing task, is_child = 0 16.32.422.753 I slot print_timing: id 1 | task 2687 | n_gen = 161, tg = 4.00 t/s, tg_3s = 2.52 t/s 16.32.423.523 I slot print_timing: id 3 | task 2561 | n_gen = 285, tg = 4.11 t/s, tg_3s = 2.75 t/s 16.35.462.912 I slot print_timing: id 1 | task 2687 | n_gen = 174, tg = 4.02 t/s, tg_3s = 4.28 t/s 16.35.464.228 I slot print_timing: id 3 | task 2561 | n_gen = 298, tg = 4.12 t/s, tg_3s = 4.28 t/s 16.38.663.622 I slot print_timing: id 1 | task 2687 | n_gen = 189, tg = 4.07 t/s, tg_3s = 4.69 t/s 16.38.665.235 I slot print_timing: id 3 | task 2561 | n_gen = 313, tg = 4.15 t/s, tg_3s = 4.69 t/s 16.41.875.045 I slot print_timing: id 1 | task 2687 | n_gen = 204, tg = 4.11 t/s, tg_3s = 4.67 t/s 16.41.875.907 I slot print_timing: id 3 | task 2561 | n_gen = 328, tg = 4.17 t/s, tg_3s = 4.67 t/s 16.42.303.435 I slot print_timing: id 0 | task 2796 | n_gen = 100, tg = 4.29 t/s, tg_3s = 4.33 t/s 16.44.019.047 I slot print_timing: id 0 | task 2796 | prompt eval time = 2099.23 ms / 125 tokens ( 16.79 ms per token, 59.55 tokens per second) 16.44.019.052 I slot print_timing: id 0 | task 2796 | eval time = 24795.87 ms / 108 tokens ( 231.74 ms per token, 4.32 tokens per second) 16.44.019.053 I slot print_timing: id 0 | task 2796 | total time = 26895.11 ms / 233 tokens 16.44.019.054 I slot print_timing: id 0 | task 2796 | graphs reused = 2335 16.44.019.055 I slot print_timing: id 0 | task 2796 | graph reallocs = 0 / 0 (same size) / (changed size) 16.44.019.163 I slot release: id 0 | task 2796 | stop processing: n_tokens = 1357, truncated = 0 16.44.221.302 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.916 (> 0.100 thold), f_keep = 0.845 16.44.221.550 I slot launch_slot_: id 0 | task 2908 | processing task, is_child = 0 16.45.929.421 I slot print_timing: id 1 | task 2687 | n_gen = 216, tg = 4.02 t/s, tg_3s = 2.96 t/s 16.45.931.468 I slot print_timing: id 3 | task 2561 | n_gen = 340, tg = 4.11 t/s, tg_3s = 2.96 t/s 16.49.088.456 I slot print_timing: id 1 | task 2687 | n_gen = 230, tg = 4.04 t/s, tg_3s = 4.43 t/s 16.49.090.210 I slot print_timing: id 3 | task 2561 | n_gen = 354, tg = 4.12 t/s, tg_3s = 4.43 t/s 16.52.273.248 I slot print_timing: id 1 | task 2687 | n_gen = 245, tg = 4.08 t/s, tg_3s = 4.71 t/s 16.52.274.941 I slot print_timing: id 3 | task 2561 | n_gen = 369, tg = 4.14 t/s, tg_3s = 4.71 t/s 16.52.487.443 I slot print_timing: id 3 | task 2561 | prompt eval time = 2453.06 ms / 158 tokens ( 15.53 ms per token, 64.41 tokens per second) 16.52.487.463 I slot print_timing: id 3 | task 2561 | eval time = 89081.93 ms / 370 tokens ( 241.41 ms per token, 4.14 tokens per second) 16.52.487.466 I slot print_timing: id 3 | task 2561 | total time = 91534.99 ms / 528 tokens 16.52.487.469 I slot print_timing: id 3 | task 2561 | graphs reused = 2364 16.52.487.472 I slot print_timing: id 3 | task 2561 | graph reallocs = 0 / 0 (same size) / (changed size) 16.52.487.702 I slot release: id 3 | task 2561 | stop processing: n_tokens = 1652, truncated = 0 16.52.691.411 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.694 16.52.691.644 I slot launch_slot_: id 3 | task 2941 | processing task, is_child = 0 16.55.456.578 I slot print_timing: id 1 | task 2687 | n_gen = 252, tg = 3.98 t/s, tg_3s = 2.20 t/s 16.57.378.995 I slot print_timing: id 2 | task 2852 | n_gen = 100, tg = 4.05 t/s, tg_3s = 4.09 t/s 16.58.659.517 I slot print_timing: id 1 | task 2687 | n_gen = 267, tg = 4.02 t/s, tg_3s = 4.68 t/s 17.00.579.708 I slot print_timing: id 2 | task 2852 | n_gen = 115, tg = 4.12 t/s, tg_3s = 4.69 t/s 17.01.859.079 I slot print_timing: id 1 | task 2687 | n_gen = 282, tg = 4.05 t/s, tg_3s = 4.69 t/s 17.03.779.742 I slot print_timing: id 2 | task 2852 | n_gen = 130, tg = 4.18 t/s, tg_3s = 4.69 t/s 17.05.064.956 I slot print_timing: id 1 | task 2687 | n_gen = 297, tg = 4.08 t/s, tg_3s = 4.68 t/s 17.06.990.200 I slot print_timing: id 2 | task 2852 | n_gen = 145, tg = 4.23 t/s, tg_3s = 4.67 t/s 17.07.200.404 I slot print_timing: id 0 | task 2908 | prompt eval time = 2095.88 ms / 126 tokens ( 16.63 ms per token, 60.12 tokens per second) 17.07.200.421 I slot print_timing: id 0 | task 2908 | eval time = 20882.93 ms / 91 tokens ( 232.03 ms per token, 4.31 tokens per second) 17.07.200.424 I slot print_timing: id 0 | task 2908 | total time = 22978.80 ms / 217 tokens 17.07.200.426 I slot print_timing: id 0 | task 2908 | graphs reused = 2420 17.07.200.431 I slot print_timing: id 0 | task 2908 | graph reallocs = 0 / 0 (same size) / (changed size) 17.07.200.654 I slot release: id 0 | task 2908 | stop processing: n_tokens = 1341, truncated = 0 17.07.406.041 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.855 17.07.406.208 I slot launch_slot_: id 0 | task 3003 | processing task, is_child = 0 17.09.097.443 I slot print_timing: id 1 | task 2687 | n_gen = 309, tg = 4.02 t/s, tg_3s = 2.98 t/s 17.10.131.579 I slot print_timing: id 2 | task 2852 | n_gen = 152, tg = 4.06 t/s, tg_3s = 2.23 t/s 17.12.267.082 I slot print_timing: id 1 | task 2687 | n_gen = 323, tg = 4.03 t/s, tg_3s = 4.42 t/s 17.13.336.828 I slot print_timing: id 2 | task 2852 | n_gen = 167, tg = 4.11 t/s, tg_3s = 4.68 t/s 17.15.471.640 I slot print_timing: id 1 | task 2687 | n_gen = 338, tg = 4.06 t/s, tg_3s = 4.68 t/s 17.16.540.320 I slot print_timing: id 2 | task 2852 | n_gen = 182, tg = 4.15 t/s, tg_3s = 4.68 t/s 17.17.618.613 I slot print_timing: id 3 | task 2941 | n_gen = 100, tg = 4.34 t/s, tg_3s = 4.39 t/s 17.18.681.313 I slot print_timing: id 1 | task 2687 | n_gen = 353, tg = 4.08 t/s, tg_3s = 4.67 t/s 17.18.682.134 I slot print_timing: id 2 | task 2852 | prompt eval time = 2274.76 ms / 103 tokens ( 22.09 ms per token, 45.28 tokens per second) 17.18.682.139 I slot print_timing: id 2 | task 2852 | eval time = 45773.66 ms / 192 tokens ( 239.65 ms per token, 4.17 tokens per second) 17.18.682.141 I slot print_timing: id 2 | task 2852 | total time = 48048.42 ms / 295 tokens 17.18.682.143 I slot print_timing: id 2 | task 2852 | graphs reused = 2463 17.18.682.144 I slot print_timing: id 2 | task 2852 | graph reallocs = 0 / 0 (same size) / (changed size) 17.18.682.332 I slot release: id 2 | task 2852 | stop processing: n_tokens = 1419, truncated = 0 17.18.971.301 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.808 17.18.971.483 I slot launch_slot_: id 2 | task 3050 | processing task, is_child = 0 17.20.921.385 I slot print_timing: id 3 | task 2941 | n_gen = 108, tg = 4.10 t/s, tg_3s = 2.42 t/s 17.21.741.790 I slot print_timing: id 1 | task 2687 | n_gen = 360, tg = 4.02 t/s, tg_3s = 2.29 t/s 17.23.992.554 I slot print_timing: id 3 | task 2941 | n_gen = 123, tg = 4.18 t/s, tg_3s = 4.88 t/s 17.24.810.802 I slot print_timing: id 1 | task 2687 | n_gen = 375, tg = 4.05 t/s, tg_3s = 4.89 t/s 17.27.061.379 I slot print_timing: id 3 | task 2941 | n_gen = 138, tg = 4.25 t/s, tg_3s = 4.89 t/s 17.27.879.282 I slot print_timing: id 1 | task 2687 | n_gen = 390, tg = 4.08 t/s, tg_3s = 4.89 t/s 17.30.130.756 I slot print_timing: id 3 | task 2941 | n_gen = 153, tg = 4.30 t/s, tg_3s = 4.89 t/s 17.30.948.648 I slot print_timing: id 0 | task 3003 | prompt eval time = 2079.97 ms / 108 tokens ( 19.26 ms per token, 51.92 tokens per second) 17.30.948.654 I slot print_timing: id 0 | task 3003 | eval time = 21462.44 ms / 96 tokens ( 225.92 ms per token, 4.43 tokens per second) 17.30.948.654 I slot print_timing: id 0 | task 3003 | total time = 23542.42 ms / 204 tokens 17.30.948.655 I slot print_timing: id 0 | task 3003 | graphs reused = 2511 17.30.948.655 I slot print_timing: id 0 | task 3003 | graph reallocs = 0 / 0 (same size) / (changed size) 17.30.948.701 I slot release: id 0 | task 3003 | stop processing: n_tokens = 1328, truncated = 0 17.30.948.850 I slot print_timing: id 1 | task 2687 | n_gen = 405, tg = 4.10 t/s, tg_3s = 4.89 t/s 17.31.143.603 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.863 17.31.143.638 I slot launch_slot_: id 0 | task 3103 | processing task, is_child = 0 17.33.539.628 I slot print_timing: id 3 | task 2941 | n_gen = 159, tg = 4.08 t/s, tg_3s = 1.76 t/s 17.34.124.054 I slot print_timing: id 1 | task 2687 | n_gen = 409, tg = 4.01 t/s, tg_3s = 1.26 t/s 17.36.580.444 I slot print_timing: id 3 | task 2941 | n_gen = 173, tg = 4.12 t/s, tg_3s = 4.60 t/s 17.37.194.057 I slot print_timing: id 1 | task 2687 | n_gen = 424, tg = 4.04 t/s, tg_3s = 4.89 t/s 17.38.217.274 I slot print_timing: id 3 | task 2941 | prompt eval time = 2125.09 ms / 125 tokens ( 17.00 ms per token, 58.82 tokens per second) 17.38.217.277 I slot print_timing: id 3 | task 2941 | eval time = 43400.51 ms / 181 tokens ( 241.11 ms per token, 4.15 tokens per second) 17.38.217.278 I slot print_timing: id 3 | task 2941 | total time = 45525.60 ms / 306 tokens 17.38.217.279 I slot print_timing: id 3 | task 2941 | graphs reused = 2532 17.38.217.279 I slot print_timing: id 3 | task 2941 | graph reallocs = 0 / 0 (same size) / (changed size) 17.38.217.331 I slot release: id 3 | task 2941 | stop processing: n_tokens = 1430, truncated = 0 17.38.411.709 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.944 (> 0.100 thold), f_keep = 0.801 17.38.411.745 I slot launch_slot_: id 3 | task 3128 | processing task, is_child = 0 17.40.368.092 I slot print_timing: id 1 | task 2687 | n_gen = 433, tg = 4.00 t/s, tg_3s = 2.84 t/s 17.40.777.762 I slot print_timing: id 2 | task 3050 | prompt eval time = 1949.73 ms / 100 tokens ( 19.50 ms per token, 51.29 tokens per second) 17.40.777.768 I slot print_timing: id 2 | task 3050 | eval time = 19856.53 ms / 80 tokens ( 251.35 ms per token, 3.98 tokens per second) 17.40.777.769 I slot print_timing: id 2 | task 3050 | total time = 21806.25 ms / 180 tokens 17.40.777.769 I slot print_timing: id 2 | task 3050 | graphs reused = 2534 17.40.777.769 I slot print_timing: id 2 | task 3050 | graph reallocs = 0 / 0 (same size) / (changed size) 17.40.777.818 I slot release: id 2 | task 3050 | stop processing: n_tokens = 1304, truncated = 0 17.41.057.193 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.949 (> 0.100 thold), f_keep = 0.879 17.41.057.231 I slot launch_slot_: id 2 | task 3135 | processing task, is_child = 0 17.43.385.014 I slot print_timing: id 1 | task 2687 | n_gen = 440, tg = 3.96 t/s, tg_3s = 2.32 t/s 17.46.453.696 I slot print_timing: id 1 | task 2687 | n_gen = 455, tg = 3.98 t/s, tg_3s = 4.89 t/s 17.49.523.748 I slot print_timing: id 1 | task 2687 | n_gen = 470, tg = 4.01 t/s, tg_3s = 4.89 t/s 17.52.593.339 I slot print_timing: id 1 | task 2687 | n_gen = 485, tg = 4.03 t/s, tg_3s = 4.89 t/s 17.53.207.284 I slot print_timing: id 0 | task 3103 | prompt eval time = 2773.14 ms / 171 tokens ( 16.22 ms per token, 61.66 tokens per second) 17.53.207.289 I slot print_timing: id 0 | task 3103 | eval time = 19290.50 ms / 81 tokens ( 241.13 ms per token, 4.15 tokens per second) 17.53.207.289 I slot print_timing: id 0 | task 3103 | total time = 22063.64 ms / 252 tokens 17.53.207.290 I slot print_timing: id 0 | task 3103 | graphs reused = 2583 17.53.207.290 I slot print_timing: id 0 | task 3103 | graph reallocs = 0 / 0 (same size) / (changed size) 17.53.207.336 I slot release: id 0 | task 3103 | stop processing: n_tokens = 1376, truncated = 0 17.53.401.813 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.833 17.53.401.849 I slot launch_slot_: id 0 | task 3189 | processing task, is_child = 0 17.55.666.815 I slot print_timing: id 1 | task 2687 | n_gen = 492, tg = 3.98 t/s, tg_3s = 2.28 t/s 17.56.894.776 I slot print_timing: id 2 | task 3135 | prompt eval time = 1916.31 ms / 82 tokens ( 23.37 ms per token, 42.79 tokens per second) 17.56.894.781 I slot print_timing: id 2 | task 3135 | eval time = 13921.23 ms / 61 tokens ( 232.02 ms per token, 4.31 tokens per second) 17.56.894.781 I slot print_timing: id 2 | task 3135 | total time = 15837.54 ms / 143 tokens 17.56.894.782 I slot print_timing: id 2 | task 3135 | graphs reused = 2590 17.56.894.782 I slot print_timing: id 2 | task 3135 | graph reallocs = 0 / 0 (same size) / (changed size) 17.56.894.825 I slot release: id 2 | task 3135 | stop processing: n_tokens = 1267, truncated = 0 17.57.174.155 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.904 17.57.174.190 I slot launch_slot_: id 2 | task 3200 | processing task, is_child = 0 17.59.102.852 I slot print_timing: id 1 | task 2687 | n_gen = 501, tg = 3.95 t/s, tg_3s = 2.62 t/s 18.02.174.180 I slot print_timing: id 1 | task 2687 | n_gen = 516, tg = 3.97 t/s, tg_3s = 4.88 t/s 18.02.583.560 I slot print_timing: id 3 | task 3128 | prompt eval time = 1749.38 ms / 89 tokens ( 19.66 ms per token, 50.88 tokens per second) 18.02.583.565 I slot print_timing: id 3 | task 3128 | eval time = 22422.43 ms / 87 tokens ( 260.73 ms per token, 3.84 tokens per second) 18.02.583.567 I slot print_timing: id 3 | task 3128 | total time = 24171.81 ms / 176 tokens 18.02.583.567 I slot print_timing: id 3 | task 3128 | graphs reused = 2606 18.02.583.568 I slot print_timing: id 3 | task 3128 | graph reallocs = 0 / 0 (same size) / (changed size) 18.02.583.613 I slot release: id 3 | task 3128 | stop processing: n_tokens = 1300, truncated = 0 18.02.778.509 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.882 18.02.778.535 I slot launch_slot_: id 3 | task 3221 | processing task, is_child = 0 18.05.265.236 I slot print_timing: id 1 | task 2687 | n_gen = 523, tg = 3.93 t/s, tg_3s = 2.26 t/s 18.08.335.193 I slot print_timing: id 1 | task 2687 | n_gen = 538, tg = 3.95 t/s, tg_3s = 4.89 t/s 18.11.407.306 I slot print_timing: id 1 | task 2687 | n_gen = 553, tg = 3.97 t/s, tg_3s = 4.88 t/s 18.13.248.731 I slot print_timing: id 0 | task 3189 | prompt eval time = 2058.00 ms / 114 tokens ( 18.05 ms per token, 55.39 tokens per second) 18.13.248.737 I slot print_timing: id 0 | task 3189 | eval time = 17788.88 ms / 72 tokens ( 250.55 ms per token, 3.99 tokens per second) 18.13.248.738 I slot print_timing: id 0 | task 3189 | total time = 19846.88 ms / 186 tokens 18.13.248.738 I slot print_timing: id 0 | task 3189 | graphs reused = 2645 18.13.248.739 I slot print_timing: id 0 | task 3189 | graph reallocs = 0 / 0 (same size) / (changed size) 18.13.248.782 I slot release: id 0 | task 3189 | stop processing: n_tokens = 1310, truncated = 0 18.13.443.317 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.875 18.13.443.348 I slot launch_slot_: id 0 | task 3266 | processing task, is_child = 0 18.14.803.413 I slot print_timing: id 1 | task 2687 | n_gen = 564, tg = 3.95 t/s, tg_3s = 3.24 t/s 18.17.227.292 I slot print_timing: id 2 | task 3200 | prompt eval time = 1928.86 ms / 98 tokens ( 19.68 ms per token, 50.81 tokens per second) 18.17.227.296 I slot print_timing: id 2 | task 3200 | eval time = 18124.24 ms / 75 tokens ( 244.92 ms per token, 4.08 tokens per second) 18.17.227.296 I slot print_timing: id 2 | task 3200 | total time = 20053.09 ms / 173 tokens 18.17.227.297 I slot print_timing: id 2 | task 3200 | graphs reused = 2655 18.17.227.297 I slot print_timing: id 2 | task 3200 | graph reallocs = 0 / 0 (same size) / (changed size) 18.17.227.339 I slot release: id 2 | task 3200 | stop processing: n_tokens = 1297, truncated = 0 18.17.507.035 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.884 18.17.507.065 I slot launch_slot_: id 2 | task 3280 | processing task, is_child = 0 18.19.287.210 I slot print_timing: id 1 | task 2687 | n_gen = 577, tg = 3.92 t/s, tg_3s = 2.90 t/s 18.22.421.601 I slot print_timing: id 1 | task 2687 | n_gen = 591, tg = 3.93 t/s, tg_3s = 4.47 t/s 18.25.490.987 I slot print_timing: id 1 | task 2687 | n_gen = 606, tg = 3.95 t/s, tg_3s = 4.89 t/s 18.28.356.762 I slot print_timing: id 3 | task 3221 | n_gen = 100, tg = 4.21 t/s, tg_3s = 4.25 t/s 18.28.561.281 I slot print_timing: id 1 | task 2687 | n_gen = 621, tg = 3.97 t/s, tg_3s = 4.89 t/s 18.31.427.902 I slot print_timing: id 3 | task 3221 | n_gen = 115, tg = 4.29 t/s, tg_3s = 4.88 t/s 18.31.632.355 I slot print_timing: id 1 | task 2687 | n_gen = 636, tg = 3.99 t/s, tg_3s = 4.88 t/s 18.34.499.082 I slot print_timing: id 3 | task 3221 | n_gen = 130, tg = 4.35 t/s, tg_3s = 4.88 t/s 18.34.703.456 I slot print_timing: id 1 | task 2687 | n_gen = 651, tg = 4.01 t/s, tg_3s = 4.88 t/s 18.37.365.286 I slot print_timing: id 0 | task 3266 | n_gen = 100, tg = 4.46 t/s, tg_3s = 4.51 t/s 18.37.570.452 I slot print_timing: id 3 | task 3221 | n_gen = 145, tg = 4.40 t/s, tg_3s = 4.88 t/s 18.37.774.917 I slot print_timing: id 1 | task 2687 | n_gen = 666, tg = 4.02 t/s, tg_3s = 4.88 t/s 18.40.027.019 I slot print_timing: id 2 | task 3280 | n_gen = 100, tg = 4.88 t/s, tg_3s = 4.93 t/s 18.40.436.198 I slot print_timing: id 0 | task 3266 | n_gen = 115, tg = 4.51 t/s, tg_3s = 4.88 t/s 18.40.641.461 I slot print_timing: id 3 | task 3221 | prompt eval time = 2075.43 ms / 109 tokens ( 19.04 ms per token, 52.52 tokens per second) 18.40.641.466 I slot print_timing: id 3 | task 3221 | eval time = 35787.49 ms / 160 tokens ( 225.08 ms per token, 4.44 tokens per second) 18.40.641.467 I slot print_timing: id 3 | task 3221 | total time = 37862.92 ms / 269 tokens 18.40.641.467 I slot print_timing: id 3 | task 3221 | graphs reused = 2756 18.40.641.468 I slot print_timing: id 3 | task 3221 | graph reallocs = 0 / 0 (same size) / (changed size) 18.40.641.514 I slot release: id 3 | task 3221 | stop processing: n_tokens = 1393, truncated = 0 18.40.835.650 I slot print_timing: id 1 | task 2687 | n_gen = 681, tg = 4.04 t/s, tg_3s = 4.90 t/s 18.40.835.812 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.823 18.40.835.848 I slot launch_slot_: id 3 | task 3386 | processing task, is_child = 0 18.43.130.168 I slot print_timing: id 2 | task 3280 | n_gen = 107, tg = 4.54 t/s, tg_3s = 2.26 t/s 18.43.539.348 I slot print_timing: id 0 | task 3266 | n_gen = 122, tg = 4.27 t/s, tg_3s = 2.26 t/s 18.43.949.016 I slot print_timing: id 1 | task 2687 | n_gen = 688, tg = 4.01 t/s, tg_3s = 2.25 t/s 18.46.201.350 I slot print_timing: id 2 | task 3280 | n_gen = 122, tg = 4.58 t/s, tg_3s = 4.88 t/s 18.46.610.629 I slot print_timing: id 0 | task 3266 | prompt eval time = 1734.30 ms / 97 tokens ( 17.88 ms per token, 55.93 tokens per second) 18.46.610.634 I slot print_timing: id 0 | task 3266 | eval time = 31432.97 ms / 137 tokens ( 231.12 ms per token, 4.33 tokens per second) 18.46.610.635 I slot print_timing: id 0 | task 3266 | total time = 33167.27 ms / 234 tokens 18.46.610.635 I slot print_timing: id 0 | task 3266 | graphs reused = 2773 18.46.610.636 I slot print_timing: id 0 | task 3266 | graph reallocs = 0 / 0 (same size) / (changed size) 18.46.610.680 I slot release: id 0 | task 3266 | stop processing: n_tokens = 1358, truncated = 0 18.46.805.152 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.844 18.46.805.188 I slot launch_slot_: id 0 | task 3408 | processing task, is_child = 0 18.48.840.363 I slot print_timing: id 1 | task 2687 | n_gen = 703, tg = 3.98 t/s, tg_3s = 3.07 t/s 18.49.215.971 I slot print_timing: id 2 | task 3280 | n_gen = 127, tg = 4.28 t/s, tg_3s = 1.66 t/s 18.51.879.649 I slot print_timing: id 1 | task 2687 | n_gen = 717, tg = 3.99 t/s, tg_3s = 4.61 t/s 18.52.289.114 I slot print_timing: id 2 | task 3280 | n_gen = 142, tg = 4.33 t/s, tg_3s = 4.88 t/s 18.54.950.781 I slot print_timing: id 1 | task 2687 | n_gen = 732, tg = 4.01 t/s, tg_3s = 4.88 t/s 18.55.360.470 I slot print_timing: id 2 | task 3280 | n_gen = 157, tg = 4.38 t/s, tg_3s = 4.88 t/s 18.58.022.186 I slot print_timing: id 1 | task 2687 | n_gen = 747, tg = 4.02 t/s, tg_3s = 4.88 t/s 18.58.431.589 I slot print_timing: id 2 | task 3280 | n_gen = 172, tg = 4.42 t/s, tg_3s = 4.88 t/s 19.01.093.647 I slot print_timing: id 1 | task 2687 | n_gen = 762, tg = 4.03 t/s, tg_3s = 4.88 t/s 19.01.503.302 I slot print_timing: id 2 | task 3280 | n_gen = 187, tg = 4.46 t/s, tg_3s = 4.88 t/s 19.04.165.900 I slot print_timing: id 1 | task 2687 | n_gen = 777, tg = 4.05 t/s, tg_3s = 4.88 t/s 19.04.575.604 I slot print_timing: id 2 | task 3280 | n_gen = 202, tg = 4.48 t/s, tg_3s = 4.88 t/s 19.05.190.483 I slot print_timing: id 3 | task 3386 | n_gen = 100, tg = 4.45 t/s, tg_3s = 4.49 t/s 19.07.239.373 I slot print_timing: id 1 | task 2687 | n_gen = 792, tg = 4.06 t/s, tg_3s = 4.88 t/s 19.07.649.709 I slot print_timing: id 2 | task 3280 | n_gen = 217, tg = 4.51 t/s, tg_3s = 4.88 t/s 19.08.269.237 I slot print_timing: id 3 | task 3386 | n_gen = 115, tg = 4.50 t/s, tg_3s = 4.87 t/s 19.08.679.991 I slot print_timing: id 2 | task 3280 | prompt eval time = 2251.39 ms / 113 tokens ( 19.92 ms per token, 50.19 tokens per second) 19.08.679.996 I slot print_timing: id 2 | task 3280 | eval time = 48921.53 ms / 222 tokens ( 221.36 ms per token, 4.52 tokens per second) 19.08.679.996 I slot print_timing: id 2 | task 3280 | total time = 51172.92 ms / 335 tokens 19.08.679.997 I slot print_timing: id 2 | task 3280 | graphs reused = 2867 19.08.679.997 I slot print_timing: id 2 | task 3280 | graph reallocs = 0 / 0 (same size) / (changed size) 19.08.680.044 I slot release: id 2 | task 3280 | stop processing: n_tokens = 1459, truncated = 0 19.08.960.283 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.785 19.08.960.320 I slot launch_slot_: id 2 | task 3507 | processing task, is_child = 0 19.10.758.512 I slot print_timing: id 1 | task 2687 | n_gen = 801, tg = 4.03 t/s, tg_3s = 2.56 t/s 19.11.437.006 I slot print_timing: id 0 | task 3408 | n_gen = 100, tg = 4.46 t/s, tg_3s = 4.50 t/s 19.11.437.446 I slot print_timing: id 3 | task 3386 | n_gen = 121, tg = 4.21 t/s, tg_3s = 1.89 t/s 19.11.642.825 I slot print_timing: id 3 | task 3386 | prompt eval time = 2087.55 ms / 119 tokens ( 17.54 ms per token, 57.00 tokens per second) 19.11.642.829 I slot print_timing: id 3 | task 3386 | eval time = 28719.42 ms / 122 tokens ( 237.35 ms per token, 4.21 tokens per second) 19.11.642.830 I slot print_timing: id 3 | task 3386 | total time = 30806.97 ms / 241 tokens 19.11.642.830 I slot print_timing: id 3 | task 3386 | graphs reused = 2868 19.11.642.830 I slot print_timing: id 3 | task 3386 | graph reallocs = 0 / 0 (same size) / (changed size) 19.11.642.878 I slot release: id 3 | task 3386 | stop processing: n_tokens = 1365, truncated = 0 19.11.837.419 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.840 19.11.837.448 I slot launch_slot_: id 3 | task 3513 | processing task, is_child = 0 19.13.963.221 I slot print_timing: id 1 | task 2687 | n_gen = 807, tg = 4.00 t/s, tg_3s = 1.87 t/s 19.14.581.990 I slot print_timing: id 0 | task 3408 | n_gen = 107, tg = 4.18 t/s, tg_3s = 2.23 t/s 19.17.047.117 I slot print_timing: id 1 | task 2687 | n_gen = 822, tg = 4.01 t/s, tg_3s = 4.86 t/s 19.17.663.252 I slot print_timing: id 0 | task 3408 | n_gen = 122, tg = 4.25 t/s, tg_3s = 4.87 t/s 19.20.127.810 I slot print_timing: id 1 | task 2687 | n_gen = 837, tg = 4.03 t/s, tg_3s = 4.87 t/s 19.20.743.407 I slot print_timing: id 0 | task 3408 | n_gen = 137, tg = 4.31 t/s, tg_3s = 4.87 t/s 19.23.207.114 I slot print_timing: id 1 | task 2687 | n_gen = 852, tg = 4.04 t/s, tg_3s = 4.87 t/s 19.23.823.139 I slot print_timing: id 0 | task 3408 | n_gen = 152, tg = 4.36 t/s, tg_3s = 4.87 t/s 19.26.289.155 I slot print_timing: id 1 | task 2687 | n_gen = 867, tg = 4.05 t/s, tg_3s = 4.87 t/s 19.26.905.305 I slot print_timing: id 0 | task 3408 | n_gen = 167, tg = 4.40 t/s, tg_3s = 4.87 t/s 19.29.371.760 I slot print_timing: id 1 | task 2687 | n_gen = 882, tg = 4.06 t/s, tg_3s = 4.87 t/s 19.29.987.467 I slot print_timing: id 0 | task 3408 | n_gen = 182, tg = 4.44 t/s, tg_3s = 4.87 t/s 19.32.452.553 I slot print_timing: id 1 | task 2687 | n_gen = 897, tg = 4.07 t/s, tg_3s = 4.87 t/s 19.33.068.535 I slot print_timing: id 0 | task 3408 | n_gen = 197, tg = 4.47 t/s, tg_3s = 4.87 t/s 19.33.274.319 I slot print_timing: id 2 | task 3507 | n_gen = 100, tg = 4.49 t/s, tg_3s = 4.54 t/s 19.34.301.714 I slot print_timing: id 3 | task 3513 | n_gen = 100, tg = 4.87 t/s, tg_3s = 4.92 t/s 19.35.123.078 I slot print_timing: id 3 | task 3513 | prompt eval time = 2126.17 ms / 109 tokens ( 19.51 ms per token, 51.27 tokens per second) 19.35.123.084 I slot print_timing: id 3 | task 3513 | eval time = 21159.46 ms / 104 tokens ( 205.43 ms per token, 4.87 tokens per second) 19.35.123.085 I slot print_timing: id 3 | task 3513 | total time = 23285.62 ms / 213 tokens 19.35.123.086 I slot print_timing: id 3 | task 3513 | graphs reused = 2970 19.35.123.087 I slot print_timing: id 3 | task 3513 | graph reallocs = 0 / 0 (same size) / (changed size) 19.35.123.138 I slot release: id 3 | task 3513 | stop processing: n_tokens = 1337, truncated = 0 19.35.317.983 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.857 19.35.318.012 I slot launch_slot_: id 3 | task 3620 | processing task, is_child = 0 19.36.710.975 I slot print_timing: id 0 | task 3408 | n_gen = 209, tg = 4.38 t/s, tg_3s = 3.29 t/s 19.36.711.125 I slot print_timing: id 1 | task 2687 | n_gen = 912, tg = 4.06 t/s, tg_3s = 3.52 t/s 19.36.711.328 I slot print_timing: id 2 | task 3507 | n_gen = 111, tg = 4.32 t/s, tg_3s = 3.20 t/s 19.39.772.455 I slot print_timing: id 0 | task 3408 | n_gen = 223, tg = 4.39 t/s, tg_3s = 4.57 t/s 19.39.772.598 I slot print_timing: id 1 | task 2687 | n_gen = 926, tg = 4.07 t/s, tg_3s = 4.57 t/s 19.39.772.742 I slot print_timing: id 2 | task 3507 | n_gen = 125, tg = 4.34 t/s, tg_3s = 4.57 t/s 19.42.855.837 I slot print_timing: id 0 | task 3408 | n_gen = 238, tg = 4.42 t/s, tg_3s = 4.86 t/s 19.42.855.976 I slot print_timing: id 1 | task 2687 | n_gen = 941, tg = 4.08 t/s, tg_3s = 4.86 t/s 19.42.856.116 I slot print_timing: id 2 | task 3507 | n_gen = 140, tg = 4.39 t/s, tg_3s = 4.86 t/s 19.45.938.162 I slot print_timing: id 0 | task 3408 | n_gen = 253, tg = 4.44 t/s, tg_3s = 4.87 t/s 19.45.938.314 I slot print_timing: id 1 | task 2687 | n_gen = 956, tg = 4.09 t/s, tg_3s = 4.87 t/s 19.45.938.470 I slot print_timing: id 2 | task 3507 | n_gen = 155, tg = 4.44 t/s, tg_3s = 4.87 t/s 19.49.020.108 I slot print_timing: id 0 | task 3408 | n_gen = 268, tg = 4.46 t/s, tg_3s = 4.87 t/s 19.49.020.253 I slot print_timing: id 1 | task 2687 | n_gen = 971, tg = 4.10 t/s, tg_3s = 4.87 t/s 19.49.020.402 I slot print_timing: id 2 | task 3507 | n_gen = 170, tg = 4.47 t/s, tg_3s = 4.87 t/s 19.52.102.921 I slot print_timing: id 0 | task 3408 | n_gen = 283, tg = 4.48 t/s, tg_3s = 4.87 t/s 19.52.103.065 I slot print_timing: id 1 | task 2687 | n_gen = 986, tg = 4.11 t/s, tg_3s = 4.87 t/s 19.52.103.220 I slot print_timing: id 2 | task 3507 | n_gen = 185, tg = 4.50 t/s, tg_3s = 4.87 t/s 19.55.186.654 I slot print_timing: id 0 | task 3408 | n_gen = 298, tg = 4.50 t/s, tg_3s = 4.86 t/s 19.55.186.802 I slot print_timing: id 1 | task 2687 | n_gen = 1001, tg = 4.12 t/s, tg_3s = 4.86 t/s 19.55.186.944 I slot print_timing: id 2 | task 3507 | n_gen = 200, tg = 4.53 t/s, tg_3s = 4.86 t/s 19.57.448.078 I slot print_timing: id 3 | task 3620 | n_gen = 100, tg = 4.86 t/s, tg_3s = 4.91 t/s 19.58.270.201 I slot print_timing: id 0 | task 3408 | n_gen = 313, tg = 4.52 t/s, tg_3s = 4.86 t/s 19.58.270.349 I slot print_timing: id 1 | task 2687 | n_gen = 1016, tg = 4.13 t/s, tg_3s = 4.86 t/s 19.58.270.490 I slot print_timing: id 2 | task 3507 | n_gen = 215, tg = 4.55 t/s, tg_3s = 4.86 t/s 19.59.914.904 I slot print_timing: id 1 | task 2687 | prompt eval time = 2387.97 ms / 128 tokens ( 18.66 ms per token, 53.60 tokens per second) 19.59.914.909 I slot print_timing: id 1 | task 2687 | eval time = 247463.48 ms / 1024 tokens ( 241.90 ms per token, 4.13 tokens per second) 19.59.914.910 I slot print_timing: id 1 | task 2687 | total time = 249851.45 ms / 1152 tokens 19.59.914.910 I slot print_timing: id 1 | task 2687 | graphs reused = 3080 19.59.914.911 I slot print_timing: id 1 | task 2687 | graph reallocs = 0 / 0 (same size) / (changed size) 19.59.914.956 I slot release: id 1 | task 2687 | stop processing: n_tokens = 2276, truncated = 0 20.00.195.091 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.504 20.00.195.122 I slot launch_slot_: id 1 | task 3735 | processing task, is_child = 0 20.01.714.001 I slot print_timing: id 0 | task 3408 | n_gen = 323, tg = 4.44 t/s, tg_3s = 2.90 t/s 20.01.714.211 I slot print_timing: id 2 | task 3507 | n_gen = 225, tg = 4.44 t/s, tg_3s = 2.90 t/s 20.01.714.418 I slot print_timing: id 3 | task 3620 | n_gen = 114, tg = 4.59 t/s, tg_3s = 3.28 t/s 20.02.248.645 I slot print_timing: id 3 | task 3620 | prompt eval time = 1779.93 ms / 95 tokens ( 18.74 ms per token, 53.37 tokens per second) 20.02.248.651 I slot print_timing: id 3 | task 3620 | eval time = 25150.70 ms / 115 tokens ( 220.62 ms per token, 4.53 tokens per second) 20.02.248.651 I slot print_timing: id 3 | task 3620 | total time = 26930.63 ms / 210 tokens 20.02.248.651 I slot print_timing: id 3 | task 3620 | graphs reused = 3080 20.02.248.652 I slot print_timing: id 3 | task 3620 | graph reallocs = 0 / 0 (same size) / (changed size) 20.02.248.695 I slot release: id 3 | task 3620 | stop processing: n_tokens = 1334, truncated = 0 20.02.442.435 I slot print_timing: id 0 | task 3408 | prompt eval time = 2410.49 ms / 134 tokens ( 17.99 ms per token, 55.59 tokens per second) 20.02.442.440 I slot print_timing: id 0 | task 3408 | eval time = 73226.75 ms / 325 tokens ( 226.01 ms per token, 4.42 tokens per second) 20.02.442.441 I slot print_timing: id 0 | task 3408 | total time = 75637.24 ms / 459 tokens 20.02.442.441 I slot print_timing: id 0 | task 3408 | graphs reused = 3080 20.02.442.442 I slot print_timing: id 0 | task 3408 | graph reallocs = 0 / 0 (same size) / (changed size) 20.02.442.478 I slot release: id 0 | task 3408 | stop processing: n_tokens = 1583, truncated = 0 20.02.442.783 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.724 20.02.442.810 I slot launch_slot_: id 0 | task 3739 | processing task, is_child = 0 20.02.442.876 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.943 MiB) 20.02.442.879 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.631 MiB) 20.02.442.880 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.131 MiB) 20.02.491.669 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.859 20.02.491.714 I slot launch_slot_: id 3 | task 3740 | processing task, is_child = 0 20.06.373.288 I slot print_timing: id 2 | task 3507 | n_gen = 228, tg = 4.12 t/s, tg_3s = 0.64 t/s 20.06.373.300 I slot print_timing: id 0 | task 3739 | prompt processing, n_tokens = 118, progress = 1.00, t = 3.88 s / 30.40 tokens per second 20.06.380.539 I slot print_timing: id 3 | task 3740 | prompt processing, n_tokens = 162, progress = 1.00, t = 3.87 s / 41.82 tokens per second 20.09.379.922 I slot print_timing: id 2 | task 3507 | n_gen = 241, tg = 4.13 t/s, tg_3s = 4.32 t/s 20.12.445.356 I slot print_timing: id 2 | task 3507 | n_gen = 256, tg = 4.17 t/s, tg_3s = 4.89 t/s 20.15.512.029 I slot print_timing: id 2 | task 3507 | n_gen = 271, tg = 4.20 t/s, tg_3s = 4.89 t/s 20.18.579.872 I slot print_timing: id 2 | task 3507 | n_gen = 286, tg = 4.23 t/s, tg_3s = 4.89 t/s 20.18.989.019 I slot print_timing: id 2 | task 3507 | prompt eval time = 2268.85 ms / 112 tokens ( 20.26 ms per token, 49.36 tokens per second) 20.18.989.024 I slot print_timing: id 2 | task 3507 | eval time = 67759.84 ms / 288 tokens ( 236.10 ms per token, 4.24 tokens per second) 20.18.989.025 I slot print_timing: id 2 | task 3507 | total time = 70028.69 ms / 400 tokens 20.18.989.025 I slot print_timing: id 2 | task 3507 | graphs reused = 3138 20.18.989.026 I slot print_timing: id 2 | task 3507 | graph reallocs = 0 / 0 (same size) / (changed size) 20.18.989.077 I slot release: id 2 | task 3507 | stop processing: n_tokens = 1524, truncated = 0 20.19.268.950 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.752 20.19.268.986 I slot launch_slot_: id 2 | task 3803 | processing task, is_child = 0 20.27.860.108 I slot print_timing: id 1 | task 3735 | prompt eval time = 2053.24 ms / 96 tokens ( 21.39 ms per token, 46.76 tokens per second) 20.27.860.113 I slot print_timing: id 1 | task 3735 | eval time = 25611.74 ms / 97 tokens ( 266.79 ms per token, 3.75 tokens per second) 20.27.860.114 I slot print_timing: id 1 | task 3735 | total time = 27664.98 ms / 193 tokens 20.27.860.114 I slot print_timing: id 1 | task 3735 | graphs reused = 3168 20.27.860.114 I slot print_timing: id 1 | task 3735 | graph reallocs = 0 / 0 (same size) / (changed size) 20.27.860.157 I slot release: id 1 | task 3735 | stop processing: n_tokens = 1317, truncated = 0 20.28.140.376 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.870 20.28.140.424 I slot launch_slot_: id 1 | task 3838 | processing task, is_child = 0 20.31.126.163 I slot print_timing: id 0 | task 3739 | n_gen = 100, tg = 4.09 t/s, tg_3s = 4.13 t/s 20.31.126.591 I slot print_timing: id 3 | task 3740 | n_gen = 100, tg = 4.09 t/s, tg_3s = 4.13 t/s 20.34.193.811 I slot print_timing: id 0 | task 3739 | n_gen = 115, tg = 4.18 t/s, tg_3s = 4.89 t/s 20.34.194.236 I slot print_timing: id 3 | task 3740 | n_gen = 115, tg = 4.18 t/s, tg_3s = 4.89 t/s 20.37.262.194 I slot print_timing: id 0 | task 3739 | n_gen = 130, tg = 4.25 t/s, tg_3s = 4.89 t/s 20.37.262.636 I slot print_timing: id 3 | task 3740 | n_gen = 130, tg = 4.25 t/s, tg_3s = 4.89 t/s 20.40.330.007 I slot print_timing: id 0 | task 3739 | n_gen = 145, tg = 4.31 t/s, tg_3s = 4.89 t/s 20.40.330.407 I slot print_timing: id 3 | task 3740 | n_gen = 145, tg = 4.31 t/s, tg_3s = 4.89 t/s 20.43.398.033 I slot print_timing: id 0 | task 3739 | n_gen = 160, tg = 4.36 t/s, tg_3s = 4.89 t/s 20.43.398.461 I slot print_timing: id 3 | task 3740 | n_gen = 160, tg = 4.36 t/s, tg_3s = 4.89 t/s 20.43.807.457 I slot print_timing: id 2 | task 3803 | n_gen = 100, tg = 4.44 t/s, tg_3s = 4.49 t/s 20.46.466.098 I slot print_timing: id 0 | task 3739 | n_gen = 175, tg = 4.40 t/s, tg_3s = 4.89 t/s 20.46.466.533 I slot print_timing: id 3 | task 3740 | n_gen = 175, tg = 4.40 t/s, tg_3s = 4.89 t/s 20.46.875.534 I slot print_timing: id 2 | task 3803 | n_gen = 115, tg = 4.50 t/s, tg_3s = 4.89 t/s 20.49.535.871 I slot print_timing: id 0 | task 3739 | n_gen = 190, tg = 4.44 t/s, tg_3s = 4.89 t/s 20.49.536.300 I slot print_timing: id 3 | task 3740 | n_gen = 190, tg = 4.44 t/s, tg_3s = 4.89 t/s 20.49.945.436 I slot print_timing: id 2 | task 3803 | n_gen = 130, tg = 4.54 t/s, tg_3s = 4.89 t/s 20.50.763.735 I slot print_timing: id 1 | task 3838 | n_gen = 100, tg = 4.89 t/s, tg_3s = 4.94 t/s 20.52.605.760 I slot print_timing: id 0 | task 3739 | n_gen = 205, tg = 4.47 t/s, tg_3s = 4.89 t/s 20.52.606.172 I slot print_timing: id 3 | task 3740 | n_gen = 205, tg = 4.47 t/s, tg_3s = 4.89 t/s 20.53.014.092 I slot print_timing: id 1 | task 3838 | prompt eval time = 2369.79 ms / 104 tokens ( 22.79 ms per token, 43.89 tokens per second) 20.53.014.098 I slot print_timing: id 1 | task 3838 | eval time = 22503.87 ms / 111 tokens ( 204.58 ms per token, 4.89 tokens per second) 20.53.014.098 I slot print_timing: id 1 | task 3838 | total time = 24873.66 ms / 215 tokens 20.53.014.099 I slot print_timing: id 1 | task 3838 | graphs reused = 3277 20.53.014.099 I slot print_timing: id 1 | task 3838 | graph reallocs = 0 / 0 (same size) / (changed size) 20.53.014.152 I slot release: id 1 | task 3838 | stop processing: n_tokens = 1339, truncated = 0 20.53.014.315 I slot print_timing: id 2 | task 3803 | n_gen = 145, tg = 4.57 t/s, tg_3s = 4.89 t/s 20.53.294.008 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.856 20.53.294.048 I slot launch_slot_: id 1 | task 3952 | processing task, is_child = 0 20.55.663.614 I slot print_timing: id 0 | task 3739 | prompt eval time = 4431.17 ms / 122 tokens ( 36.32 ms per token, 27.53 tokens per second) 20.55.663.620 I slot print_timing: id 0 | task 3739 | eval time = 48740.72 ms / 210 tokens ( 233.21 ms per token, 4.29 tokens per second) 20.55.663.621 I slot print_timing: id 0 | task 3739 | total time = 53171.89 ms / 332 tokens 20.55.663.621 I slot print_timing: id 0 | task 3739 | graphs reused = 3277 20.55.663.621 I slot print_timing: id 0 | task 3739 | graph reallocs = 0 / 0 (same size) / (changed size) 20.55.663.668 I slot release: id 0 | task 3739 | stop processing: n_tokens = 1456, truncated = 0 20.55.664.211 I slot print_timing: id 3 | task 3740 | n_gen = 210, tg = 4.29 t/s, tg_3s = 1.64 t/s 20.55.858.436 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.911 (> 0.100 thold), f_keep = 0.787 20.55.858.467 I slot launch_slot_: id 0 | task 3956 | processing task, is_child = 0 20.57.892.065 I slot print_timing: id 2 | task 3803 | n_gen = 150, tg = 4.10 t/s, tg_3s = 1.03 t/s 20.58.678.365 I slot print_timing: id 3 | task 3740 | n_gen = 215, tg = 4.13 t/s, tg_3s = 1.66 t/s 21.00.928.339 I slot print_timing: id 2 | task 3803 | n_gen = 164, tg = 4.14 t/s, tg_3s = 4.61 t/s 21.01.747.134 I slot print_timing: id 3 | task 3740 | n_gen = 230, tg = 4.18 t/s, tg_3s = 4.89 t/s 21.03.996.673 I slot print_timing: id 2 | task 3803 | n_gen = 179, tg = 4.19 t/s, tg_3s = 4.89 t/s 21.04.815.368 I slot print_timing: id 3 | task 3740 | n_gen = 245, tg = 4.21 t/s, tg_3s = 4.89 t/s 21.07.068.836 I slot print_timing: id 2 | task 3803 | n_gen = 194, tg = 4.24 t/s, tg_3s = 4.88 t/s 21.07.887.711 I slot print_timing: id 3 | task 3740 | n_gen = 260, tg = 4.25 t/s, tg_3s = 4.88 t/s 21.10.139.106 I slot print_timing: id 2 | task 3803 | n_gen = 209, tg = 4.28 t/s, tg_3s = 4.89 t/s 21.10.957.706 I slot print_timing: id 3 | task 3740 | n_gen = 275, tg = 4.28 t/s, tg_3s = 4.89 t/s 21.13.208.653 I slot print_timing: id 2 | task 3803 | n_gen = 224, tg = 4.31 t/s, tg_3s = 4.89 t/s 21.14.027.537 I slot print_timing: id 3 | task 3740 | n_gen = 290, tg = 4.31 t/s, tg_3s = 4.89 t/s 21.16.277.589 I slot print_timing: id 2 | task 3803 | n_gen = 239, tg = 4.35 t/s, tg_3s = 4.89 t/s 21.17.096.731 I slot print_timing: id 3 | task 3740 | n_gen = 305, tg = 4.33 t/s, tg_3s = 4.89 t/s 21.17.915.143 I slot print_timing: id 1 | task 3952 | n_gen = 100, tg = 4.45 t/s, tg_3s = 4.49 t/s 21.18.529.202 I slot print_timing: id 0 | task 3956 | n_gen = 100, tg = 4.89 t/s, tg_3s = 4.94 t/s 21.19.348.033 I slot print_timing: id 2 | task 3803 | n_gen = 254, tg = 4.38 t/s, tg_3s = 4.89 t/s 21.20.166.537 I slot print_timing: id 3 | task 3740 | n_gen = 320, tg = 4.36 t/s, tg_3s = 4.89 t/s 21.20.984.890 I slot print_timing: id 1 | task 3952 | n_gen = 115, tg = 4.50 t/s, tg_3s = 4.89 t/s 21.21.599.278 I slot print_timing: id 0 | task 3956 | n_gen = 115, tg = 4.89 t/s, tg_3s = 4.89 t/s 21.22.418.686 I slot print_timing: id 2 | task 3803 | n_gen = 269, tg = 4.40 t/s, tg_3s = 4.88 t/s 21.23.238.135 I slot print_timing: id 3 | task 3740 | n_gen = 335, tg = 4.38 t/s, tg_3s = 4.88 t/s 21.24.056.394 I slot print_timing: id 1 | task 3952 | n_gen = 130, tg = 4.54 t/s, tg_3s = 4.88 t/s 21.24.261.354 I slot print_timing: id 2 | task 3803 | prompt eval time = 2251.85 ms / 117 tokens ( 19.25 ms per token, 51.96 tokens per second) 21.24.261.358 I slot print_timing: id 2 | task 3803 | eval time = 62740.50 ms / 278 tokens ( 226.50 ms per token, 4.42 tokens per second) 21.24.261.359 I slot print_timing: id 2 | task 3803 | total time = 64992.36 ms / 395 tokens 21.24.261.359 I slot print_timing: id 2 | task 3803 | graphs reused = 3403 21.24.261.360 I slot print_timing: id 2 | task 3803 | graph reallocs = 0 / 0 (same size) / (changed size) 21.24.261.406 I slot release: id 2 | task 3803 | stop processing: n_tokens = 1519, truncated = 0 21.24.540.940 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.754 21.24.540.971 I slot launch_slot_: id 2 | task 4087 | processing task, is_child = 0 21.26.317.919 I slot print_timing: id 0 | task 3956 | n_gen = 130, tg = 4.60 t/s, tg_3s = 3.18 t/s 21.26.318.303 I slot print_timing: id 3 | task 3740 | n_gen = 342, tg = 4.29 t/s, tg_3s = 2.27 t/s 21.27.201.245 I slot print_timing: id 1 | task 3952 | n_gen = 136, tg = 4.28 t/s, tg_3s = 1.91 t/s 21.29.452.349 I slot print_timing: id 0 | task 3956 | n_gen = 144, tg = 4.59 t/s, tg_3s = 4.47 t/s 21.29.452.779 I slot print_timing: id 3 | task 3740 | n_gen = 356, tg = 4.30 t/s, tg_3s = 4.47 t/s 21.30.271.173 I slot print_timing: id 1 | task 3952 | n_gen = 151, tg = 4.33 t/s, tg_3s = 4.89 t/s 21.31.294.244 I slot print_timing: id 1 | task 3952 | prompt eval time = 2369.86 ms / 108 tokens ( 21.94 ms per token, 45.57 tokens per second) 21.31.294.249 I slot print_timing: id 1 | task 3952 | eval time = 35630.33 ms / 156 tokens ( 229.87 ms per token, 4.35 tokens per second) 21.31.294.250 I slot print_timing: id 1 | task 3952 | total time = 38000.19 ms / 264 tokens 21.31.294.250 I slot print_timing: id 1 | task 3952 | graphs reused = 3424 21.31.294.251 I slot print_timing: id 1 | task 3952 | graph reallocs = 0 / 0 (same size) / (changed size) 21.31.294.295 I slot release: id 1 | task 3952 | stop processing: n_tokens = 1388, truncated = 0 21.31.574.083 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.826 21.31.574.130 I slot launch_slot_: id 1 | task 4113 | processing task, is_child = 0 21.33.422.687 I slot print_timing: id 0 | task 3956 | n_gen = 155, tg = 4.38 t/s, tg_3s = 2.77 t/s 21.33.423.012 I slot print_timing: id 3 | task 3740 | n_gen = 367, tg = 4.23 t/s, tg_3s = 2.77 t/s 21.36.618.424 I slot print_timing: id 0 | task 3956 | n_gen = 169, tg = 4.38 t/s, tg_3s = 4.38 t/s 21.36.618.833 I slot print_timing: id 3 | task 3740 | n_gen = 381, tg = 4.24 t/s, tg_3s = 4.38 t/s 21.39.687.764 I slot print_timing: id 0 | task 3956 | n_gen = 184, tg = 4.42 t/s, tg_3s = 4.89 t/s 21.39.688.176 I slot print_timing: id 3 | task 3740 | n_gen = 396, tg = 4.26 t/s, tg_3s = 4.89 t/s 21.42.758.038 I slot print_timing: id 0 | task 3956 | n_gen = 199, tg = 4.45 t/s, tg_3s = 4.89 t/s 21.42.758.483 I slot print_timing: id 3 | task 3740 | prompt eval time = 4424.06 ms / 166 tokens ( 26.65 ms per token, 37.52 tokens per second) 21.42.758.486 I slot print_timing: id 3 | task 3740 | eval time = 95835.11 ms / 411 tokens ( 233.74 ms per token, 4.28 tokens per second) 21.42.758.486 I slot print_timing: id 3 | task 3740 | total time = 100259.17 ms / 577 tokens 21.42.758.487 I slot print_timing: id 3 | task 3740 | graphs reused = 3466 21.42.758.487 I slot print_timing: id 3 | task 3740 | graph reallocs = 0 / 0 (same size) / (changed size) 21.42.758.537 I slot release: id 3 | task 3740 | stop processing: n_tokens = 1701, truncated = 0 21.42.953.112 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.674 21.42.953.139 I slot launch_slot_: id 3 | task 4160 | processing task, is_child = 0 21.45.860.612 I slot print_timing: id 0 | task 3956 | n_gen = 206, tg = 4.31 t/s, tg_3s = 2.26 t/s 21.48.928.517 I slot print_timing: id 0 | task 3956 | n_gen = 221, tg = 4.34 t/s, tg_3s = 4.89 t/s 21.50.769.227 I slot print_timing: id 2 | task 4087 | n_gen = 100, tg = 4.13 t/s, tg_3s = 4.17 t/s 21.51.996.093 I slot print_timing: id 0 | task 3956 | n_gen = 236, tg = 4.37 t/s, tg_3s = 4.89 t/s 21.52.609.742 I slot print_timing: id 2 | task 4087 | prompt eval time = 2248.49 ms / 112 tokens ( 20.08 ms per token, 49.81 tokens per second) 21.52.609.748 I slot print_timing: id 2 | task 4087 | eval time = 25820.28 ms / 109 tokens ( 239.08 ms per token, 4.18 tokens per second) 21.52.609.748 I slot print_timing: id 2 | task 4087 | total time = 28068.76 ms / 221 tokens 21.52.609.749 I slot print_timing: id 2 | task 4087 | graphs reused = 3502 21.52.609.749 I slot print_timing: id 2 | task 4087 | graph reallocs = 0 / 0 (same size) / (changed size) 21.52.609.795 I slot release: id 2 | task 4087 | stop processing: n_tokens = 1345, truncated = 0 21.52.889.482 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.852 21.52.889.514 I slot launch_slot_: id 2 | task 4201 | processing task, is_child = 0 21.55.145.263 I slot print_timing: id 0 | task 3956 | n_gen = 242, tg = 4.24 t/s, tg_3s = 1.91 t/s 21.55.557.028 I slot print_timing: id 1 | task 4113 | prompt eval time = 2381.70 ms / 116 tokens ( 20.53 ms per token, 48.70 tokens per second) 21.55.557.031 I slot print_timing: id 1 | task 4113 | eval time = 21601.20 ms / 89 tokens ( 245.47 ms per token, 4.07 tokens per second) 21.55.557.031 I slot print_timing: id 1 | task 4113 | total time = 23982.89 ms / 205 tokens 21.55.557.032 I slot print_timing: id 1 | task 4113 | graphs reused = 3503 21.55.557.032 I slot print_timing: id 1 | task 4113 | graph reallocs = 0 / 0 (same size) / (changed size) 21.55.557.076 I slot release: id 1 | task 4113 | stop processing: n_tokens = 1329, truncated = 0 21.55.836.745 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.862 21.55.836.781 I slot launch_slot_: id 1 | task 4207 | processing task, is_child = 0 21.58.205.566 I slot print_timing: id 0 | task 3956 | n_gen = 247, tg = 4.10 t/s, tg_3s = 1.63 t/s 22.01.275.940 I slot print_timing: id 0 | task 3956 | n_gen = 262, tg = 4.14 t/s, tg_3s = 4.89 t/s 22.04.343.347 I slot print_timing: id 0 | task 3956 | n_gen = 277, tg = 4.18 t/s, tg_3s = 4.89 t/s 22.06.390.326 I slot print_timing: id 0 | task 3956 | prompt eval time = 2408.33 ms / 133 tokens ( 18.11 ms per token, 55.22 tokens per second) 22.06.390.331 I slot print_timing: id 0 | task 3956 | eval time = 68123.52 ms / 287 tokens ( 238.19 ms per token, 4.20 tokens per second) 22.06.390.332 I slot print_timing: id 0 | task 3956 | total time = 70531.85 ms / 420 tokens 22.06.390.332 I slot print_timing: id 0 | task 3956 | graphs reused = 3541 22.06.390.333 I slot print_timing: id 0 | task 3956 | graph reallocs = 0 / 0 (same size) / (changed size) 22.06.390.382 I slot release: id 0 | task 3956 | stop processing: n_tokens = 1544, truncated = 0 22.06.584.986 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.742 22.06.585.014 I slot launch_slot_: id 0 | task 4251 | processing task, is_child = 0 22.10.900.714 I slot print_timing: id 3 | task 4160 | n_gen = 100, tg = 3.83 t/s, tg_3s = 3.87 t/s 22.13.968.152 I slot print_timing: id 3 | task 4160 | n_gen = 115, tg = 3.94 t/s, tg_3s = 4.89 t/s 22.16.215.126 I slot print_timing: id 1 | task 4207 | prompt eval time = 2369.01 ms / 103 tokens ( 23.00 ms per token, 43.48 tokens per second) 22.16.215.131 I slot print_timing: id 1 | task 4207 | eval time = 18009.33 ms / 81 tokens ( 225.12 ms per token, 4.44 tokens per second) 22.16.215.132 I slot print_timing: id 1 | task 4207 | total time = 20378.34 ms / 184 tokens 22.16.215.132 I slot print_timing: id 1 | task 4207 | graphs reused = 3578 22.16.215.133 I slot print_timing: id 1 | task 4207 | graph reallocs = 0 / 0 (same size) / (changed size) 22.16.215.175 I slot release: id 1 | task 4207 | stop processing: n_tokens = 1308, truncated = 0 22.16.494.469 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.876 22.16.494.503 I slot launch_slot_: id 1 | task 4292 | processing task, is_child = 0 22.18.335.246 I slot print_timing: id 3 | task 4160 | n_gen = 128, tg = 3.81 t/s, tg_3s = 2.98 t/s 22.21.118.838 I slot print_timing: id 2 | task 4201 | n_gen = 100, tg = 3.81 t/s, tg_3s = 3.85 t/s 22.21.528.068 I slot print_timing: id 3 | task 4160 | n_gen = 142, tg = 3.86 t/s, tg_3s = 4.38 t/s 22.22.550.458 I slot print_timing: id 2 | task 4201 | prompt eval time = 2256.12 ms / 119 tokens ( 18.96 ms per token, 52.75 tokens per second) 22.22.550.464 I slot print_timing: id 2 | task 4201 | eval time = 27404.81 ms / 107 tokens ( 258.54 ms per token, 3.87 tokens per second) 22.22.550.465 I slot print_timing: id 2 | task 4201 | total time = 29660.94 ms / 226 tokens 22.22.550.465 I slot print_timing: id 2 | task 4201 | graphs reused = 3595 22.22.550.466 I slot print_timing: id 2 | task 4201 | graph reallocs = 0 / 0 (same size) / (changed size) 22.22.550.510 I slot release: id 2 | task 4201 | stop processing: n_tokens = 1350, truncated = 0 22.22.830.007 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.849 22.22.830.043 I slot launch_slot_: id 2 | task 4314 | processing task, is_child = 0 22.24.759.424 I slot print_timing: id 3 | task 4160 | n_gen = 150, tg = 3.75 t/s, tg_3s = 2.48 t/s 22.27.827.482 I slot print_timing: id 3 | task 4160 | n_gen = 165, tg = 3.83 t/s, tg_3s = 4.89 t/s 22.28.850.375 I slot print_timing: id 3 | task 4160 | prompt eval time = 2087.49 ms / 119 tokens ( 17.54 ms per token, 57.01 tokens per second) 22.28.850.380 I slot print_timing: id 3 | task 4160 | eval time = 43809.74 ms / 170 tokens ( 259.23 ms per token, 3.86 tokens per second) 22.28.850.381 I slot print_timing: id 3 | task 4160 | total time = 45897.23 ms / 289 tokens 22.28.850.381 I slot print_timing: id 3 | task 4160 | graphs reused = 3614 22.28.850.382 I slot print_timing: id 3 | task 4160 | graph reallocs = 0 / 0 (same size) / (changed size) 22.28.850.428 I slot release: id 3 | task 4160 | stop processing: n_tokens = 1413, truncated = 0 22.29.044.639 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.811 22.29.044.672 I slot launch_slot_: id 3 | task 4338 | processing task, is_child = 0 22.33.876.339 I slot print_timing: id 0 | task 4251 | prompt eval time = 2063.22 ms / 120 tokens ( 17.19 ms per token, 58.16 tokens per second) 22.33.876.345 I slot print_timing: id 0 | task 4251 | eval time = 25228.10 ms / 100 tokens ( 254.83 ms per token, 3.92 tokens per second) 22.33.876.345 I slot print_timing: id 0 | task 4251 | total time = 27291.32 ms / 220 tokens 22.33.876.346 I slot print_timing: id 0 | task 4251 | graphs reused = 3628 22.33.876.346 I slot print_timing: id 0 | task 4251 | graph reallocs = 0 / 0 (same size) / (changed size) 22.33.876.395 I slot release: id 0 | task 4251 | stop processing: n_tokens = 1344, truncated = 0 22.34.071.261 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.853 22.34.071.294 I slot launch_slot_: id 0 | task 4357 | processing task, is_child = 0 22.43.997.704 I slot print_timing: id 2 | task 4314 | prompt eval time = 1929.19 ms / 97 tokens ( 19.89 ms per token, 50.28 tokens per second) 22.43.997.710 I slot print_timing: id 2 | task 4314 | eval time = 19238.47 ms / 77 tokens ( 253.14 ms per token, 3.95 tokens per second) 22.43.997.711 I slot print_timing: id 2 | task 4314 | total time = 21167.66 ms / 174 tokens 22.43.997.711 I slot print_timing: id 2 | task 4314 | graphs reused = 3663 22.43.997.711 I slot print_timing: id 2 | task 4314 | graph reallocs = 0 / 0 (same size) / (changed size) 22.43.997.753 I slot release: id 2 | task 4314 | stop processing: n_tokens = 1298, truncated = 0 22.44.277.613 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.883 22.44.277.644 I slot launch_slot_: id 2 | task 4396 | processing task, is_child = 0 22.46.064.189 I slot print_timing: id 1 | task 4292 | n_gen = 100, tg = 3.64 t/s, tg_3s = 3.68 t/s 22.49.196.678 I slot print_timing: id 1 | task 4292 | n_gen = 114, tg = 3.73 t/s, tg_3s = 4.47 t/s 22.50.629.005 I slot print_timing: id 3 | task 4338 | prompt eval time = 1762.80 ms / 100 tokens ( 17.63 ms per token, 56.73 tokens per second) 22.50.629.010 I slot print_timing: id 3 | task 4338 | eval time = 19821.53 ms / 77 tokens ( 260.81 ms per token, 3.83 tokens per second) 22.50.629.011 I slot print_timing: id 3 | task 4338 | total time = 21584.33 ms / 177 tokens 22.50.629.011 I slot print_timing: id 3 | task 4338 | graphs reused = 3682 22.50.629.011 I slot print_timing: id 3 | task 4338 | graph reallocs = 0 / 0 (same size) / (changed size) 22.50.629.055 I slot release: id 3 | task 4338 | stop processing: n_tokens = 1301, truncated = 0 22.50.823.402 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.881 22.50.823.453 I slot launch_slot_: id 3 | task 4420 | processing task, is_child = 0 22.52.517.421 I slot print_timing: id 1 | task 4292 | n_gen = 123, tg = 3.63 t/s, tg_3s = 2.71 t/s 22.53.928.734 I slot print_timing: id 1 | task 4292 | prompt eval time = 2372.59 ms / 108 tokens ( 21.97 ms per token, 45.52 tokens per second) 22.53.928.739 I slot print_timing: id 1 | task 4292 | eval time = 35061.64 ms / 129 tokens ( 273.92 ms per token, 3.65 tokens per second) 22.53.928.740 I slot print_timing: id 1 | task 4292 | total time = 37434.23 ms / 237 tokens 22.53.928.740 I slot print_timing: id 1 | task 4292 | graphs reused = 3686 22.53.928.741 I slot print_timing: id 1 | task 4292 | graph reallocs = 0 / 0 (same size) / (changed size) 22.53.928.795 I slot release: id 1 | task 4292 | stop processing: n_tokens = 1361, truncated = 0 22.54.208.262 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.842 22.54.208.296 I slot launch_slot_: id 1 | task 4429 | processing task, is_child = 0 23.02.710.390 I slot print_timing: id 0 | task 4357 | n_gen = 100, tg = 3.83 t/s, tg_3s = 3.87 t/s 23.05.777.915 I slot print_timing: id 0 | task 4357 | n_gen = 115, tg = 3.94 t/s, tg_3s = 4.89 t/s 23.08.845.395 I slot print_timing: id 0 | task 4357 | n_gen = 130, tg = 4.03 t/s, tg_3s = 4.89 t/s 23.10.481.592 I slot print_timing: id 2 | task 4396 | n_gen = 100, tg = 4.13 t/s, tg_3s = 4.18 t/s 23.10.686.234 I slot print_timing: id 3 | task 4420 | prompt eval time = 2080.76 ms / 114 tokens ( 18.25 ms per token, 54.79 tokens per second) 23.10.686.239 I slot print_timing: id 3 | task 4420 | eval time = 17782.01 ms / 78 tokens ( 230.94 ms per token, 4.33 tokens per second) 23.10.686.239 I slot print_timing: id 3 | task 4420 | total time = 19862.77 ms / 192 tokens 23.10.686.240 I slot print_timing: id 3 | task 4420 | graphs reused = 3754 23.10.686.240 I slot print_timing: id 3 | task 4420 | graph reallocs = 0 / 0 (same size) / (changed size) 23.10.686.286 I slot release: id 3 | task 4420 | stop processing: n_tokens = 1316, truncated = 0 23.10.880.590 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.871 23.10.880.623 I slot launch_slot_: id 3 | task 4502 | processing task, is_child = 0 23.12.576.804 I slot print_timing: id 0 | task 4357 | n_gen = 141, tg = 3.92 t/s, tg_3s = 2.95 t/s 23.13.578.359 I slot print_timing: id 2 | task 4396 | n_gen = 107, tg = 3.92 t/s, tg_3s = 2.26 t/s 23.15.622.119 I slot print_timing: id 0 | task 4357 | n_gen = 155, tg = 3.97 t/s, tg_3s = 4.60 t/s 23.16.644.547 I slot print_timing: id 2 | task 4396 | n_gen = 122, tg = 4.02 t/s, tg_3s = 4.89 t/s 23.18.484.836 I slot print_timing: id 1 | task 4429 | n_gen = 100, tg = 4.52 t/s, tg_3s = 4.56 t/s 23.18.689.252 I slot print_timing: id 0 | task 4357 | n_gen = 170, tg = 4.04 t/s, tg_3s = 4.89 t/s 23.19.712.015 I slot print_timing: id 2 | task 4396 | n_gen = 137, tg = 4.10 t/s, tg_3s = 4.89 t/s 23.21.553.381 I slot print_timing: id 1 | task 4429 | n_gen = 115, tg = 4.56 t/s, tg_3s = 4.89 t/s 23.21.757.768 I slot print_timing: id 0 | task 4357 | n_gen = 185, tg = 4.10 t/s, tg_3s = 4.89 t/s 23.22.781.071 I slot print_timing: id 2 | task 4396 | n_gen = 152, tg = 4.17 t/s, tg_3s = 4.89 t/s 23.23.599.354 I slot print_timing: id 1 | task 4429 | prompt eval time = 2366.63 ms / 104 tokens ( 22.76 ms per token, 43.94 tokens per second) 23.23.599.359 I slot print_timing: id 1 | task 4429 | eval time = 27024.42 ms / 125 tokens ( 217.94 ms per token, 4.59 tokens per second) 23.23.599.359 I slot print_timing: id 1 | task 4429 | total time = 29391.05 ms / 229 tokens 23.23.599.360 I slot print_timing: id 1 | task 4429 | graphs reused = 3805 23.23.599.360 I slot print_timing: id 1 | task 4429 | graph reallocs = 0 / 0 (same size) / (changed size) 23.23.599.405 I slot release: id 1 | task 4429 | stop processing: n_tokens = 1353, truncated = 0 23.23.879.288 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.945 (> 0.100 thold), f_keep = 0.847 23.23.879.323 I slot launch_slot_: id 1 | task 4558 | processing task, is_child = 0 23.25.392.361 I slot print_timing: id 0 | task 4357 | n_gen = 196, tg = 4.02 t/s, tg_3s = 3.03 t/s 23.25.926.824 I slot print_timing: id 2 | task 4396 | n_gen = 159, tg = 4.01 t/s, tg_3s = 2.23 t/s 23.28.587.980 I slot print_timing: id 0 | task 4357 | n_gen = 210, tg = 4.04 t/s, tg_3s = 4.38 t/s 23.28.997.179 I slot print_timing: id 2 | task 4396 | n_gen = 174, tg = 4.07 t/s, tg_3s = 4.89 t/s 23.30.633.862 I slot print_timing: id 3 | task 4502 | prompt eval time = 2081.73 ms / 117 tokens ( 17.79 ms per token, 56.20 tokens per second) 23.30.633.867 I slot print_timing: id 3 | task 4502 | eval time = 17671.50 ms / 79 tokens ( 226.56 ms per token, 4.41 tokens per second) 23.30.633.868 I slot print_timing: id 3 | task 4502 | total time = 19753.23 ms / 196 tokens 23.30.633.868 I slot print_timing: id 3 | task 4502 | graphs reused = 3827 23.30.633.869 I slot print_timing: id 3 | task 4502 | graph reallocs = 0 / 0 (same size) / (changed size) 23.30.633.912 I slot release: id 3 | task 4502 | stop processing: n_tokens = 1320, truncated = 0 23.30.828.077 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.868 23.30.828.105 I slot launch_slot_: id 3 | task 4585 | processing task, is_child = 0 23.32.536.625 I slot print_timing: id 0 | task 4357 | n_gen = 222, tg = 3.97 t/s, tg_3s = 3.04 t/s 23.32.537.021 I slot print_timing: id 2 | task 4396 | n_gen = 184, tg = 3.98 t/s, tg_3s = 2.82 t/s 23.33.538.349 I slot print_timing: id 2 | task 4396 | prompt eval time = 2257.94 ms / 119 tokens ( 18.97 ms per token, 52.70 tokens per second) 23.33.538.354 I slot print_timing: id 2 | task 4396 | eval time = 47002.75 ms / 188 tokens ( 251.35 ms per token, 3.98 tokens per second) 23.33.538.355 I slot print_timing: id 2 | task 4396 | total time = 49260.70 ms / 307 tokens 23.33.538.355 I slot print_timing: id 2 | task 4396 | graphs reused = 3829 23.33.538.356 I slot print_timing: id 2 | task 4396 | graph reallocs = 0 / 0 (same size) / (changed size) 23.33.538.401 I slot release: id 2 | task 4396 | stop processing: n_tokens = 1431, truncated = 0 23.33.817.809 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.801 23.33.817.846 I slot launch_slot_: id 2 | task 4592 | processing task, is_child = 0 23.35.736.896 I slot print_timing: id 0 | task 4357 | n_gen = 229, tg = 3.87 t/s, tg_3s = 2.19 t/s 23.38.808.954 I slot print_timing: id 0 | task 4357 | n_gen = 244, tg = 3.92 t/s, tg_3s = 4.88 t/s 23.41.876.827 I slot print_timing: id 0 | task 4357 | n_gen = 259, tg = 3.97 t/s, tg_3s = 4.89 t/s 23.44.945.604 I slot print_timing: id 0 | task 4357 | n_gen = 274, tg = 4.01 t/s, tg_3s = 4.89 t/s 23.45.559.095 I slot print_timing: id 1 | task 4558 | prompt eval time = 2047.35 ms / 88 tokens ( 23.27 ms per token, 42.98 tokens per second) 23.45.559.100 I slot print_timing: id 1 | task 4558 | eval time = 19632.41 ms / 81 tokens ( 245.41 ms per token, 4.07 tokens per second) 23.45.559.101 I slot print_timing: id 1 | task 4558 | total time = 21679.77 ms / 169 tokens 23.45.559.101 I slot print_timing: id 1 | task 4558 | graphs reused = 3875 23.45.559.101 I slot print_timing: id 1 | task 4558 | graph reallocs = 0 / 0 (same size) / (changed size) 23.45.559.147 I slot release: id 1 | task 4558 | stop processing: n_tokens = 1293, truncated = 0 23.45.839.186 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.886 23.45.839.223 I slot launch_slot_: id 1 | task 4644 | processing task, is_child = 0 23.48.050.855 I slot print_timing: id 0 | task 4357 | n_gen = 279, tg = 3.90 t/s, tg_3s = 1.61 t/s 23.51.245.954 I slot print_timing: id 0 | task 4357 | n_gen = 293, tg = 3.92 t/s, tg_3s = 4.38 t/s 23.54.315.171 I slot print_timing: id 0 | task 4357 | n_gen = 308, tg = 3.96 t/s, tg_3s = 4.89 t/s 23.54.928.777 I slot print_timing: id 0 | task 4357 | prompt eval time = 2768.66 ms / 172 tokens ( 16.10 ms per token, 62.12 tokens per second) 23.54.928.783 I slot print_timing: id 0 | task 4357 | eval time = 78088.82 ms / 311 tokens ( 251.90 ms per token, 3.97 tokens per second) 23.54.928.783 I slot print_timing: id 0 | task 4357 | total time = 80857.48 ms / 483 tokens 23.54.928.784 I slot print_timing: id 0 | task 4357 | graphs reused = 3905 23.54.928.784 I slot print_timing: id 0 | task 4357 | graph reallocs = 0 / 0 (same size) / (changed size) 23.54.928.831 I slot release: id 0 | task 4357 | stop processing: n_tokens = 1607, truncated = 0 23.55.123.129 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.713 23.55.123.162 I slot launch_slot_: id 0 | task 4679 | processing task, is_child = 0 23.58.207.904 I slot print_timing: id 2 | task 4592 | prompt eval time = 1919.47 ms / 87 tokens ( 22.06 ms per token, 45.33 tokens per second) 23.58.207.909 I slot print_timing: id 2 | task 4592 | eval time = 22470.58 ms / 91 tokens ( 249.67 ms per token, 4.01 tokens per second) 23.58.207.910 I slot print_timing: id 2 | task 4592 | total time = 24390.05 ms / 178 tokens 23.58.207.910 I slot print_timing: id 2 | task 4592 | graphs reused = 3910 23.58.207.911 I slot print_timing: id 2 | task 4592 | graph reallocs = 0 / 0 (same size) / (changed size) 23.58.207.953 I slot release: id 2 | task 4592 | stop processing: n_tokens = 1302, truncated = 0 23.58.487.450 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.880 23.58.487.494 I slot launch_slot_: id 2 | task 4688 | processing task, is_child = 0 24.00.733.447 I slot print_timing: id 3 | task 4585 | n_gen = 100, tg = 3.56 t/s, tg_3s = 3.60 t/s 24.03.802.949 I slot print_timing: id 3 | task 4585 | n_gen = 115, tg = 3.69 t/s, tg_3s = 4.89 t/s 24.06.869.090 I slot print_timing: id 3 | task 4585 | n_gen = 130, tg = 3.80 t/s, tg_3s = 4.89 t/s 24.09.730.841 I slot print_timing: id 3 | task 4585 | prompt eval time = 2094.18 ms / 129 tokens ( 16.23 ms per token, 61.60 tokens per second) 24.09.730.844 I slot print_timing: id 3 | task 4585 | eval time = 36808.55 ms / 144 tokens ( 257.40 ms per token, 3.88 tokens per second) 24.09.730.844 I slot print_timing: id 3 | task 4585 | total time = 38902.73 ms / 273 tokens 24.09.730.845 I slot print_timing: id 3 | task 4585 | graphs reused = 3953 24.09.730.845 I slot print_timing: id 3 | task 4585 | graph reallocs = 0 / 0 (same size) / (changed size) 24.09.730.898 I slot release: id 3 | task 4585 | stop processing: n_tokens = 1397, truncated = 0 24.09.924.685 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.820 24.09.924.722 I slot launch_slot_: id 3 | task 4736 | processing task, is_child = 0 24.14.406.401 I slot print_timing: id 1 | task 4644 | n_gen = 100, tg = 3.83 t/s, tg_3s = 3.87 t/s 24.17.472.784 I slot print_timing: id 1 | task 4644 | n_gen = 115, tg = 3.95 t/s, tg_3s = 4.89 t/s 24.19.108.017 I slot print_timing: id 0 | task 4679 | prompt eval time = 2061.21 ms / 118 tokens ( 17.47 ms per token, 57.25 tokens per second) 24.19.108.022 I slot print_timing: id 0 | task 4679 | eval time = 21923.64 ms / 89 tokens ( 249.13 ms per token, 4.01 tokens per second) 24.19.108.023 I slot print_timing: id 0 | task 4679 | total time = 23984.85 ms / 207 tokens 24.19.108.023 I slot print_timing: id 0 | task 4679 | graphs reused = 3985 24.19.108.024 I slot print_timing: id 0 | task 4679 | graph reallocs = 0 / 0 (same size) / (changed size) 24.19.108.068 I slot release: id 0 | task 4679 | stop processing: n_tokens = 1331, truncated = 0 24.19.302.877 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.942 (> 0.100 thold), f_keep = 0.861 24.19.302.907 I slot launch_slot_: id 0 | task 4773 | processing task, is_child = 0 24.20.654.427 I slot print_timing: id 1 | task 4644 | n_gen = 125, tg = 3.87 t/s, tg_3s = 3.14 t/s 24.21.644.322 I slot print_timing: id 1 | task 4644 | prompt eval time = 2745.27 ms / 152 tokens ( 18.06 ms per token, 55.37 tokens per second) 24.21.644.328 I slot print_timing: id 1 | task 4644 | eval time = 33059.82 ms / 129 tokens ( 258.28 ms per token, 3.87 tokens per second) 24.21.644.328 I slot print_timing: id 1 | task 4644 | total time = 35805.09 ms / 281 tokens 24.21.644.329 I slot print_timing: id 1 | task 4644 | graphs reused = 3988 24.21.644.329 I slot print_timing: id 1 | task 4644 | graph reallocs = 0 / 0 (same size) / (changed size) 24.21.644.373 I slot release: id 1 | task 4644 | stop processing: n_tokens = 1405, truncated = 0 24.21.923.878 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.816 24.21.923.917 I slot launch_slot_: id 1 | task 4780 | processing task, is_child = 0 24.26.351.922 I slot print_timing: id 2 | task 4688 | n_gen = 100, tg = 3.86 t/s, tg_3s = 3.90 t/s 24.29.415.403 I slot print_timing: id 2 | task 4688 | n_gen = 115, tg = 3.97 t/s, tg_3s = 4.90 t/s 24.32.481.291 I slot print_timing: id 2 | task 4688 | n_gen = 130, tg = 4.06 t/s, tg_3s = 4.89 t/s 24.33.503.602 I slot print_timing: id 3 | task 4736 | prompt eval time = 2435.07 ms / 135 tokens ( 18.04 ms per token, 55.44 tokens per second) 24.33.503.608 I slot print_timing: id 3 | task 4736 | eval time = 21143.80 ms / 88 tokens ( 243.03 ms per token, 4.11 tokens per second) 24.33.503.608 I slot print_timing: id 3 | task 4736 | total time = 23578.87 ms / 223 tokens 24.33.503.609 I slot print_timing: id 3 | task 4736 | graphs reused = 4032 24.33.503.609 I slot print_timing: id 3 | task 4736 | graph reallocs = 0 / 0 (same size) / (changed size) 24.33.503.657 I slot release: id 3 | task 4736 | stop processing: n_tokens = 1347, truncated = 0 24.33.697.973 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.851 24.33.698.000 I slot launch_slot_: id 3 | task 4829 | processing task, is_child = 0 24.35.796.010 I slot print_timing: id 2 | task 4688 | n_gen = 138, tg = 3.91 t/s, tg_3s = 2.41 t/s 24.38.863.244 I slot print_timing: id 2 | task 4688 | n_gen = 153, tg = 3.99 t/s, tg_3s = 4.89 t/s 24.41.519.978 I slot print_timing: id 0 | task 4773 | prompt eval time = 1725.59 ms / 92 tokens ( 18.76 ms per token, 53.32 tokens per second) 24.41.519.980 I slot print_timing: id 0 | task 4773 | eval time = 20491.47 ms / 83 tokens ( 249.90 ms per token, 4.00 tokens per second) 24.41.519.981 I slot print_timing: id 0 | task 4773 | total time = 22217.06 ms / 175 tokens 24.41.519.981 I slot print_timing: id 0 | task 4773 | graphs reused = 4059 24.41.519.981 I slot print_timing: id 0 | task 4773 | graph reallocs = 0 / 0 (same size) / (changed size) 24.41.520.024 I slot release: id 0 | task 4773 | stop processing: n_tokens = 1299, truncated = 0 24.41.714.724 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.882 24.41.714.760 I slot launch_slot_: id 0 | task 4861 | processing task, is_child = 0 24.43.070.734 I slot print_timing: id 2 | task 4688 | n_gen = 168, tg = 3.94 t/s, tg_3s = 3.57 t/s 24.46.103.861 I slot print_timing: id 1 | task 4780 | prompt eval time = 2381.72 ms / 120 tokens ( 19.85 ms per token, 50.38 tokens per second) 24.46.103.867 I slot print_timing: id 1 | task 4780 | eval time = 21798.21 ms / 93 tokens ( 236.94 ms per token, 4.22 tokens per second) 24.46.103.868 I slot print_timing: id 1 | task 4780 | total time = 24179.94 ms / 213 tokens 24.46.103.868 I slot print_timing: id 1 | task 4780 | graphs reused = 4072 24.46.103.868 I slot print_timing: id 1 | task 4780 | graph reallocs = 0 / 0 (same size) / (changed size) 24.46.103.911 I slot release: id 1 | task 4780 | stop processing: n_tokens = 1337, truncated = 0 24.46.104.067 I slot print_timing: id 2 | task 4688 | n_gen = 182, tg = 3.99 t/s, tg_3s = 4.62 t/s 24.46.383.146 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.857 24.46.383.182 I slot launch_slot_: id 1 | task 4878 | processing task, is_child = 0 24.49.253.965 I slot print_timing: id 2 | task 4688 | n_gen = 189, tg = 3.87 t/s, tg_3s = 2.22 t/s 24.52.318.913 I slot print_timing: id 2 | task 4688 | n_gen = 204, tg = 3.94 t/s, tg_3s = 4.89 t/s 24.55.385.446 I slot print_timing: id 2 | task 4688 | n_gen = 219, tg = 3.99 t/s, tg_3s = 4.89 t/s 24.58.451.537 I slot print_timing: id 2 | task 4688 | n_gen = 234, tg = 4.04 t/s, tg_3s = 4.89 t/s 24.59.064.627 I slot print_timing: id 3 | task 4829 | n_gen = 100, tg = 4.25 t/s, tg_3s = 4.30 t/s 25.01.518.961 I slot print_timing: id 2 | task 4688 | n_gen = 249, tg = 4.08 t/s, tg_3s = 4.89 t/s 25.02.132.289 I slot print_timing: id 3 | task 4829 | n_gen = 115, tg = 4.33 t/s, tg_3s = 4.89 t/s 25.04.585.812 I slot print_timing: id 2 | task 4688 | n_gen = 264, tg = 4.12 t/s, tg_3s = 4.89 t/s 25.05.199.410 I slot print_timing: id 3 | task 4829 | n_gen = 130, tg = 4.39 t/s, tg_3s = 4.89 t/s 25.05.403.616 I slot print_timing: id 0 | task 4861 | n_gen = 100, tg = 4.51 t/s, tg_3s = 4.55 t/s 25.07.654.312 I slot print_timing: id 2 | task 4688 | n_gen = 279, tg = 4.15 t/s, tg_3s = 4.89 t/s 25.08.267.005 I slot print_timing: id 3 | task 4829 | n_gen = 145, tg = 4.43 t/s, tg_3s = 4.89 t/s 25.08.471.274 I slot print_timing: id 0 | task 4861 | n_gen = 115, tg = 4.56 t/s, tg_3s = 4.89 t/s 25.08.676.196 I slot print_timing: id 1 | task 4878 | n_gen = 100, tg = 4.89 t/s, tg_3s = 4.94 t/s 25.10.722.311 I slot print_timing: id 2 | task 4688 | n_gen = 294, tg = 4.19 t/s, tg_3s = 4.89 t/s 25.11.336.163 I slot print_timing: id 3 | task 4829 | n_gen = 160, tg = 4.47 t/s, tg_3s = 4.89 t/s 25.11.540.538 I slot print_timing: id 0 | task 4861 | n_gen = 130, tg = 4.59 t/s, tg_3s = 4.89 t/s 25.11.540.681 I slot print_timing: id 1 | task 4878 | prompt eval time = 2051.52 ms / 98 tokens ( 20.93 ms per token, 47.77 tokens per second) 25.11.540.682 I slot print_timing: id 1 | task 4878 | eval time = 23105.97 ms / 114 tokens ( 204.48 ms per token, 4.89 tokens per second) 25.11.540.683 I slot print_timing: id 1 | task 4878 | total time = 25157.49 ms / 212 tokens 25.11.540.683 I slot print_timing: id 1 | task 4878 | graphs reused = 4184 25.11.540.684 I slot print_timing: id 1 | task 4878 | graph reallocs = 0 / 0 (same size) / (changed size) 25.11.540.728 I slot release: id 1 | task 4878 | stop processing: n_tokens = 1336, truncated = 0 25.11.820.971 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.858 25.11.821.003 I slot launch_slot_: id 1 | task 4995 | processing task, is_child = 0 25.14.198.122 I slot print_timing: id 2 | task 4688 | n_gen = 301, tg = 4.08 t/s, tg_3s = 2.01 t/s 25.14.405.629 I slot print_timing: id 3 | task 4829 | n_gen = 165, tg = 4.25 t/s, tg_3s = 1.63 t/s 25.14.612.136 I slot print_timing: id 0 | task 4861 | n_gen = 135, tg = 4.30 t/s, tg_3s = 1.63 t/s 25.16.248.922 I slot print_timing: id 0 | task 4861 | prompt eval time = 1730.10 ms / 95 tokens ( 18.21 ms per token, 54.91 tokens per second) 25.16.248.924 I slot print_timing: id 0 | task 4861 | eval time = 32804.05 ms / 143 tokens ( 231.01 ms per token, 4.33 tokens per second) 25.16.248.924 I slot print_timing: id 0 | task 4861 | total time = 34534.15 ms / 238 tokens 25.16.248.925 I slot print_timing: id 0 | task 4861 | graphs reused = 4192 25.16.248.925 I slot print_timing: id 0 | task 4861 | graph reallocs = 0 / 0 (same size) / (changed size) 25.16.248.971 I slot release: id 0 | task 4861 | stop processing: n_tokens = 1362, truncated = 0 25.16.443.780 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.841 25.16.443.813 I slot launch_slot_: id 0 | task 5009 | processing task, is_child = 0 25.18.138.732 I slot print_timing: id 2 | task 4688 | n_gen = 313, tg = 4.03 t/s, tg_3s = 3.05 t/s 25.18.138.892 I slot print_timing: id 3 | task 4829 | n_gen = 176, tg = 4.13 t/s, tg_3s = 2.95 t/s 25.21.175.030 I slot print_timing: id 2 | task 4688 | n_gen = 327, tg = 4.05 t/s, tg_3s = 4.61 t/s 25.21.175.186 I slot print_timing: id 3 | task 4829 | n_gen = 190, tg = 4.16 t/s, tg_3s = 4.61 t/s 25.22.812.121 I slot print_timing: id 2 | task 4688 | prompt eval time = 2245.79 ms / 110 tokens ( 20.42 ms per token, 48.98 tokens per second) 25.22.812.126 I slot print_timing: id 2 | task 4688 | eval time = 82078.83 ms / 335 tokens ( 245.74 ms per token, 4.07 tokens per second) 25.22.812.127 I slot print_timing: id 2 | task 4688 | total time = 84324.62 ms / 445 tokens 25.22.812.127 I slot print_timing: id 2 | task 4688 | graphs reused = 4213 25.22.812.128 I slot print_timing: id 2 | task 4688 | graph reallocs = 0 / 0 (same size) / (changed size) 25.22.812.172 I slot release: id 2 | task 4688 | stop processing: n_tokens = 1569, truncated = 0 25.23.090.978 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.730 25.23.091.017 I slot launch_slot_: id 2 | task 5034 | processing task, is_child = 0 25.24.861.816 I slot print_timing: id 3 | task 4829 | n_gen = 200, tg = 4.06 t/s, tg_3s = 2.71 t/s 25.27.989.208 I slot print_timing: id 3 | task 4829 | n_gen = 214, tg = 4.08 t/s, tg_3s = 4.48 t/s 25.31.055.687 I slot print_timing: id 3 | task 4829 | n_gen = 229, tg = 4.13 t/s, tg_3s = 4.89 t/s 25.34.123.259 I slot print_timing: id 3 | task 4829 | n_gen = 244, tg = 4.17 t/s, tg_3s = 4.89 t/s 25.37.190.815 I slot print_timing: id 3 | task 4829 | n_gen = 259, tg = 4.20 t/s, tg_3s = 4.89 t/s 25.38.008.714 I slot print_timing: id 1 | task 4995 | n_gen = 100, tg = 4.16 t/s, tg_3s = 4.20 t/s 25.40.258.608 I slot print_timing: id 3 | task 4829 | n_gen = 274, tg = 4.24 t/s, tg_3s = 4.89 t/s 25.40.667.206 I slot print_timing: id 0 | task 5009 | n_gen = 100, tg = 4.47 t/s, tg_3s = 4.51 t/s 25.41.076.082 I slot print_timing: id 1 | task 4995 | n_gen = 115, tg = 4.24 t/s, tg_3s = 4.89 t/s 25.43.330.288 I slot print_timing: id 3 | task 4829 | n_gen = 289, tg = 4.26 t/s, tg_3s = 4.88 t/s 25.43.739.156 I slot print_timing: id 0 | task 5009 | n_gen = 115, tg = 4.52 t/s, tg_3s = 4.88 t/s 25.44.148.433 I slot print_timing: id 1 | task 4995 | n_gen = 130, tg = 4.31 t/s, tg_3s = 4.88 t/s 25.44.353.075 I slot print_timing: id 1 | task 4995 | prompt eval time = 2376.97 ms / 116 tokens ( 20.49 ms per token, 48.80 tokens per second) 25.44.353.078 I slot print_timing: id 1 | task 4995 | eval time = 30155.09 ms / 131 tokens ( 231.96 ms per token, 4.31 tokens per second) 25.44.353.079 I slot print_timing: id 1 | task 4995 | total time = 32532.07 ms / 247 tokens 25.44.353.080 I slot print_timing: id 1 | task 4995 | graphs reused = 4304 25.44.353.080 I slot print_timing: id 1 | task 4995 | graph reallocs = 0 / 0 (same size) / (changed size) 25.44.353.129 I slot release: id 1 | task 4995 | stop processing: n_tokens = 1371, truncated = 0 25.44.633.086 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.836 25.44.633.135 I slot launch_slot_: id 1 | task 5131 | processing task, is_child = 0 25.46.485.842 I slot print_timing: id 3 | task 4829 | n_gen = 296, tg = 4.17 t/s, tg_3s = 2.22 t/s 25.47.019.229 I slot print_timing: id 0 | task 5009 | n_gen = 121, tg = 4.21 t/s, tg_3s = 1.83 t/s 25.47.635.502 I slot print_timing: id 2 | task 5034 | n_gen = 100, tg = 4.44 t/s, tg_3s = 4.48 t/s 25.48.044.309 I slot print_timing: id 0 | task 5009 | prompt eval time = 2069.95 ms / 130 tokens ( 15.92 ms per token, 62.80 tokens per second) 25.48.044.311 I slot print_timing: id 0 | task 5009 | eval time = 29530.53 ms / 126 tokens ( 236.24 ms per token, 4.23 tokens per second) 25.48.044.312 I slot print_timing: id 0 | task 5009 | total time = 31600.49 ms / 256 tokens 25.48.044.312 I slot print_timing: id 0 | task 5009 | graphs reused = 4308 25.48.044.313 I slot print_timing: id 0 | task 5009 | graph reallocs = 0 / 0 (same size) / (changed size) 25.48.044.364 I slot release: id 0 | task 5009 | stop processing: n_tokens = 1380, truncated = 0 25.48.238.776 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.911 (> 0.100 thold), f_keep = 0.830 25.48.238.809 I slot launch_slot_: id 0 | task 5140 | processing task, is_child = 0 25.50.272.206 I slot print_timing: id 3 | task 4829 | n_gen = 304, tg = 4.07 t/s, tg_3s = 2.11 t/s 25.50.647.874 I slot print_timing: id 2 | task 5034 | n_gen = 105, tg = 4.11 t/s, tg_3s = 1.66 t/s 25.53.309.492 I slot print_timing: id 3 | task 4829 | n_gen = 318, tg = 4.09 t/s, tg_3s = 4.61 t/s 25.53.718.265 I slot print_timing: id 2 | task 5034 | n_gen = 120, tg = 4.19 t/s, tg_3s = 4.89 t/s 25.56.377.013 I slot print_timing: id 3 | task 4829 | n_gen = 333, tg = 4.12 t/s, tg_3s = 4.89 t/s 25.56.786.097 I slot print_timing: id 2 | task 5034 | n_gen = 135, tg = 4.26 t/s, tg_3s = 4.89 t/s 25.59.445.083 I slot print_timing: id 3 | task 4829 | n_gen = 348, tg = 4.15 t/s, tg_3s = 4.89 t/s 25.59.854.114 I slot print_timing: id 2 | task 5034 | n_gen = 150, tg = 4.32 t/s, tg_3s = 4.89 t/s 26.02.513.760 I slot print_timing: id 3 | task 4829 | n_gen = 363, tg = 4.17 t/s, tg_3s = 4.89 t/s 26.02.922.807 I slot print_timing: id 2 | task 5034 | n_gen = 165, tg = 4.36 t/s, tg_3s = 4.89 t/s 26.05.583.274 I slot print_timing: id 2 | task 5034 | prompt eval time = 2240.15 ms / 103 tokens ( 21.75 ms per token, 45.98 tokens per second) 26.05.583.279 I slot print_timing: id 2 | task 5034 | eval time = 40252.10 ms / 178 tokens ( 227.41 ms per token, 4.40 tokens per second) 26.05.583.280 I slot print_timing: id 2 | task 5034 | total time = 42492.25 ms / 281 tokens 26.05.583.280 I slot print_timing: id 2 | task 5034 | graphs reused = 4381 26.05.583.281 I slot print_timing: id 2 | task 5034 | graph reallocs = 0 / 0 (same size) / (changed size) 26.05.583.331 I slot release: id 2 | task 5034 | stop processing: n_tokens = 1405, truncated = 0 26.05.583.484 I slot print_timing: id 3 | task 4829 | n_gen = 378, tg = 4.20 t/s, tg_3s = 4.89 t/s 26.05.863.057 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.918 (> 0.100 thold), f_keep = 0.816 26.05.863.089 I slot launch_slot_: id 2 | task 5217 | processing task, is_child = 0 26.08.738.756 I slot print_timing: id 3 | task 4829 | n_gen = 384, tg = 4.12 t/s, tg_3s = 1.90 t/s 26.11.193.216 I slot print_timing: id 1 | task 5131 | n_gen = 100, tg = 4.10 t/s, tg_3s = 4.14 t/s 26.11.807.408 I slot print_timing: id 3 | task 4829 | n_gen = 399, tg = 4.15 t/s, tg_3s = 4.89 t/s 26.12.830.216 I slot print_timing: id 0 | task 5140 | n_gen = 100, tg = 4.46 t/s, tg_3s = 4.51 t/s 26.14.262.587 I slot print_timing: id 1 | task 5131 | n_gen = 115, tg = 4.18 t/s, tg_3s = 4.89 t/s 26.14.877.143 I slot print_timing: id 3 | task 4829 | n_gen = 414, tg = 4.17 t/s, tg_3s = 4.89 t/s 26.15.900.136 I slot print_timing: id 0 | task 5140 | n_gen = 115, tg = 4.51 t/s, tg_3s = 4.89 t/s 26.17.333.064 I slot print_timing: id 1 | task 5131 | n_gen = 130, tg = 4.26 t/s, tg_3s = 4.89 t/s 26.17.947.325 I slot print_timing: id 3 | task 4829 | n_gen = 429, tg = 4.19 t/s, tg_3s = 4.89 t/s 26.18.970.185 I slot print_timing: id 0 | task 5140 | n_gen = 130, tg = 4.55 t/s, tg_3s = 4.89 t/s 26.20.403.109 I slot print_timing: id 1 | task 5131 | n_gen = 145, tg = 4.31 t/s, tg_3s = 4.89 t/s 26.21.017.574 I slot print_timing: id 3 | task 4829 | n_gen = 444, tg = 4.21 t/s, tg_3s = 4.89 t/s 26.22.040.793 I slot print_timing: id 0 | task 5140 | n_gen = 145, tg = 4.59 t/s, tg_3s = 4.89 t/s 26.23.268.903 I slot print_timing: id 1 | task 5131 | prompt eval time = 2386.29 ms / 122 tokens ( 19.56 ms per token, 51.13 tokens per second) 26.23.268.908 I slot print_timing: id 1 | task 5131 | eval time = 36249.47 ms / 159 tokens ( 229.43 ms per token, 4.36 tokens per second) 26.23.268.908 I slot print_timing: id 1 | task 5131 | total time = 38635.76 ms / 281 tokens 26.23.268.909 I slot print_timing: id 1 | task 5131 | graphs reused = 4454 26.23.268.909 I slot print_timing: id 1 | task 5131 | graph reallocs = 0 / 0 (same size) / (changed size) 26.23.268.952 I slot release: id 1 | task 5131 | stop processing: n_tokens = 1405, truncated = 0 26.23.548.738 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.816 26.23.548.778 I slot launch_slot_: id 1 | task 5295 | processing task, is_child = 0 26.25.398.070 I slot print_timing: id 0 | task 5140 | n_gen = 153, tg = 4.37 t/s, tg_3s = 2.38 t/s 26.25.398.361 I slot print_timing: id 3 | task 4829 | n_gen = 457, tg = 4.16 t/s, tg_3s = 2.97 t/s 26.28.595.817 I slot print_timing: id 0 | task 5140 | n_gen = 167, tg = 4.37 t/s, tg_3s = 4.38 t/s 26.28.596.213 I slot print_timing: id 3 | task 4829 | n_gen = 471, tg = 4.17 t/s, tg_3s = 4.38 t/s 26.30.438.284 I slot print_timing: id 2 | task 5217 | n_gen = 100, tg = 4.44 t/s, tg_3s = 4.48 t/s 26.31.666.505 I slot print_timing: id 0 | task 5140 | n_gen = 182, tg = 4.41 t/s, tg_3s = 4.88 t/s 26.31.666.925 I slot print_timing: id 3 | task 4829 | n_gen = 486, tg = 4.19 t/s, tg_3s = 4.88 t/s 26.33.509.136 I slot print_timing: id 2 | task 5217 | n_gen = 115, tg = 4.49 t/s, tg_3s = 4.88 t/s 26.34.737.697 I slot print_timing: id 0 | task 5140 | n_gen = 197, tg = 4.45 t/s, tg_3s = 4.88 t/s 26.34.738.096 I slot print_timing: id 3 | task 4829 | n_gen = 501, tg = 4.20 t/s, tg_3s = 4.88 t/s 26.36.580.731 I slot print_timing: id 2 | task 5217 | n_gen = 130, tg = 4.53 t/s, tg_3s = 4.88 t/s 26.37.194.977 I slot print_timing: id 2 | task 5217 | prompt eval time = 2259.02 ms / 123 tokens ( 18.37 ms per token, 54.45 tokens per second) 26.37.194.982 I slot print_timing: id 2 | task 5217 | eval time = 29072.86 ms / 133 tokens ( 220.25 ms per token, 4.54 tokens per second) 26.37.194.983 I slot print_timing: id 2 | task 5217 | total time = 31331.88 ms / 256 tokens 26.37.194.983 I slot print_timing: id 2 | task 5217 | graphs reused = 4508 26.37.194.984 I slot print_timing: id 2 | task 5217 | graph reallocs = 0 / 0 (same size) / (changed size) 26.37.195.028 I slot release: id 2 | task 5217 | stop processing: n_tokens = 1380, truncated = 0 26.37.475.230 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.830 26.37.475.258 I slot launch_slot_: id 2 | task 5354 | processing task, is_child = 0 26.38.919.791 I slot print_timing: id 0 | task 5140 | n_gen = 211, tg = 4.35 t/s, tg_3s = 3.35 t/s 26.38.920.081 I slot print_timing: id 3 | task 4829 | n_gen = 515, tg = 4.17 t/s, tg_3s = 3.35 t/s 26.40.620.828 I slot print_timing: id 3 | task 4829 | prompt eval time = 2098.20 ms / 131 tokens ( 16.02 ms per token, 62.43 tokens per second) 26.40.620.833 I slot print_timing: id 3 | task 4829 | eval time = 124824.62 ms / 522 tokens ( 239.59 ms per token, 4.17 tokens per second) 26.40.620.833 I slot print_timing: id 3 | task 4829 | total time = 126922.82 ms / 653 tokens 26.40.620.834 I slot print_timing: id 3 | task 4829 | graphs reused = 4513 26.40.620.834 I slot print_timing: id 3 | task 4829 | graph reallocs = 0 / 0 (same size) / (changed size) 26.40.620.879 I slot release: id 3 | task 4829 | stop processing: n_tokens = 1777, truncated = 0 26.40.815.514 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.645 26.40.815.546 I slot launch_slot_: id 3 | task 5364 | processing task, is_child = 0 26.42.184.477 I slot print_timing: id 0 | task 5140 | n_gen = 220, tg = 4.25 t/s, tg_3s = 2.76 t/s 26.45.229.938 I slot print_timing: id 0 | task 5140 | n_gen = 234, tg = 4.27 t/s, tg_3s = 4.60 t/s 26.47.889.369 I slot print_timing: id 0 | task 5140 | prompt eval time = 2408.79 ms / 133 tokens ( 18.11 ms per token, 55.21 tokens per second) 26.47.889.373 I slot print_timing: id 0 | task 5140 | eval time = 57241.76 ms / 247 tokens ( 232.69 ms per token, 4.30 tokens per second) 26.47.889.374 I slot print_timing: id 0 | task 5140 | total time = 59650.55 ms / 380 tokens 26.47.889.374 I slot print_timing: id 0 | task 5140 | graphs reused = 4538 26.47.889.374 I slot print_timing: id 0 | task 5140 | graph reallocs = 0 / 0 (same size) / (changed size) 26.47.889.427 I slot release: id 0 | task 5140 | stop processing: n_tokens = 1504, truncated = 0 26.48.084.195 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.762 26.48.084.223 I slot launch_slot_: id 0 | task 5394 | processing task, is_child = 0 26.51.121.980 I slot print_timing: id 1 | task 5295 | n_gen = 100, tg = 3.93 t/s, tg_3s = 3.97 t/s 26.54.188.982 I slot print_timing: id 1 | task 5295 | n_gen = 115, tg = 4.03 t/s, tg_3s = 4.89 t/s 26.57.255.742 I slot print_timing: id 1 | task 5295 | n_gen = 130, tg = 4.12 t/s, tg_3s = 4.89 t/s 26.59.914.523 I slot print_timing: id 3 | task 5364 | prompt eval time = 1754.12 ms / 95 tokens ( 18.46 ms per token, 54.16 tokens per second) 26.59.914.528 I slot print_timing: id 3 | task 5364 | eval time = 17344.85 ms / 76 tokens ( 231.26 ms per token, 4.32 tokens per second) 26.59.914.529 I slot print_timing: id 3 | task 5364 | total time = 19098.97 ms / 171 tokens 26.59.914.529 I slot print_timing: id 3 | task 5364 | graphs reused = 4584 26.59.914.530 I slot print_timing: id 3 | task 5364 | graph reallocs = 0 / 0 (same size) / (changed size) 26.59.914.577 I slot release: id 3 | task 5364 | stop processing: n_tokens = 1295, truncated = 0 27.00.109.095 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.944 (> 0.100 thold), f_keep = 0.885 27.00.109.122 I slot launch_slot_: id 3 | task 5444 | processing task, is_child = 0 27.01.472.712 I slot print_timing: id 1 | task 5295 | n_gen = 145, tg = 4.05 t/s, tg_3s = 3.56 t/s 27.04.314.204 I slot print_timing: id 2 | task 5354 | n_gen = 100, tg = 3.97 t/s, tg_3s = 4.01 t/s 27.04.518.509 I slot print_timing: id 1 | task 5295 | n_gen = 159, tg = 4.09 t/s, tg_3s = 4.60 t/s 27.06.154.855 I slot print_timing: id 2 | task 5354 | prompt eval time = 1914.42 ms / 101 tokens ( 18.95 ms per token, 52.76 tokens per second) 27.06.154.861 I slot print_timing: id 2 | task 5354 | eval time = 26765.17 ms / 109 tokens ( 247.83 ms per token, 4.04 tokens per second) 27.06.154.861 I slot print_timing: id 2 | task 5354 | total time = 28679.59 ms / 210 tokens 27.06.154.862 I slot print_timing: id 2 | task 5354 | graphs reused = 4604 27.06.154.862 I slot print_timing: id 2 | task 5354 | graph reallocs = 0 / 0 (same size) / (changed size) 27.06.154.909 I slot release: id 2 | task 5354 | stop processing: n_tokens = 1334, truncated = 0 27.06.434.832 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.859 27.06.434.865 I slot launch_slot_: id 2 | task 5469 | processing task, is_child = 0 27.07.895.898 I slot print_timing: id 1 | task 5295 | n_gen = 169, tg = 4.00 t/s, tg_3s = 2.96 t/s 27.11.028.712 I slot print_timing: id 1 | task 5295 | n_gen = 183, tg = 4.04 t/s, tg_3s = 4.47 t/s 27.13.687.053 I slot print_timing: id 0 | task 5394 | n_gen = 100, tg = 4.27 t/s, tg_3s = 4.31 t/s 27.14.096.370 I slot print_timing: id 1 | task 5295 | n_gen = 198, tg = 4.09 t/s, tg_3s = 4.89 t/s 27.16.346.853 I slot print_timing: id 3 | task 5444 | prompt eval time = 1749.49 ms / 89 tokens ( 19.66 ms per token, 50.87 tokens per second) 27.16.346.859 I slot print_timing: id 3 | task 5444 | eval time = 14488.24 ms / 64 tokens ( 229.97 ms per token, 4.35 tokens per second) 27.16.346.860 I slot print_timing: id 3 | task 5444 | total time = 16237.72 ms / 153 tokens 27.16.346.860 I slot print_timing: id 3 | task 5444 | graphs reused = 4642 27.16.346.860 I slot print_timing: id 3 | task 5444 | graph reallocs = 0 / 0 (same size) / (changed size) 27.16.346.903 I slot release: id 3 | task 5444 | stop processing: n_tokens = 1277, truncated = 0 27.16.541.084 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.942 (> 0.100 thold), f_keep = 0.897 27.16.541.111 I slot launch_slot_: id 3 | task 5512 | processing task, is_child = 0 27.17.907.575 I slot print_timing: id 0 | task 5394 | n_gen = 115, tg = 4.16 t/s, tg_3s = 3.55 t/s 27.17.907.732 I slot print_timing: id 1 | task 5295 | n_gen = 211, tg = 4.04 t/s, tg_3s = 3.41 t/s 27.20.954.781 I slot print_timing: id 0 | task 5394 | n_gen = 129, tg = 4.20 t/s, tg_3s = 4.59 t/s 27.20.954.924 I slot print_timing: id 1 | task 5295 | n_gen = 225, tg = 4.07 t/s, tg_3s = 4.59 t/s 27.24.022.408 I slot print_timing: id 0 | task 5394 | n_gen = 144, tg = 4.27 t/s, tg_3s = 4.89 t/s 27.24.022.550 I slot print_timing: id 1 | task 5295 | n_gen = 240, tg = 4.11 t/s, tg_3s = 4.89 t/s 27.27.090.752 I slot print_timing: id 0 | task 5394 | n_gen = 159, tg = 4.32 t/s, tg_3s = 4.89 t/s 27.27.090.900 I slot print_timing: id 1 | task 5295 | n_gen = 255, tg = 4.15 t/s, tg_3s = 4.89 t/s 27.29.954.961 I slot print_timing: id 2 | task 5469 | n_gen = 100, tg = 4.59 t/s, tg_3s = 4.63 t/s 27.30.159.487 I slot print_timing: id 0 | task 5394 | n_gen = 174, tg = 4.36 t/s, tg_3s = 4.89 t/s 27.30.159.647 I slot print_timing: id 1 | task 5295 | n_gen = 270, tg = 4.19 t/s, tg_3s = 4.89 t/s 27.30.773.335 I slot print_timing: id 2 | task 5469 | prompt eval time = 1932.42 ms / 99 tokens ( 19.52 ms per token, 51.23 tokens per second) 27.30.773.340 I slot print_timing: id 2 | task 5469 | eval time = 22406.04 ms / 104 tokens ( 217.53 ms per token, 4.60 tokens per second) 27.30.773.341 I slot print_timing: id 2 | task 5469 | total time = 24338.46 ms / 203 tokens 27.30.773.341 I slot print_timing: id 2 | task 5469 | graphs reused = 4702 27.30.773.342 I slot print_timing: id 2 | task 5469 | graph reallocs = 0 / 0 (same size) / (changed size) 27.30.773.390 I slot release: id 2 | task 5469 | stop processing: n_tokens = 1327, truncated = 0 27.31.052.919 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.864 27.31.052.948 I slot launch_slot_: id 2 | task 5577 | processing task, is_child = 0 27.33.300.164 I slot print_timing: id 0 | task 5394 | n_gen = 180, tg = 4.18 t/s, tg_3s = 1.91 t/s 27.33.300.369 I slot print_timing: id 1 | task 5295 | n_gen = 276, tg = 4.08 t/s, tg_3s = 1.91 t/s 27.36.372.379 I slot print_timing: id 0 | task 5394 | n_gen = 195, tg = 4.23 t/s, tg_3s = 4.88 t/s 27.36.372.518 I slot print_timing: id 1 | task 5295 | n_gen = 291, tg = 4.12 t/s, tg_3s = 4.88 t/s 27.36.372.799 I slot print_timing: id 3 | task 5512 | prompt eval time = 1752.42 ms / 92 tokens ( 19.05 ms per token, 52.50 tokens per second) 27.36.372.804 I slot print_timing: id 3 | task 5512 | eval time = 18079.26 ms / 80 tokens ( 228.85 ms per token, 4.37 tokens per second) 27.36.372.804 I slot print_timing: id 3 | task 5512 | total time = 19831.68 ms / 172 tokens 27.36.372.805 I slot print_timing: id 3 | task 5512 | graphs reused = 4716 27.36.372.805 I slot print_timing: id 3 | task 5512 | graph reallocs = 0 / 0 (same size) / (changed size) 27.36.372.857 I slot release: id 3 | task 5512 | stop processing: n_tokens = 1296, truncated = 0 27.36.567.117 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.884 27.36.567.150 I slot launch_slot_: id 3 | task 5596 | processing task, is_child = 0 27.39.472.385 I slot print_timing: id 0 | task 5394 | n_gen = 202, tg = 4.10 t/s, tg_3s = 2.26 t/s 27.39.472.527 I slot print_timing: id 1 | task 5295 | n_gen = 298, tg = 4.04 t/s, tg_3s = 2.26 t/s 27.42.541.144 I slot print_timing: id 0 | task 5394 | n_gen = 217, tg = 4.15 t/s, tg_3s = 4.89 t/s 27.42.541.290 I slot print_timing: id 1 | task 5295 | n_gen = 313, tg = 4.07 t/s, tg_3s = 4.89 t/s 27.45.610.210 I slot print_timing: id 0 | task 5394 | n_gen = 232, tg = 4.19 t/s, tg_3s = 4.89 t/s 27.45.610.352 I slot print_timing: id 1 | task 5295 | n_gen = 328, tg = 4.10 t/s, tg_3s = 4.89 t/s 27.48.680.135 I slot print_timing: id 0 | task 5394 | n_gen = 247, tg = 4.23 t/s, tg_3s = 4.89 t/s 27.48.680.273 I slot print_timing: id 1 | task 5295 | n_gen = 343, tg = 4.13 t/s, tg_3s = 4.89 t/s 27.51.748.969 I slot print_timing: id 0 | task 5394 | n_gen = 262, tg = 4.26 t/s, tg_3s = 4.89 t/s 27.51.749.109 I slot print_timing: id 1 | task 5295 | n_gen = 358, tg = 4.16 t/s, tg_3s = 4.89 t/s 27.52.773.040 I slot print_timing: id 2 | task 5577 | prompt eval time = 2247.60 ms / 113 tokens ( 19.89 ms per token, 50.28 tokens per second) 27.52.773.046 I slot print_timing: id 2 | task 5577 | eval time = 19472.49 ms / 88 tokens ( 223.82 ms per token, 4.47 tokens per second) 27.52.773.047 I slot print_timing: id 2 | task 5577 | total time = 21720.08 ms / 201 tokens 27.52.773.047 I slot print_timing: id 2 | task 5577 | graphs reused = 4784 27.52.773.047 I slot print_timing: id 2 | task 5577 | graph reallocs = 0 / 0 (same size) / (changed size) 27.52.773.093 I slot release: id 2 | task 5577 | stop processing: n_tokens = 1325, truncated = 0 27.53.052.802 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.943 (> 0.100 thold), f_keep = 0.865 27.53.052.837 I slot launch_slot_: id 2 | task 5669 | processing task, is_child = 0 27.54.975.946 I slot print_timing: id 0 | task 5394 | n_gen = 270, tg = 4.17 t/s, tg_3s = 2.48 t/s 27.54.976.149 I slot print_timing: id 1 | task 5295 | n_gen = 366, tg = 4.10 t/s, tg_3s = 2.48 t/s 27.55.183.070 I slot print_timing: id 1 | task 5295 | prompt eval time = 2383.66 ms / 118 tokens ( 20.20 ms per token, 49.50 tokens per second) 27.55.183.073 I slot print_timing: id 1 | task 5295 | eval time = 89250.62 ms / 367 tokens ( 243.85 ms per token, 4.10 tokens per second) 27.55.183.073 I slot print_timing: id 1 | task 5295 | total time = 91634.28 ms / 485 tokens 27.55.183.074 I slot print_timing: id 1 | task 5295 | graphs reused = 4784 27.55.183.074 I slot print_timing: id 1 | task 5295 | graph reallocs = 0 / 0 (same size) / (changed size) 27.55.183.119 I slot release: id 1 | task 5295 | stop processing: n_tokens = 1609, truncated = 0 27.55.462.807 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.885 (> 0.100 thold), f_keep = 0.712 27.55.462.840 I slot launch_slot_: id 1 | task 5674 | processing task, is_child = 0 27.58.018.728 I slot print_timing: id 0 | task 5394 | n_gen = 273, tg = 4.03 t/s, tg_3s = 0.99 t/s 28.01.214.174 I slot print_timing: id 0 | task 5394 | n_gen = 287, tg = 4.04 t/s, tg_3s = 4.38 t/s 28.03.259.691 I slot print_timing: id 3 | task 5596 | n_gen = 100, tg = 4.02 t/s, tg_3s = 4.06 t/s 28.03.668.607 I slot print_timing: id 0 | task 5394 | prompt eval time = 2422.66 ms / 152 tokens ( 15.94 ms per token, 62.74 tokens per second) 28.03.668.610 I slot print_timing: id 0 | task 5394 | eval time = 73161.72 ms / 299 tokens ( 245.51 ms per token, 4.07 tokens per second) 28.03.668.611 I slot print_timing: id 0 | task 5394 | total time = 75584.38 ms / 451 tokens 28.03.668.611 I slot print_timing: id 0 | task 5394 | graphs reused = 4808 28.03.668.612 I slot print_timing: id 0 | task 5394 | graph reallocs = 0 / 0 (same size) / (changed size) 28.03.668.656 I slot release: id 0 | task 5394 | stop processing: n_tokens = 1575, truncated = 0 28.03.863.782 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.728 28.03.863.813 I slot launch_slot_: id 0 | task 5703 | processing task, is_child = 0 28.06.325.446 I slot print_timing: id 3 | task 5596 | n_gen = 107, tg = 3.83 t/s, tg_3s = 2.28 t/s 28.09.392.623 I slot print_timing: id 3 | task 5596 | n_gen = 122, tg = 3.94 t/s, tg_3s = 4.89 t/s 28.12.459.433 I slot print_timing: id 3 | task 5596 | n_gen = 137, tg = 4.02 t/s, tg_3s = 4.89 t/s 28.15.526.691 I slot print_timing: id 3 | task 5596 | n_gen = 152, tg = 4.09 t/s, tg_3s = 4.89 t/s 28.16.140.220 I slot print_timing: id 2 | task 5669 | prompt eval time = 1923.52 ms / 90 tokens ( 21.37 ms per token, 46.79 tokens per second) 28.16.140.226 I slot print_timing: id 2 | task 5669 | eval time = 21163.86 ms / 83 tokens ( 258.10 ms per token, 3.87 tokens per second) 28.16.140.226 I slot print_timing: id 2 | task 5669 | total time = 23087.38 ms / 173 tokens 28.16.140.227 I slot print_timing: id 2 | task 5669 | graphs reused = 4858 28.16.140.227 I slot print_timing: id 2 | task 5669 | graph reallocs = 0 / 0 (same size) / (changed size) 28.16.140.275 I slot release: id 2 | task 5669 | stop processing: n_tokens = 1297, truncated = 0 28.16.420.587 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.901 (> 0.100 thold), f_keep = 0.884 28.16.420.621 I slot launch_slot_: id 2 | task 5757 | processing task, is_child = 0 28.18.566.157 I slot print_timing: id 3 | task 5596 | n_gen = 157, tg = 3.91 t/s, tg_3s = 1.65 t/s 28.21.698.615 I slot print_timing: id 3 | task 5596 | n_gen = 171, tg = 3.95 t/s, tg_3s = 4.47 t/s 28.22.517.075 I slot print_timing: id 3 | task 5596 | prompt eval time = 2084.83 ms / 118 tokens ( 17.67 ms per token, 56.60 tokens per second) 28.22.517.081 I slot print_timing: id 3 | task 5596 | eval time = 43865.09 ms / 175 tokens ( 252.10 ms per token, 3.97 tokens per second) 28.22.517.081 I slot print_timing: id 3 | task 5596 | total time = 45949.92 ms / 293 tokens 28.22.517.081 I slot print_timing: id 3 | task 5596 | graphs reused = 4874 28.22.517.082 I slot print_timing: id 3 | task 5596 | graph reallocs = 0 / 0 (same size) / (changed size) 28.22.517.126 I slot release: id 3 | task 5596 | stop processing: n_tokens = 1417, truncated = 0 28.22.711.145 I slot print_timing: id 1 | task 5674 | n_gen = 100, tg = 4.10 t/s, tg_3s = 4.14 t/s 28.22.711.300 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.809 28.22.711.328 I slot launch_slot_: id 3 | task 5778 | processing task, is_child = 0 28.25.808.327 I slot print_timing: id 1 | task 5674 | n_gen = 107, tg = 3.89 t/s, tg_3s = 2.26 t/s 28.28.876.121 I slot print_timing: id 1 | task 5674 | n_gen = 122, tg = 3.99 t/s, tg_3s = 4.89 t/s 28.30.102.267 I slot print_timing: id 0 | task 5703 | n_gen = 100, tg = 4.09 t/s, tg_3s = 4.13 t/s 28.31.942.679 I slot print_timing: id 1 | task 5674 | n_gen = 137, tg = 4.07 t/s, tg_3s = 4.89 t/s 28.33.169.916 I slot print_timing: id 0 | task 5703 | n_gen = 115, tg = 4.18 t/s, tg_3s = 4.89 t/s 28.33.374.486 I slot print_timing: id 1 | task 5674 | prompt eval time = 3089.53 ms / 170 tokens ( 18.17 ms per token, 55.02 tokens per second) 28.33.374.492 I slot print_timing: id 1 | task 5674 | eval time = 34822.11 ms / 144 tokens ( 243.51 ms per token, 4.11 tokens per second) 28.33.374.493 I slot print_timing: id 1 | task 5674 | total time = 37911.64 ms / 314 tokens 28.33.374.493 I slot print_timing: id 1 | task 5674 | graphs reused = 4915 28.33.374.494 I slot print_timing: id 1 | task 5674 | graph reallocs = 0 / 0 (same size) / (changed size) 28.33.374.544 I slot release: id 1 | task 5674 | stop processing: n_tokens = 1438, truncated = 0 28.33.654.075 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.797 28.33.654.106 I slot launch_slot_: id 1 | task 5824 | processing task, is_child = 0 28.36.388.632 I slot print_timing: id 0 | task 5703 | n_gen = 119, tg = 3.87 t/s, tg_3s = 1.24 t/s 28.38.027.524 I slot print_timing: id 0 | task 5703 | prompt eval time = 2050.10 ms / 107 tokens ( 19.16 ms per token, 52.19 tokens per second) 28.38.027.527 I slot print_timing: id 0 | task 5703 | eval time = 32113.60 ms / 127 tokens ( 254.87 ms per token, 3.92 tokens per second) 28.38.027.527 I slot print_timing: id 0 | task 5703 | total time = 34163.70 ms / 234 tokens 28.38.027.528 I slot print_timing: id 0 | task 5703 | graphs reused = 4922 28.38.027.528 I slot print_timing: id 0 | task 5703 | graph reallocs = 0 / 0 (same size) / (changed size) 28.38.027.573 I slot release: id 0 | task 5703 | stop processing: n_tokens = 1358, truncated = 0 28.38.221.930 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.844 28.38.221.966 I slot launch_slot_: id 0 | task 5836 | processing task, is_child = 0 28.43.550.677 I slot print_timing: id 3 | task 5778 | prompt eval time = 2072.27 ms / 109 tokens ( 19.01 ms per token, 52.60 tokens per second) 28.43.550.683 I slot print_timing: id 3 | task 5778 | eval time = 18767.07 ms / 73 tokens ( 260.65 ms per token, 3.84 tokens per second) 28.43.550.683 I slot print_timing: id 3 | task 5778 | total time = 20839.34 ms / 182 tokens 28.43.550.684 I slot print_timing: id 3 | task 5778 | graphs reused = 4938 28.43.550.684 I slot print_timing: id 3 | task 5778 | graph reallocs = 0 / 0 (same size) / (changed size) 28.43.550.728 I slot release: id 3 | task 5778 | stop processing: n_tokens = 1306, truncated = 0 28.43.744.799 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.877 28.43.744.830 I slot launch_slot_: id 3 | task 5856 | processing task, is_child = 0 28.46.996.802 I slot print_timing: id 2 | task 5757 | n_gen = 100, tg = 3.54 t/s, tg_3s = 3.58 t/s 28.50.064.581 I slot print_timing: id 2 | task 5757 | n_gen = 115, tg = 3.67 t/s, tg_3s = 4.89 t/s 28.53.132.151 I slot print_timing: id 2 | task 5757 | n_gen = 130, tg = 3.78 t/s, tg_3s = 4.89 t/s 28.56.198.493 I slot print_timing: id 2 | task 5757 | n_gen = 145, tg = 3.88 t/s, tg_3s = 4.89 t/s 28.56.402.920 I slot print_timing: id 2 | task 5757 | prompt eval time = 2616.89 ms / 147 tokens ( 17.80 ms per token, 56.17 tokens per second) 28.56.402.923 I slot print_timing: id 2 | task 5757 | eval time = 37365.40 ms / 146 tokens ( 257.69 ms per token, 3.88 tokens per second) 28.56.402.924 I slot print_timing: id 2 | task 5757 | total time = 39982.29 ms / 293 tokens 28.56.402.924 I slot print_timing: id 2 | task 5757 | graphs reused = 4987 28.56.402.925 I slot print_timing: id 2 | task 5757 | graph reallocs = 0 / 0 (same size) / (changed size) 28.56.402.975 I slot release: id 2 | task 5757 | stop processing: n_tokens = 1417, truncated = 0 28.56.682.906 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.809 28.56.682.938 I slot launch_slot_: id 2 | task 5910 | processing task, is_child = 0 29.02.219.875 I slot print_timing: id 1 | task 5824 | n_gen = 100, tg = 3.83 t/s, tg_3s = 3.87 t/s 29.04.469.049 I slot print_timing: id 0 | task 5836 | n_gen = 100, tg = 4.09 t/s, tg_3s = 4.13 t/s 29.05.287.105 I slot print_timing: id 1 | task 5824 | n_gen = 115, tg = 3.94 t/s, tg_3s = 4.89 t/s 29.07.536.476 I slot print_timing: id 0 | task 5836 | n_gen = 115, tg = 4.18 t/s, tg_3s = 4.89 t/s 29.08.354.739 I slot print_timing: id 1 | task 5824 | n_gen = 130, tg = 4.04 t/s, tg_3s = 4.89 t/s 29.08.355.059 I slot print_timing: id 3 | task 5856 | n_gen = 100, tg = 4.46 t/s, tg_3s = 4.51 t/s 29.08.968.483 I slot print_timing: id 0 | task 5836 | prompt eval time = 2054.62 ms / 110 tokens ( 18.68 ms per token, 53.54 tokens per second) 29.08.968.491 I slot print_timing: id 0 | task 5836 | eval time = 28691.89 ms / 122 tokens ( 237.12 ms per token, 4.22 tokens per second) 29.08.968.491 I slot print_timing: id 0 | task 5836 | total time = 30746.51 ms / 232 tokens 29.08.968.492 I slot print_timing: id 0 | task 5836 | graphs reused = 5035 29.08.968.492 I slot print_timing: id 0 | task 5836 | graph reallocs = 0 / 0 (same size) / (changed size) 29.08.968.537 I slot release: id 0 | task 5836 | stop processing: n_tokens = 1356, truncated = 0 29.09.162.835 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.845 29.09.162.869 I slot launch_slot_: id 0 | task 5963 | processing task, is_child = 0 29.11.508.962 I slot print_timing: id 1 | task 5824 | n_gen = 139, tg = 3.93 t/s, tg_3s = 2.85 t/s 29.11.509.254 I slot print_timing: id 3 | task 5856 | n_gen = 109, tg = 4.26 t/s, tg_3s = 2.85 t/s 29.14.576.026 I slot print_timing: id 1 | task 5824 | n_gen = 154, tg = 4.01 t/s, tg_3s = 4.89 t/s 29.14.576.321 I slot print_timing: id 3 | task 5856 | n_gen = 124, tg = 4.33 t/s, tg_3s = 4.89 t/s 29.17.234.532 I slot print_timing: id 3 | task 5856 | prompt eval time = 2432.55 ms / 134 tokens ( 18.15 ms per token, 55.09 tokens per second) 29.17.234.535 I slot print_timing: id 3 | task 5856 | eval time = 31057.15 ms / 137 tokens ( 228.36 ms per token, 4.38 tokens per second) 29.17.234.536 I slot print_timing: id 3 | task 5856 | total time = 33489.70 ms / 271 tokens 29.17.234.536 I slot print_timing: id 3 | task 5856 | graphs reused = 5066 29.17.234.537 I slot print_timing: id 3 | task 5856 | graph reallocs = 0 / 0 (same size) / (changed size) 29.17.234.582 I slot release: id 3 | task 5856 | stop processing: n_tokens = 1395, truncated = 0 29.17.429.101 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.822 29.17.429.135 I slot launch_slot_: id 3 | task 5998 | processing task, is_child = 0 29.19.119.449 I slot print_timing: id 1 | task 5824 | n_gen = 169, tg = 3.93 t/s, tg_3s = 3.30 t/s 29.22.165.144 I slot print_timing: id 1 | task 5824 | n_gen = 183, tg = 3.98 t/s, tg_3s = 4.60 t/s 29.22.165.288 I slot print_timing: id 2 | task 5910 | n_gen = 100, tg = 4.26 t/s, tg_3s = 4.31 t/s 29.25.232.512 I slot print_timing: id 1 | task 5824 | n_gen = 198, tg = 4.03 t/s, tg_3s = 4.89 t/s 29.25.232.654 I slot print_timing: id 2 | task 5910 | n_gen = 115, tg = 4.34 t/s, tg_3s = 4.89 t/s 29.28.300.946 I slot print_timing: id 1 | task 5824 | n_gen = 213, tg = 4.08 t/s, tg_3s = 4.89 t/s 29.28.301.090 I slot print_timing: id 2 | task 5910 | n_gen = 130, tg = 4.39 t/s, tg_3s = 4.89 t/s 29.29.937.515 I slot print_timing: id 2 | task 5910 | prompt eval time = 2262.86 ms / 122 tokens ( 18.55 ms per token, 53.91 tokens per second) 29.29.937.521 I slot print_timing: id 2 | task 5910 | eval time = 30991.71 ms / 138 tokens ( 226.22 ms per token, 4.42 tokens per second) 29.29.937.521 I slot print_timing: id 2 | task 5910 | total time = 33254.57 ms / 260 tokens 29.29.937.522 I slot print_timing: id 2 | task 5910 | graphs reused = 5116 29.29.937.522 I slot print_timing: id 2 | task 5910 | graph reallocs = 0 / 0 (same size) / (changed size) 29.29.937.570 I slot release: id 2 | task 5910 | stop processing: n_tokens = 1384, truncated = 0 29.30.217.213 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.828 29.30.217.244 I slot launch_slot_: id 2 | task 6053 | processing task, is_child = 0 29.31.662.116 I slot print_timing: id 1 | task 5824 | n_gen = 223, tg = 4.02 t/s, tg_3s = 2.98 t/s 29.33.770.954 I slot print_timing: id 0 | task 5963 | prompt eval time = 1730.31 ms / 96 tokens ( 18.02 ms per token, 55.48 tokens per second) 29.33.770.959 I slot print_timing: id 0 | task 5963 | eval time = 22877.77 ms / 97 tokens ( 238.31 ms per token, 4.20 tokens per second) 29.33.770.959 I slot print_timing: id 0 | task 5963 | total time = 24608.08 ms / 193 tokens 29.33.770.960 I slot print_timing: id 0 | task 5963 | graphs reused = 5123 29.33.770.960 I slot print_timing: id 0 | task 5963 | graph reallocs = 0 / 0 (same size) / (changed size) 29.33.771.004 I slot release: id 0 | task 5963 | stop processing: n_tokens = 1317, truncated = 0 29.33.965.384 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.870 29.33.965.417 I slot launch_slot_: id 0 | task 6065 | processing task, is_child = 0 29.35.638.454 I slot print_timing: id 1 | task 5824 | n_gen = 234, tg = 3.93 t/s, tg_3s = 2.77 t/s 29.38.672.155 I slot print_timing: id 1 | task 5824 | n_gen = 248, tg = 3.97 t/s, tg_3s = 4.61 t/s 29.41.738.852 I slot print_timing: id 1 | task 5824 | n_gen = 263, tg = 4.01 t/s, tg_3s = 4.89 t/s 29.42.966.520 I slot print_timing: id 3 | task 5998 | n_gen = 100, tg = 4.22 t/s, tg_3s = 4.26 t/s 29.43.171.055 I slot print_timing: id 3 | task 5998 | prompt eval time = 2075.32 ms / 111 tokens ( 18.70 ms per token, 53.49 tokens per second) 29.43.171.060 I slot print_timing: id 3 | task 5998 | eval time = 23666.59 ms / 101 tokens ( 236.67 ms per token, 4.23 tokens per second) 29.43.171.061 I slot print_timing: id 3 | task 5998 | total time = 25741.92 ms / 212 tokens 29.43.171.062 I slot print_timing: id 3 | task 5998 | graphs reused = 5158 29.43.171.062 I slot print_timing: id 3 | task 5998 | graph reallocs = 0 / 0 (same size) / (changed size) 29.43.171.106 I slot release: id 3 | task 5998 | stop processing: n_tokens = 1336, truncated = 0 29.43.366.048 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.858 29.43.366.078 I slot launch_slot_: id 3 | task 6104 | processing task, is_child = 0 29.45.769.492 I slot print_timing: id 1 | task 5824 | n_gen = 272, tg = 3.91 t/s, tg_3s = 2.23 t/s 29.48.816.379 I slot print_timing: id 1 | task 5824 | n_gen = 286, tg = 3.93 t/s, tg_3s = 4.59 t/s 29.51.885.134 I slot print_timing: id 1 | task 5824 | n_gen = 301, tg = 3.97 t/s, tg_3s = 4.89 t/s 29.54.953.842 I slot print_timing: id 1 | task 5824 | n_gen = 316, tg = 4.01 t/s, tg_3s = 4.89 t/s 29.56.385.483 I slot print_timing: id 2 | task 6053 | n_gen = 100, tg = 4.08 t/s, tg_3s = 4.12 t/s 29.58.022.506 I slot print_timing: id 1 | task 5824 | n_gen = 331, tg = 4.04 t/s, tg_3s = 4.89 t/s 29.58.636.003 I slot print_timing: id 0 | task 6065 | n_gen = 100, tg = 4.38 t/s, tg_3s = 4.42 t/s 29.58.636.290 I slot print_timing: id 2 | task 6053 | prompt eval time = 1915.71 ms / 101 tokens ( 18.97 ms per token, 52.72 tokens per second) 29.58.636.294 I slot print_timing: id 2 | task 6053 | eval time = 26503.34 ms / 111 tokens ( 240.94 ms per token, 4.15 tokens per second) 29.58.636.295 I slot print_timing: id 2 | task 6053 | total time = 28419.04 ms / 212 tokens 29.58.636.295 I slot print_timing: id 2 | task 6053 | graphs reused = 5218 29.58.636.296 I slot print_timing: id 2 | task 6053 | graph reallocs = 0 / 0 (same size) / (changed size) 29.58.636.339 I slot release: id 2 | task 6053 | stop processing: n_tokens = 1336, truncated = 0 29.58.916.778 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.858 29.58.916.815 I slot launch_slot_: id 2 | task 6169 | processing task, is_child = 0 30.01.162.950 I slot print_timing: id 1 | task 5824 | n_gen = 337, tg = 3.96 t/s, tg_3s = 1.91 t/s 30.01.779.012 I slot print_timing: id 0 | task 6065 | n_gen = 106, tg = 4.08 t/s, tg_3s = 1.91 t/s 30.01.983.713 I slot print_timing: id 1 | task 5824 | prompt eval time = 2734.71 ms / 139 tokens ( 19.67 ms per token, 50.83 tokens per second) 30.01.983.718 I slot print_timing: id 1 | task 5824 | eval time = 85594.89 ms / 341 tokens ( 251.75 ms per token, 3.97 tokens per second) 30.01.983.719 I slot print_timing: id 1 | task 5824 | total time = 88329.60 ms / 480 tokens 30.01.983.719 I slot print_timing: id 1 | task 5824 | graphs reused = 5221 30.01.983.720 I slot print_timing: id 1 | task 5824 | graph reallocs = 0 / 0 (same size) / (changed size) 30.01.983.769 I slot release: id 1 | task 5824 | stop processing: n_tokens = 1604, truncated = 0 30.02.263.578 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.714 30.02.263.610 I slot launch_slot_: id 1 | task 6177 | processing task, is_child = 0 30.04.860.124 I slot print_timing: id 0 | task 6065 | n_gen = 111, tg = 3.81 t/s, tg_3s = 1.62 t/s 30.07.927.456 I slot print_timing: id 0 | task 6065 | n_gen = 126, tg = 3.92 t/s, tg_3s = 4.89 t/s 30.08.540.878 I slot print_timing: id 0 | task 6065 | prompt eval time = 2048.30 ms / 108 tokens ( 18.97 ms per token, 52.73 tokens per second) 30.08.540.887 I slot print_timing: id 0 | task 6065 | eval time = 32527.15 ms / 129 tokens ( 254.12 ms per token, 3.94 tokens per second) 30.08.540.888 I slot print_timing: id 0 | task 6065 | total time = 34575.46 ms / 237 tokens 30.08.540.888 I slot print_timing: id 0 | task 6065 | graphs reused = 5239 30.08.540.889 I slot print_timing: id 0 | task 6065 | graph reallocs = 0 / 0 (same size) / (changed size) 30.08.540.933 I slot release: id 0 | task 6065 | stop processing: n_tokens = 1361, truncated = 0 30.08.735.263 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.842 30.08.735.303 I slot launch_slot_: id 0 | task 6200 | processing task, is_child = 0 30.11.696.158 I slot print_timing: id 3 | task 6104 | n_gen = 100, tg = 3.88 t/s, tg_3s = 3.92 t/s 30.14.762.064 I slot print_timing: id 3 | task 6104 | n_gen = 115, tg = 3.99 t/s, tg_3s = 4.89 t/s 30.17.827.792 I slot print_timing: id 3 | task 6104 | n_gen = 130, tg = 4.07 t/s, tg_3s = 4.89 t/s 30.20.895.109 I slot print_timing: id 3 | task 6104 | n_gen = 145, tg = 4.15 t/s, tg_3s = 4.89 t/s 30.23.963.021 I slot print_timing: id 3 | task 6104 | n_gen = 160, tg = 4.21 t/s, tg_3s = 4.89 t/s 30.24.781.655 I slot print_timing: id 2 | task 6169 | n_gen = 100, tg = 4.19 t/s, tg_3s = 4.23 t/s 30.24.985.991 I slot print_timing: id 0 | task 6200 | prompt eval time = 1731.09 ms / 95 tokens ( 18.22 ms per token, 54.88 tokens per second) 30.24.985.993 I slot print_timing: id 0 | task 6200 | eval time = 14519.59 ms / 72 tokens ( 204.50 ms per token, 4.89 tokens per second) 30.24.985.994 I slot print_timing: id 0 | task 6200 | total time = 16250.68 ms / 167 tokens 30.24.985.994 I slot print_timing: id 0 | task 6200 | graphs reused = 5310 30.24.985.995 I slot print_timing: id 0 | task 6200 | graph reallocs = 0 / 0 (same size) / (changed size) 30.24.986.039 I slot release: id 0 | task 6200 | stop processing: n_tokens = 1291, truncated = 0 30.25.181.061 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.904 (> 0.100 thold), f_keep = 0.888 30.25.181.093 I slot launch_slot_: id 0 | task 6275 | processing task, is_child = 0 30.27.222.379 I slot print_timing: id 3 | task 6104 | n_gen = 167, tg = 4.04 t/s, tg_3s = 2.15 t/s 30.27.803.647 I slot print_timing: id 2 | task 6169 | n_gen = 105, tg = 3.90 t/s, tg_3s = 1.65 t/s 30.28.212.762 I slot print_timing: id 1 | task 6177 | n_gen = 100, tg = 4.20 t/s, tg_3s = 4.24 t/s 30.29.644.362 I slot print_timing: id 1 | task 6177 | prompt eval time = 2389.70 ms / 128 tokens ( 18.67 ms per token, 53.56 tokens per second) 30.29.644.364 I slot print_timing: id 1 | task 6177 | eval time = 24991.05 ms / 107 tokens ( 235.76 ms per token, 4.24 tokens per second) 30.29.644.365 I slot print_timing: id 1 | task 6177 | total time = 27380.74 ms / 235 tokens 30.29.644.365 I slot print_timing: id 1 | task 6177 | graphs reused = 5320 30.29.644.366 I slot print_timing: id 1 | task 6177 | graph reallocs = 0 / 0 (same size) / (changed size) 30.29.644.415 I slot release: id 1 | task 6177 | stop processing: n_tokens = 1359, truncated = 0 30.29.924.649 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.843 30.29.924.686 I slot launch_slot_: id 1 | task 6289 | processing task, is_child = 0 30.31.445.699 I slot print_timing: id 2 | task 6169 | n_gen = 116, tg = 3.80 t/s, tg_3s = 3.02 t/s 30.31.445.904 I slot print_timing: id 3 | task 6104 | n_gen = 180, tg = 3.95 t/s, tg_3s = 3.08 t/s 30.34.641.832 I slot print_timing: id 2 | task 6169 | n_gen = 130, tg = 3.85 t/s, tg_3s = 4.38 t/s 30.34.641.984 I slot print_timing: id 3 | task 6104 | n_gen = 194, tg = 3.98 t/s, tg_3s = 4.38 t/s 30.35.664.353 I slot print_timing: id 2 | task 6169 | prompt eval time = 2246.31 ms / 110 tokens ( 20.42 ms per token, 48.97 tokens per second) 30.35.664.358 I slot print_timing: id 2 | task 6169 | eval time = 34501.22 ms / 135 tokens ( 257.47 ms per token, 3.88 tokens per second) 30.35.664.358 I slot print_timing: id 2 | task 6169 | total time = 36747.53 ms / 245 tokens 30.35.664.359 I slot print_timing: id 2 | task 6169 | graphs reused = 5337 30.35.664.359 I slot print_timing: id 2 | task 6169 | graph reallocs = 0 / 0 (same size) / (changed size) 30.35.664.401 I slot release: id 2 | task 6169 | stop processing: n_tokens = 1369, truncated = 0 30.37.899.187 I slot print_timing: id 3 | task 6104 | n_gen = 207, tg = 3.98 t/s, tg_3s = 3.99 t/s 30.40.968.978 I slot print_timing: id 3 | task 6104 | n_gen = 218, tg = 3.96 t/s, tg_3s = 3.58 t/s 30.44.041.054 I slot print_timing: id 3 | task 6104 | n_gen = 229, tg = 3.94 t/s, tg_3s = 3.58 t/s 30.47.114.219 I slot print_timing: id 3 | task 6104 | n_gen = 240, tg = 3.92 t/s, tg_3s = 3.58 t/s 30.50.186.833 I slot print_timing: id 3 | task 6104 | n_gen = 251, tg = 3.90 t/s, tg_3s = 3.58 t/s 30.53.259.281 I slot print_timing: id 3 | task 6104 | n_gen = 262, tg = 3.89 t/s, tg_3s = 3.58 t/s 30.54.096.687 I slot print_timing: id 1 | task 6289 | prompt eval time = 2055.38 ms / 96 tokens ( 21.41 ms per token, 46.71 tokens per second) 30.54.096.693 I slot print_timing: id 1 | task 6289 | eval time = 22116.61 ms / 85 tokens ( 263.29 ms per token, 3.80 tokens per second) 30.54.096.693 I slot print_timing: id 1 | task 6289 | total time = 24171.99 ms / 181 tokens 30.54.096.694 I slot print_timing: id 1 | task 6289 | graphs reused = 5337 30.54.096.694 I slot print_timing: id 1 | task 6289 | graph reallocs = 0 / 0 (same size) / (changed size) 30.54.096.739 I slot release: id 1 | task 6289 | stop processing: n_tokens = 1305, truncated = 0 30.54.496.306 I slot print_timing: id 0 | task 6275 | n_gen = 100, tg = 3.68 t/s, tg_3s = 3.72 t/s 30.56.292.101 I slot print_timing: id 3 | task 6104 | n_gen = 276, tg = 3.92 t/s, tg_3s = 4.62 t/s 30.57.688.431 I slot print_timing: id 0 | task 6275 | n_gen = 116, tg = 3.82 t/s, tg_3s = 5.01 t/s 30.59.484.840 I slot print_timing: id 3 | task 6104 | n_gen = 292, tg = 3.97 t/s, tg_3s = 5.01 t/s 31.00.881.622 I slot print_timing: id 0 | task 6275 | n_gen = 132, tg = 3.94 t/s, tg_3s = 5.01 t/s 31.02.677.840 I slot print_timing: id 3 | task 6104 | n_gen = 308, tg = 4.01 t/s, tg_3s = 5.01 t/s 31.04.074.842 I slot print_timing: id 0 | task 6275 | n_gen = 148, tg = 4.03 t/s, tg_3s = 5.01 t/s 31.05.872.031 I slot print_timing: id 3 | task 6104 | n_gen = 324, tg = 4.05 t/s, tg_3s = 5.01 t/s 31.06.472.138 I slot print_timing: id 3 | task 6104 | prompt eval time = 2788.80 ms / 166 tokens ( 16.80 ms per token, 59.52 tokens per second) 31.06.472.141 I slot print_timing: id 3 | task 6104 | eval time = 80317.25 ms / 327 tokens ( 246.37 ms per token, 4.06 tokens per second) 31.06.472.142 I slot print_timing: id 3 | task 6104 | total time = 83106.05 ms / 493 tokens 31.06.472.142 I slot print_timing: id 3 | task 6104 | graphs reused = 5337 31.06.472.142 I slot print_timing: id 3 | task 6104 | graph reallocs = 0 / 0 (same size) / (changed size) 31.06.472.189 I slot release: id 3 | task 6104 | stop processing: n_tokens = 1617, truncated = 0 31.07.164.349 I slot print_timing: id 0 | task 6275 | n_gen = 167, tg = 4.20 t/s, tg_3s = 6.15 t/s 31.08.445.216 I slot print_timing: id 0 | task 6275 | prompt eval time = 2415.02 ms / 142 tokens ( 17.01 ms per token, 58.80 tokens per second) 31.08.445.221 I slot print_timing: id 0 | task 6275 | eval time = 40849.10 ms / 180 tokens ( 228.21 ms per token, 4.38 tokens per second) 31.08.445.222 I slot print_timing: id 0 | task 6275 | total time = 43264.12 ms / 322 tokens 31.08.445.222 I slot print_timing: id 0 | task 6275 | graphs reused = 5356 31.08.445.223 I slot print_timing: id 0 | task 6275 | graph reallocs = 0 / 0 (same size) / (changed size) 31.08.445.268 I slot release: id 0 | task 6275 | stop processing: n_tokens = 1446, truncated = 0 31.08.461.580 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1369, t_last = 88624481075 31.08.461.693 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.631 MiB) 31.08.461.697 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.319 MiB) 31.08.513.286 I slot launch_slot_: id 2 | task 6458 | processing task, is_child = 0 31.08.513.370 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.006 MiB) 31.08.513.381 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.944 MiB) 31.08.513.382 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.443 MiB) 31.08.568.150 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.882 MiB) 31.08.568.156 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.943 MiB) 31.08.568.157 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.193 MiB) 31.09.628.676 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.569 MiB) 31.09.628.694 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.131 MiB) 31.10.320.216 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1305, t_last = 88642913413 31.10.320.530 I slot launch_slot_: id 1 | task 6459 | processing task, is_child = 0 31.10.320.674 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1617, t_last = 88655288863 31.10.320.777 I slot launch_slot_: id 3 | task 6460 | processing task, is_child = 0 31.10.320.842 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1446, t_last = 88657261942 31.10.320.927 I slot launch_slot_: id 0 | task 6461 | processing task, is_child = 0 31.17.156.103 I slot print_timing: id 0 | task 6461 | prompt processing, n_tokens = 154, progress = 0.16, t = 6.84 s / 22.53 tokens per second 31.17.919.208 I slot print_timing: id 1 | task 6459 | prompt processing, n_tokens = 137, progress = 0.17, t = 6.83 s / 20.04 tokens per second 31.17.986.284 I slot print_timing: id 2 | task 6458 | prompt processing, n_tokens = 124, progress = 0.16, t = 6.83 s / 18.14 tokens per second 31.18.012.012 I slot print_timing: id 3 | task 6460 | prompt processing, n_tokens = 168, progress = 0.17, t = 6.83 s / 24.58 tokens per second 31.24.327.561 I slot print_timing: id 0 | task 6461 | prompt processing, n_tokens = 279, progress = 0.29, t = 14.01 s / 19.92 tokens per second 31.24.327.579 I slot print_timing: id 1 | task 6459 | prompt processing, n_tokens = 261, progress = 0.32, t = 14.01 s / 18.63 tokens per second 31.24.327.584 I slot print_timing: id 2 | task 6458 | prompt processing, n_tokens = 263, progress = 0.34, t = 14.01 s / 18.78 tokens per second 31.25.466.181 I slot print_timing: id 3 | task 6460 | prompt processing, n_tokens = 387, progress = 0.39, t = 14.01 s / 27.63 tokens per second 31.29.893.675 I slot print_timing: id 0 | task 6461 | prompt processing, n_tokens = 436, progress = 0.46, t = 19.57 s / 22.28 tokens per second 31.33.506.947 I slot print_timing: id 1 | task 6459 | prompt processing, n_tokens = 290, progress = 0.36, t = 19.57 s / 14.82 tokens per second 31.33.520.688 I slot print_timing: id 2 | task 6458 | prompt processing, n_tokens = 656, progress = 0.84, t = 19.57 s / 33.52 tokens per second 31.33.534.368 I slot print_timing: id 3 | task 6460 | prompt processing, n_tokens = 471, progress = 0.48, t = 19.57 s / 24.06 tokens per second 31.45.200.889 I slot print_timing: id 0 | task 6461 | prompt processing, n_tokens = 835, progress = 0.88, t = 34.88 s / 23.94 tokens per second 31.48.487.937 I slot print_timing: id 1 | task 6459 | prompt processing, n_tokens = 642, progress = 0.80, t = 34.88 s / 18.41 tokens per second 31.48.501.480 I slot print_timing: id 2 | task 6458 | prompt processing, n_tokens = 775, progress = 0.99, t = 34.88 s / 22.22 tokens per second 31.48.515.190 I slot print_timing: id 3 | task 6460 | prompt processing, n_tokens = 877, progress = 0.89, t = 34.88 s / 25.14 tokens per second 31.53.691.457 I slot print_timing: id 0 | task 6461 | prompt processing, n_tokens = 948, progress = 1.00, t = 43.37 s / 21.86 tokens per second 31.53.708.017 I slot print_timing: id 1 | task 6459 | prompt processing, n_tokens = 802, progress = 1.00, t = 43.37 s / 18.49 tokens per second 31.53.721.363 I slot print_timing: id 3 | task 6460 | prompt processing, n_tokens = 983, progress = 1.00, t = 43.37 s / 22.67 tokens per second 31.54.283.574 I slot print_timing: id 2 | task 6458 | prompt eval time = 43370.26 ms / 779 tokens ( 55.67 ms per token, 17.96 tokens per second) 31.54.283.578 I slot print_timing: id 2 | task 6458 | eval time = 592.12 ms / 2 tokens ( 592.12 ms per token, 1.69 tokens per second) 31.54.283.578 I slot print_timing: id 2 | task 6458 | total time = 43962.38 ms / 781 tokens 31.54.283.579 I slot print_timing: id 2 | task 6458 | graphs reused = 5356 31.54.283.580 I slot print_timing: id 2 | task 6458 | graph reallocs = 0 / 0 (same size) / (changed size) 31.54.283.778 I slot release: id 2 | task 6458 | stop processing: n_tokens = 780, truncated = 0 31.54.561.591 I slot print_timing: id 0 | task 6461 | prompt eval time = 43961.77 ms / 952 tokens ( 46.18 ms per token, 21.66 tokens per second) 31.54.561.596 I slot print_timing: id 0 | task 6461 | eval time = 278.88 ms / 2 tokens ( 278.88 ms per token, 3.59 tokens per second) 31.54.561.597 I slot print_timing: id 0 | task 6461 | total time = 44240.65 ms / 954 tokens 31.54.561.597 I slot print_timing: id 0 | task 6461 | graphs reused = 5356 31.54.561.598 I slot print_timing: id 0 | task 6461 | graph reallocs = 0 / 0 (same size) / (changed size) 31.54.561.709 I slot release: id 0 | task 6461 | stop processing: n_tokens = 953, truncated = 0 31.54.561.941 I slot print_timing: id 1 | task 6459 | prompt eval time = 43962.03 ms / 806 tokens ( 54.54 ms per token, 18.33 tokens per second) 31.54.561.944 I slot print_timing: id 1 | task 6459 | eval time = 278.81 ms / 2 tokens ( 278.81 ms per token, 3.59 tokens per second) 31.54.561.944 I slot print_timing: id 1 | task 6459 | total time = 44240.85 ms / 808 tokens 31.54.561.945 I slot print_timing: id 1 | task 6459 | graphs reused = 5356 31.54.561.945 I slot print_timing: id 1 | task 6459 | graph reallocs = 0 / 0 (same size) / (changed size) 31.54.562.000 I slot release: id 1 | task 6459 | stop processing: n_tokens = 807, truncated = 0 31.54.562.170 I slot print_timing: id 3 | task 6460 | prompt eval time = 43963.18 ms / 987 tokens ( 44.54 ms per token, 22.45 tokens per second) 31.54.562.172 I slot print_timing: id 3 | task 6460 | eval time = 277.72 ms / 2 tokens ( 277.72 ms per token, 3.60 tokens per second) 31.54.562.172 I slot print_timing: id 3 | task 6460 | total time = 44240.89 ms / 989 tokens 31.54.562.172 I slot print_timing: id 3 | task 6460 | graphs reused = 5356 31.54.562.173 I slot print_timing: id 3 | task 6460 | graph reallocs = 0 / 0 (same size) / (changed size) 31.54.562.242 I slot release: id 3 | task 6460 | stop processing: n_tokens = 988, truncated = 0 31.54.562.251 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 780, t_last = 88703100454 31.54.562.310 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.943 MiB) 31.54.562.321 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.881 MiB) 31.54.562.328 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.943 MiB) 31.54.682.987 I slot launch_slot_: id 2 | task 6469 | processing task, is_child = 0 31.54.683.053 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.818 MiB) 31.54.683.062 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.194 MiB) 31.54.683.072 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.068 MiB) 31.54.799.715 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.819 MiB) 31.54.799.728 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 305.755 MiB) 31.54.911.225 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.631 MiB) 31.54.911.238 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.694 MiB) 31.54.911.244 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.006 MiB) 31.55.044.036 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 953, t_last = 88703378384 31.55.044.158 I slot launch_slot_: id 0 | task 6470 | processing task, is_child = 0 31.55.044.255 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 807, t_last = 88703378675 31.55.044.317 I slot launch_slot_: id 1 | task 6471 | processing task, is_child = 0 31.55.044.365 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 988, t_last = 88703378918 31.55.044.429 I slot launch_slot_: id 3 | task 6472 | processing task, is_child = 0 32.06.168.851 I slot print_timing: id 0 | task 6470 | prompt processing, n_tokens = 260, progress = 0.32, t = 11.12 s / 23.37 tokens per second 32.06.168.865 I slot print_timing: id 1 | task 6471 | prompt processing, n_tokens = 260, progress = 0.30, t = 11.12 s / 23.37 tokens per second 32.06.168.871 I slot print_timing: id 2 | task 6469 | prompt processing, n_tokens = 260, progress = 0.32, t = 11.12 s / 23.37 tokens per second 32.06.168.876 I slot print_timing: id 3 | task 6472 | prompt processing, n_tokens = 260, progress = 0.31, t = 11.12 s / 23.37 tokens per second 32.09.401.098 I slot print_timing: id 0 | task 6470 | prompt processing, n_tokens = 288, progress = 0.36, t = 14.36 s / 20.06 tokens per second 32.10.166.604 I slot print_timing: id 1 | task 6471 | prompt processing, n_tokens = 339, progress = 0.40, t = 14.36 s / 23.61 tokens per second 32.10.171.028 I slot print_timing: id 2 | task 6469 | prompt processing, n_tokens = 285, progress = 0.36, t = 14.36 s / 19.85 tokens per second 32.10.175.422 I slot print_timing: id 3 | task 6472 | prompt processing, n_tokens = 330, progress = 0.39, t = 14.36 s / 22.99 tokens per second 32.27.540.401 I slot print_timing: id 0 | task 6470 | prompt processing, n_tokens = 696, progress = 0.87, t = 32.50 s / 21.42 tokens per second 32.28.310.981 I slot print_timing: id 1 | task 6471 | prompt processing, n_tokens = 696, progress = 0.81, t = 32.50 s / 21.42 tokens per second 32.28.315.403 I slot print_timing: id 2 | task 6469 | prompt processing, n_tokens = 696, progress = 0.87, t = 32.50 s / 21.42 tokens per second 32.28.319.830 I slot print_timing: id 3 | task 6472 | prompt processing, n_tokens = 696, progress = 0.82, t = 32.50 s / 21.42 tokens per second 32.34.053.813 I slot print_timing: id 0 | task 6470 | prompt processing, n_tokens = 800, progress = 1.00, t = 39.01 s / 20.51 tokens per second 32.34.824.900 I slot print_timing: id 1 | task 6471 | prompt processing, n_tokens = 851, progress = 1.00, t = 39.01 s / 21.82 tokens per second 32.34.829.428 I slot print_timing: id 2 | task 6469 | prompt processing, n_tokens = 797, progress = 1.00, t = 39.01 s / 20.43 tokens per second 32.34.850.519 I slot print_timing: id 3 | task 6472 | prompt processing, n_tokens = 842, progress = 1.00, t = 39.01 s / 21.58 tokens per second 32.35.427.078 I slot print_timing: id 0 | task 6470 | prompt eval time = 40176.47 ms / 804 tokens ( 49.97 ms per token, 20.01 tokens per second) 32.35.427.080 I slot print_timing: id 0 | task 6470 | eval time = 206.16 ms / 2 tokens ( 206.16 ms per token, 4.85 tokens per second) 32.35.427.081 I slot print_timing: id 0 | task 6470 | total time = 40382.63 ms / 806 tokens 32.35.427.081 I slot print_timing: id 0 | task 6470 | graphs reused = 5356 32.35.427.081 I slot print_timing: id 0 | task 6470 | graph reallocs = 0 / 0 (same size) / (changed size) 32.35.427.141 I slot release: id 0 | task 6470 | stop processing: n_tokens = 805, truncated = 0 32.35.427.299 I slot print_timing: id 1 | task 6471 | prompt eval time = 40176.59 ms / 855 tokens ( 46.99 ms per token, 21.28 tokens per second) 32.35.427.303 I slot print_timing: id 1 | task 6471 | eval time = 206.20 ms / 2 tokens ( 206.20 ms per token, 4.85 tokens per second) 32.35.427.304 I slot print_timing: id 1 | task 6471 | total time = 40382.79 ms / 857 tokens 32.35.427.304 I slot print_timing: id 1 | task 6471 | graphs reused = 5356 32.35.427.304 I slot print_timing: id 1 | task 6471 | graph reallocs = 0 / 0 (same size) / (changed size) 32.35.427.330 I slot release: id 1 | task 6471 | stop processing: n_tokens = 856, truncated = 0 32.35.427.491 I slot print_timing: id 2 | task 6469 | prompt eval time = 40176.75 ms / 801 tokens ( 50.16 ms per token, 19.94 tokens per second) 32.35.427.493 I slot print_timing: id 2 | task 6469 | eval time = 206.18 ms / 2 tokens ( 206.18 ms per token, 4.85 tokens per second) 32.35.427.494 I slot print_timing: id 2 | task 6469 | total time = 40382.93 ms / 803 tokens 32.35.427.494 I slot print_timing: id 2 | task 6469 | graphs reused = 5356 32.35.427.494 I slot print_timing: id 2 | task 6469 | graph reallocs = 0 / 0 (same size) / (changed size) 32.35.427.523 I slot release: id 2 | task 6469 | stop processing: n_tokens = 802, truncated = 0 32.35.427.696 I slot print_timing: id 3 | task 6472 | prompt eval time = 40176.88 ms / 846 tokens ( 47.49 ms per token, 21.06 tokens per second) 32.35.427.698 I slot print_timing: id 3 | task 6472 | eval time = 206.21 ms / 2 tokens ( 206.21 ms per token, 4.85 tokens per second) 32.35.427.698 I slot print_timing: id 3 | task 6472 | total time = 40383.09 ms / 848 tokens 32.35.427.699 I slot print_timing: id 3 | task 6472 | graphs reused = 5356 32.35.427.699 I slot print_timing: id 3 | task 6472 | graph reallocs = 0 / 0 (same size) / (changed size) 32.35.427.728 I slot release: id 3 | task 6472 | stop processing: n_tokens = 847, truncated = 0 32.35.437.408 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.878 (> 0.100 thold), f_keep = 0.899 32.35.437.505 I slot launch_slot_: id 0 | task 6480 | processing task, is_child = 0 32.35.437.556 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.318 MiB) 32.35.437.564 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.068 MiB) 32.35.437.566 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 831.537 MiB) 32.35.720.637 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 833.725 MiB) 32.35.859.027 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 856, t_last = 88744244005 32.35.859.168 I slot launch_slot_: id 1 | task 6481 | processing task, is_child = 0 32.35.859.254 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 802, t_last = 88744244198 32.35.859.319 I slot launch_slot_: id 2 | task 6482 | processing task, is_child = 0 32.35.859.367 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 847, t_last = 88744244402 32.35.859.427 I slot launch_slot_: id 3 | task 6483 | processing task, is_child = 0 32.43.145.281 I slot print_timing: id 0 | task 6480 | prompt processing, n_tokens = 125, progress = 1.00, t = 7.29 s / 17.16 tokens per second 32.43.423.608 I slot print_timing: id 1 | task 6481 | prompt processing, n_tokens = 171, progress = 0.18, t = 7.28 s / 23.49 tokens per second 32.43.428.060 I slot print_timing: id 2 | task 6482 | prompt processing, n_tokens = 160, progress = 0.18, t = 7.28 s / 21.98 tokens per second 32.43.432.596 I slot print_timing: id 3 | task 6483 | prompt processing, n_tokens = 160, progress = 0.18, t = 7.28 s / 21.98 tokens per second 32.50.000.405 I slot print_timing: id 1 | task 6481 | prompt processing, n_tokens = 340, progress = 0.35, t = 14.13 s / 24.06 tokens per second 32.50.000.420 I slot print_timing: id 2 | task 6482 | prompt processing, n_tokens = 342, progress = 0.38, t = 14.13 s / 24.20 tokens per second 32.50.000.425 I slot print_timing: id 3 | task 6483 | prompt processing, n_tokens = 342, progress = 0.39, t = 14.13 s / 24.20 tokens per second 32.52.581.358 I slot print_timing: id 0 | task 6480 | prompt eval time = 14140.95 ms / 129 tokens ( 109.62 ms per token, 9.12 tokens per second) 32.52.581.360 I slot print_timing: id 0 | task 6480 | eval time = 2580.96 ms / 2 tokens ( 2580.96 ms per token, 0.39 tokens per second) 32.52.581.361 I slot print_timing: id 0 | task 6480 | total time = 16721.92 ms / 131 tokens 32.52.581.362 I slot print_timing: id 0 | task 6480 | graphs reused = 5356 32.52.581.362 I slot print_timing: id 0 | task 6480 | graph reallocs = 0 / 0 (same size) / (changed size) 32.52.581.425 I slot release: id 0 | task 6480 | stop processing: n_tokens = 826, truncated = 0 32.52.581.437 I slot print_timing: id 1 | task 6481 | prompt processing, n_tokens = 447, progress = 0.46, t = 16.71 s / 26.74 tokens per second 32.52.587.928 I slot print_timing: id 2 | task 6482 | prompt processing, n_tokens = 380, progress = 0.42, t = 16.71 s / 22.74 tokens per second 32.52.592.384 I slot print_timing: id 3 | task 6483 | prompt processing, n_tokens = 364, progress = 0.41, t = 16.71 s / 21.78 tokens per second 33.06.050.905 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 826, t_last = 88761398099 33.06.050.963 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 838.539 MiB) 33.06.353.596 I slot launch_slot_: id 0 | task 6488 | processing task, is_child = 0 33.06.353.773 I slot print_timing: id 1 | task 6481 | prompt processing, n_tokens = 831, progress = 0.86, t = 30.18 s / 27.53 tokens per second 33.06.363.065 I slot print_timing: id 2 | task 6482 | prompt processing, n_tokens = 754, progress = 0.84, t = 30.18 s / 24.98 tokens per second 33.06.370.239 I slot print_timing: id 3 | task 6483 | prompt processing, n_tokens = 754, progress = 0.86, t = 30.18 s / 24.98 tokens per second 33.13.353.957 I slot print_timing: id 0 | task 6488 | prompt processing, n_tokens = 182, progress = 0.18, t = 7.00 s / 26.00 tokens per second 33.13.632.836 I slot print_timing: id 1 | task 6481 | prompt processing, n_tokens = 959, progress = 1.00, t = 37.49 s / 25.58 tokens per second 33.13.637.352 I slot print_timing: id 2 | task 6482 | prompt processing, n_tokens = 892, progress = 1.00, t = 37.49 s / 23.79 tokens per second 33.13.641.829 I slot print_timing: id 3 | task 6483 | prompt processing, n_tokens = 876, progress = 1.00, t = 37.49 s / 23.37 tokens per second 33.16.542.867 I slot print_timing: id 0 | task 6488 | prompt processing, n_tokens = 403, progress = 0.41, t = 10.19 s / 39.55 tokens per second 33.17.863.879 I slot print_timing: id 1 | task 6481 | prompt eval time = 40675.47 ms / 963 tokens ( 42.24 ms per token, 23.68 tokens per second) 33.17.863.885 I slot print_timing: id 1 | task 6481 | eval time = 1321.45 ms / 2 tokens ( 1321.45 ms per token, 0.76 tokens per second) 33.17.863.885 I slot print_timing: id 1 | task 6481 | total time = 41996.92 ms / 965 tokens 33.17.863.886 I slot print_timing: id 1 | task 6481 | graphs reused = 5356 33.17.863.886 I slot print_timing: id 1 | task 6481 | graph reallocs = 0 / 0 (same size) / (changed size) 33.17.863.977 I slot release: id 1 | task 6481 | stop processing: n_tokens = 964, truncated = 0 33.17.864.162 I slot print_timing: id 2 | task 6482 | prompt eval time = 40675.63 ms / 896 tokens ( 45.40 ms per token, 22.03 tokens per second) 33.17.864.164 I slot print_timing: id 2 | task 6482 | eval time = 1321.52 ms / 2 tokens ( 1321.52 ms per token, 0.76 tokens per second) 33.17.864.164 I slot print_timing: id 2 | task 6482 | total time = 41997.15 ms / 898 tokens 33.17.864.165 I slot print_timing: id 2 | task 6482 | graphs reused = 5356 33.17.864.165 I slot print_timing: id 2 | task 6482 | graph reallocs = 0 / 0 (same size) / (changed size) 33.17.864.254 I slot release: id 2 | task 6482 | stop processing: n_tokens = 897, truncated = 0 33.17.864.504 I slot print_timing: id 3 | task 6483 | prompt eval time = 40675.79 ms / 880 tokens ( 46.22 ms per token, 21.63 tokens per second) 33.17.864.507 I slot print_timing: id 3 | task 6483 | eval time = 1321.65 ms / 2 tokens ( 1321.65 ms per token, 0.76 tokens per second) 33.17.864.507 I slot print_timing: id 3 | task 6483 | total time = 41997.44 ms / 882 tokens 33.17.864.507 I slot print_timing: id 3 | task 6483 | graphs reused = 5356 33.17.864.508 I slot print_timing: id 3 | task 6483 | graph reallocs = 0 / 0 (same size) / (changed size) 33.17.864.536 I slot release: id 3 | task 6483 | stop processing: n_tokens = 881, truncated = 0 33.17.864.542 I slot print_timing: id 0 | task 6488 | prompt processing, n_tokens = 471, progress = 0.48, t = 11.51 s / 40.92 tokens per second 33.17.893.709 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 964, t_last = 88786680653 33.17.893.765 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 829.723 MiB) 33.22.585.410 I slot launch_slot_: id 1 | task 6493 | processing task, is_child = 0 33.22.585.463 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 849.231 MiB) 33.22.629.459 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 796.899 MiB) 33.23.781.326 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 897, t_last = 88786680929 33.23.781.499 I slot launch_slot_: id 2 | task 6494 | processing task, is_child = 0 33.23.781.637 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 881, t_last = 88786681210 33.23.781.871 I slot launch_slot_: id 3 | task 6495 | processing task, is_child = 0 33.23.781.888 I slot print_timing: id 0 | task 6488 | prompt processing, n_tokens = 872, progress = 0.88, t = 11.54 s / 75.56 tokens per second 33.29.766.211 I slot print_timing: id 0 | task 6488 | prompt processing, n_tokens = 983, progress = 1.00, t = 23.41 s / 41.99 tokens per second 33.30.536.693 I slot print_timing: id 1 | task 6493 | prompt processing, n_tokens = 182, progress = 0.18, t = 5.94 s / 30.66 tokens per second 33.30.551.165 I slot print_timing: id 2 | task 6494 | prompt processing, n_tokens = 129, progress = 0.14, t = 5.94 s / 21.73 tokens per second 33.30.569.144 I slot print_timing: id 3 | task 6495 | prompt processing, n_tokens = 129, progress = 0.07, t = 5.94 s / 21.73 tokens per second 33.37.432.938 I slot print_timing: id 1 | task 6493 | prompt processing, n_tokens = 403, progress = 0.39, t = 13.60 s / 29.63 tokens per second 33.37.432.952 I slot print_timing: id 2 | task 6494 | prompt processing, n_tokens = 283, progress = 0.31, t = 13.60 s / 20.80 tokens per second 33.37.432.959 I slot print_timing: id 3 | task 6495 | prompt processing, n_tokens = 283, progress = 0.16, t = 13.60 s / 20.80 tokens per second 33.46.036.480 I slot print_timing: id 0 | task 6488 | prompt eval time = 31079.30 ms / 987 tokens ( 31.49 ms per token, 31.76 tokens per second) 33.46.036.483 I slot print_timing: id 0 | task 6488 | eval time = 8603.55 ms / 2 tokens ( 8603.55 ms per token, 0.12 tokens per second) 33.46.036.483 I slot print_timing: id 0 | task 6488 | total time = 39682.85 ms / 989 tokens 33.46.036.484 I slot print_timing: id 0 | task 6488 | graphs reused = 5356 33.46.036.484 I slot print_timing: id 0 | task 6488 | graph reallocs = 0 / 0 (same size) / (changed size) 33.46.036.565 I slot release: id 0 | task 6488 | stop processing: n_tokens = 988, truncated = 0 33.46.036.585 I slot print_timing: id 1 | task 6493 | prompt processing, n_tokens = 506, progress = 0.50, t = 22.21 s / 22.79 tokens per second 33.46.053.831 I slot print_timing: id 2 | task 6494 | prompt processing, n_tokens = 408, progress = 0.44, t = 22.21 s / 18.37 tokens per second 33.46.067.580 I slot print_timing: id 3 | task 6495 | prompt processing, n_tokens = 753, progress = 0.42, t = 22.21 s / 33.91 tokens per second 33.58.503.544 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 988, t_last = 88814853239 33.58.503.609 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 807.715 MiB) 34.00.700.541 I slot launch_slot_: id 0 | task 6500 | processing task, is_child = 0 34.00.700.636 I slot print_timing: id 1 | task 6493 | prompt processing, n_tokens = 872, progress = 0.85, t = 34.67 s / 25.15 tokens per second 34.00.705.057 I slot print_timing: id 2 | task 6494 | prompt processing, n_tokens = 753, progress = 0.81, t = 34.67 s / 21.72 tokens per second 34.00.717.082 I slot print_timing: id 3 | task 6495 | prompt processing, n_tokens = 1264, progress = 0.71, t = 34.67 s / 36.45 tokens per second 34.08.247.418 I slot print_timing: id 0 | task 6500 | prompt processing, n_tokens = 129, progress = 0.14, t = 7.55 s / 17.09 tokens per second 34.12.284.406 I slot print_timing: id 1 | task 6493 | prompt processing, n_tokens = 1018, progress = 1.00, t = 44.42 s / 22.92 tokens per second 34.12.311.943 I slot print_timing: id 2 | task 6494 | prompt processing, n_tokens = 920, progress = 1.00, t = 44.42 s / 20.71 tokens per second 34.12.325.586 I slot print_timing: id 3 | task 6495 | prompt processing, n_tokens = 1776, progress = 1.00, t = 44.42 s / 39.98 tokens per second 34.14.513.955 I slot print_timing: id 0 | task 6500 | prompt processing, n_tokens = 283, progress = 0.30, t = 13.81 s / 20.49 tokens per second 34.16.531.684 I slot print_timing: id 1 | task 6493 | prompt eval time = 50683.72 ms / 1022 tokens ( 49.59 ms per token, 20.16 tokens per second) 34.16.531.686 I slot print_timing: id 1 | task 6493 | eval time = 2018.50 ms / 2 tokens ( 2018.50 ms per token, 0.50 tokens per second) 34.16.531.687 I slot print_timing: id 1 | task 6493 | total time = 52702.21 ms / 1024 tokens 34.16.531.687 I slot print_timing: id 1 | task 6493 | graphs reused = 5356 34.16.531.687 I slot print_timing: id 1 | task 6493 | graph reallocs = 0 / 0 (same size) / (changed size) 34.16.531.743 I slot release: id 1 | task 6493 | stop processing: n_tokens = 1023, truncated = 0 34.16.532.211 I slot print_timing: id 2 | task 6494 | prompt eval time = 50684.02 ms / 924 tokens ( 54.85 ms per token, 18.23 tokens per second) 34.16.532.215 I slot print_timing: id 2 | task 6494 | eval time = 2018.64 ms / 2 tokens ( 2018.64 ms per token, 0.50 tokens per second) 34.16.532.215 I slot print_timing: id 2 | task 6494 | total time = 52702.67 ms / 926 tokens 34.16.532.215 I slot print_timing: id 2 | task 6494 | graphs reused = 5356 34.16.532.216 I slot print_timing: id 2 | task 6494 | graph reallocs = 0 / 0 (same size) / (changed size) 34.16.532.281 I slot release: id 2 | task 6494 | stop processing: n_tokens = 925, truncated = 0 34.16.532.658 I slot print_timing: id 3 | task 6495 | prompt eval time = 50684.33 ms / 1780 tokens ( 28.47 ms per token, 35.12 tokens per second) 34.16.532.660 I slot print_timing: id 3 | task 6495 | eval time = 2018.72 ms / 2 tokens ( 2018.72 ms per token, 0.50 tokens per second) 34.16.532.661 I slot print_timing: id 3 | task 6495 | total time = 52703.05 ms / 1782 tokens 34.16.532.661 I slot print_timing: id 3 | task 6495 | graphs reused = 5356 34.16.532.661 I slot print_timing: id 3 | task 6495 | graph reallocs = 0 / 0 (same size) / (changed size) 34.16.532.903 I slot release: id 3 | task 6495 | stop processing: n_tokens = 1781, truncated = 0 34.16.532.927 I slot print_timing: id 0 | task 6500 | prompt processing, n_tokens = 421, progress = 0.45, t = 15.83 s / 26.59 tokens per second 34.16.554.560 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1023, t_last = 88845348417 34.16.554.619 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 798.587 MiB) 34.20.536.946 I slot launch_slot_: id 1 | task 6505 | processing task, is_child = 0 34.20.537.001 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 809.904 MiB) 34.20.668.176 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 801.651 MiB) 34.20.774.115 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 925, t_last = 88845348955 34.20.774.235 I slot launch_slot_: id 2 | task 6506 | processing task, is_child = 0 34.20.774.309 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1781, t_last = 88845349580 34.20.774.411 I slot launch_slot_: id 3 | task 6507 | processing task, is_child = 0 34.20.774.424 I slot print_timing: id 0 | task 6500 | prompt processing, n_tokens = 753, progress = 0.80, t = 15.85 s / 47.50 tokens per second 34.27.025.855 I slot print_timing: id 0 | task 6500 | prompt processing, n_tokens = 933, progress = 1.00, t = 26.33 s / 35.44 tokens per second 34.27.453.198 I slot print_timing: id 1 | task 6505 | prompt processing, n_tokens = 118, progress = 0.16, t = 6.23 s / 18.96 tokens per second 34.27.457.797 I slot print_timing: id 2 | task 6506 | prompt processing, n_tokens = 118, progress = 0.17, t = 6.23 s / 18.96 tokens per second 34.27.462.215 I slot print_timing: id 3 | task 6507 | prompt processing, n_tokens = 140, progress = 0.16, t = 6.23 s / 22.49 tokens per second 34.31.887.269 I slot print_timing: id 1 | task 6505 | prompt processing, n_tokens = 225, progress = 0.30, t = 11.09 s / 20.30 tokens per second 34.31.894.064 I slot print_timing: id 2 | task 6506 | prompt processing, n_tokens = 197, progress = 0.28, t = 11.09 s / 17.77 tokens per second 34.31.898.489 I slot print_timing: id 3 | task 6507 | prompt processing, n_tokens = 268, progress = 0.30, t = 11.09 s / 24.17 tokens per second 34.42.263.349 I slot print_timing: id 0 | task 6500 | prompt eval time = 31186.70 ms / 937 tokens ( 33.28 ms per token, 30.04 tokens per second) 34.42.263.351 I slot print_timing: id 0 | task 6500 | eval time = 10376.08 ms / 2 tokens (10376.08 ms per token, 0.10 tokens per second) 34.42.263.352 I slot print_timing: id 0 | task 6500 | total time = 41562.79 ms / 939 tokens 34.42.263.352 I slot print_timing: id 0 | task 6500 | graphs reused = 5356 34.42.263.353 I slot print_timing: id 0 | task 6500 | graph reallocs = 0 / 0 (same size) / (changed size) 34.42.263.413 I slot release: id 0 | task 6500 | stop processing: n_tokens = 938, truncated = 0 34.42.263.426 I slot print_timing: id 1 | task 6505 | prompt processing, n_tokens = 603, progress = 0.81, t = 21.46 s / 28.10 tokens per second 34.42.268.779 I slot print_timing: id 2 | task 6506 | prompt processing, n_tokens = 603, progress = 0.85, t = 21.46 s / 28.10 tokens per second 34.42.273.863 I slot print_timing: id 3 | task 6507 | prompt processing, n_tokens = 364, progress = 0.41, t = 21.46 s / 16.96 tokens per second 34.46.385.965 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 938, t_last = 88871080087 34.46.386.026 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 798.274 MiB) 34.49.997.085 I slot launch_slot_: id 0 | task 6512 | processing task, is_child = 0 34.49.997.175 I slot print_timing: id 1 | task 6505 | prompt processing, n_tokens = 737, progress = 0.99, t = 25.59 s / 28.81 tokens per second 34.50.001.780 I slot print_timing: id 2 | task 6506 | prompt processing, n_tokens = 709, progress = 0.99, t = 25.59 s / 27.71 tokens per second 34.50.006.369 I slot print_timing: id 3 | task 6507 | prompt processing, n_tokens = 769, progress = 0.87, t = 25.59 s / 30.06 tokens per second 34.53.287.620 I slot print_timing: id 0 | task 6512 | prompt processing, n_tokens = 118, progress = 0.16, t = 3.29 s / 35.87 tokens per second 34.53.294.635 I slot print_timing: id 3 | task 6507 | prompt processing, n_tokens = 876, progress = 1.00, t = 32.49 s / 26.97 tokens per second 34.54.797.483 I slot print_timing: id 1 | task 6505 | prompt eval time = 32486.75 ms / 741 tokens ( 43.84 ms per token, 22.81 tokens per second) 34.54.797.486 I slot print_timing: id 1 | task 6505 | eval time = 1510.09 ms / 2 tokens ( 1510.09 ms per token, 0.66 tokens per second) 34.54.797.486 I slot print_timing: id 1 | task 6505 | total time = 33996.84 ms / 743 tokens 34.54.797.487 I slot print_timing: id 1 | task 6505 | graphs reused = 5356 34.54.797.487 I slot print_timing: id 1 | task 6505 | graph reallocs = 0 / 0 (same size) / (changed size) 34.54.797.552 I slot release: id 1 | task 6505 | stop processing: n_tokens = 742, truncated = 0 34.54.797.777 I slot print_timing: id 2 | task 6506 | prompt eval time = 32486.88 ms / 713 tokens ( 45.56 ms per token, 21.95 tokens per second) 34.54.797.780 I slot print_timing: id 2 | task 6506 | eval time = 1510.17 ms / 2 tokens ( 1510.17 ms per token, 0.66 tokens per second) 34.54.797.781 I slot print_timing: id 2 | task 6506 | total time = 33997.05 ms / 715 tokens 34.54.797.781 I slot print_timing: id 2 | task 6506 | graphs reused = 5356 34.54.797.781 I slot print_timing: id 2 | task 6506 | graph reallocs = 0 / 0 (same size) / (changed size) 34.54.797.810 I slot release: id 2 | task 6506 | stop processing: n_tokens = 714, truncated = 0 34.54.798.019 I slot print_timing: id 0 | task 6512 | prompt processing, n_tokens = 200, progress = 0.28, t = 4.80 s / 41.67 tokens per second 34.59.600.586 I slot print_timing: id 3 | task 6507 | prompt eval time = 33997.23 ms / 880 tokens ( 38.63 ms per token, 25.88 tokens per second) 34.59.600.588 I slot print_timing: id 3 | task 6507 | eval time = 4802.57 ms / 2 tokens ( 4802.57 ms per token, 0.21 tokens per second) 34.59.600.589 I slot print_timing: id 3 | task 6507 | total time = 38799.80 ms / 882 tokens 34.59.600.589 I slot print_timing: id 3 | task 6507 | graphs reused = 5356 34.59.600.590 I slot print_timing: id 3 | task 6507 | graph reallocs = 0 / 0 (same size) / (changed size) 34.59.600.649 I slot release: id 3 | task 6507 | stop processing: n_tokens = 881, truncated = 0 34.59.600.658 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.878 (> 0.100 thold), f_keep = 0.850 34.59.600.716 I slot launch_slot_: id 1 | task 6516 | processing task, is_child = 0 34.59.600.769 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 801.088 MiB) 34.59.703.775 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 799.775 MiB) 34.59.817.216 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.870 (> 0.100 thold), f_keep = 0.884 34.59.817.295 I slot launch_slot_: id 2 | task 6517 | processing task, is_child = 0 34.59.817.344 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 881, t_last = 88888417323 34.59.817.413 I slot launch_slot_: id 3 | task 6518 | processing task, is_child = 0 34.59.817.420 I slot print_timing: id 0 | task 6512 | prompt processing, n_tokens = 603, progress = 0.84, t = 9.60 s / 62.79 tokens per second 35.05.555.796 I slot print_timing: id 0 | task 6512 | prompt processing, n_tokens = 712, progress = 0.99, t = 15.56 s / 45.76 tokens per second 35.05.840.912 I slot print_timing: id 1 | task 6516 | prompt processing, n_tokens = 112, progress = 0.99, t = 5.71 s / 19.61 tokens per second 35.05.845.368 I slot print_timing: id 2 | task 6517 | prompt processing, n_tokens = 118, progress = 0.99, t = 5.70 s / 20.69 tokens per second 35.05.849.872 I slot print_timing: id 3 | task 6518 | prompt processing, n_tokens = 133, progress = 0.15, t = 5.70 s / 23.35 tokens per second 35.08.019.985 I slot print_timing: id 3 | task 6518 | prompt processing, n_tokens = 277, progress = 0.32, t = 8.16 s / 33.95 tokens per second 35.09.362.630 I slot print_timing: id 0 | task 6512 | prompt eval time = 18022.44 ms / 716 tokens ( 25.17 ms per token, 39.73 tokens per second) 35.09.362.635 I slot print_timing: id 0 | task 6512 | eval time = 1343.09 ms / 2 tokens ( 1343.09 ms per token, 0.74 tokens per second) 35.09.362.635 I slot print_timing: id 0 | task 6512 | total time = 19365.53 ms / 718 tokens 35.09.362.636 I slot print_timing: id 0 | task 6512 | graphs reused = 5356 35.09.362.636 I slot print_timing: id 0 | task 6512 | graph reallocs = 0 / 0 (same size) / (changed size) 35.09.362.688 I slot release: id 0 | task 6512 | stop processing: n_tokens = 717, truncated = 0 35.09.362.913 I slot print_timing: id 1 | task 6516 | prompt eval time = 8175.60 ms / 116 tokens ( 70.48 ms per token, 14.19 tokens per second) 35.09.362.916 I slot print_timing: id 1 | task 6516 | eval time = 1343.15 ms / 2 tokens ( 1343.15 ms per token, 0.74 tokens per second) 35.09.362.916 I slot print_timing: id 1 | task 6516 | total time = 9518.75 ms / 118 tokens 35.09.362.917 I slot print_timing: id 1 | task 6516 | graphs reused = 5356 35.09.362.917 I slot print_timing: id 1 | task 6516 | graph reallocs = 0 / 0 (same size) / (changed size) 35.09.362.941 I slot release: id 1 | task 6516 | stop processing: n_tokens = 720, truncated = 0 35.09.363.193 I slot print_timing: id 2 | task 6517 | prompt eval time = 8168.22 ms / 122 tokens ( 66.95 ms per token, 14.94 tokens per second) 35.09.363.195 I slot print_timing: id 2 | task 6517 | eval time = 1343.22 ms / 2 tokens ( 1343.22 ms per token, 0.74 tokens per second) 35.09.363.196 I slot print_timing: id 2 | task 6517 | total time = 9511.43 ms / 124 tokens 35.09.363.196 I slot print_timing: id 2 | task 6517 | graphs reused = 5356 35.09.363.196 I slot print_timing: id 2 | task 6517 | graph reallocs = 0 / 0 (same size) / (changed size) 35.09.363.217 I slot release: id 2 | task 6517 | stop processing: n_tokens = 726, truncated = 0 35.09.363.230 I slot print_timing: id 3 | task 6518 | prompt processing, n_tokens = 360, progress = 0.41, t = 9.50 s / 37.88 tokens per second 35.09.375.965 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 717, t_last = 88898179362 35.09.376.014 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 808.403 MiB) 35.14.065.763 I slot launch_slot_: id 0 | task 6523 | processing task, is_child = 0 35.14.065.811 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 804.214 MiB) 35.14.148.239 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 803.214 MiB) 35.14.251.167 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 720, t_last = 88898179615 35.14.251.283 I slot launch_slot_: id 1 | task 6524 | processing task, is_child = 0 35.14.251.324 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 726, t_last = 88898179891 35.14.251.381 I slot launch_slot_: id 2 | task 6525 | processing task, is_child = 0 35.14.251.543 I slot print_timing: id 3 | task 6518 | prompt processing, n_tokens = 766, progress = 0.87, t = 9.52 s / 80.49 tokens per second 35.19.348.109 I slot print_timing: id 0 | task 6523 | prompt processing, n_tokens = 142, progress = 0.14, t = 5.10 s / 27.86 tokens per second 35.20.864.128 I slot print_timing: id 1 | task 6524 | prompt processing, n_tokens = 142, progress = 0.14, t = 5.10 s / 27.86 tokens per second 35.20.868.904 I slot print_timing: id 2 | task 6525 | prompt processing, n_tokens = 142, progress = 0.14, t = 5.10 s / 27.86 tokens per second 35.20.873.536 I slot print_timing: id 3 | task 6518 | prompt processing, n_tokens = 872, progress = 1.00, t = 19.49 s / 44.74 tokens per second 35.28.170.453 I slot print_timing: id 0 | task 6523 | prompt processing, n_tokens = 345, progress = 0.35, t = 13.92 s / 24.79 tokens per second 35.28.170.465 I slot print_timing: id 1 | task 6524 | prompt processing, n_tokens = 345, progress = 0.34, t = 13.92 s / 24.79 tokens per second 35.28.170.473 I slot print_timing: id 2 | task 6525 | prompt processing, n_tokens = 345, progress = 0.33, t = 13.92 s / 24.79 tokens per second 35.33.861.160 I slot print_timing: id 3 | task 6518 | prompt eval time = 28311.10 ms / 876 tokens ( 32.32 ms per token, 30.94 tokens per second) 35.33.861.166 I slot print_timing: id 3 | task 6518 | eval time = 5690.72 ms / 2 tokens ( 5690.72 ms per token, 0.18 tokens per second) 35.33.861.167 I slot print_timing: id 3 | task 6518 | total time = 34001.81 ms / 878 tokens 35.33.861.167 I slot print_timing: id 3 | task 6518 | graphs reused = 5356 35.33.861.167 I slot print_timing: id 3 | task 6518 | graph reallocs = 0 / 0 (same size) / (changed size) 35.33.861.232 I slot release: id 3 | task 6518 | stop processing: n_tokens = 877, truncated = 0 35.33.861.246 I slot print_timing: id 0 | task 6523 | prompt processing, n_tokens = 476, progress = 0.48, t = 19.61 s / 24.27 tokens per second 35.33.866.806 I slot print_timing: id 1 | task 6524 | prompt processing, n_tokens = 490, progress = 0.49, t = 19.61 s / 24.99 tokens per second 35.33.871.424 I slot print_timing: id 2 | task 6525 | prompt processing, n_tokens = 518, progress = 0.50, t = 19.61 s / 26.42 tokens per second 35.46.632.801 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 877, t_last = 88922677909 35.46.632.859 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 809.904 MiB) 35.46.919.016 I slot launch_slot_: id 3 | task 6530 | processing task, is_child = 0 35.46.919.032 I slot print_timing: id 0 | task 6523 | prompt processing, n_tokens = 861, progress = 0.87, t = 32.38 s / 26.59 tokens per second 35.46.928.923 I slot print_timing: id 1 | task 6524 | prompt processing, n_tokens = 861, progress = 0.86, t = 32.38 s / 26.59 tokens per second 35.46.933.333 I slot print_timing: id 2 | task 6525 | prompt processing, n_tokens = 861, progress = 0.83, t = 32.38 s / 26.59 tokens per second 35.53.688.771 I slot print_timing: id 0 | task 6523 | prompt processing, n_tokens = 988, progress = 1.00, t = 39.44 s / 25.05 tokens per second 35.54.124.386 I slot print_timing: id 1 | task 6524 | prompt processing, n_tokens = 1002, progress = 1.00, t = 39.44 s / 25.41 tokens per second 35.54.128.941 I slot print_timing: id 2 | task 6525 | prompt processing, n_tokens = 1030, progress = 1.00, t = 39.44 s / 26.12 tokens per second 35.54.133.540 I slot print_timing: id 3 | task 6530 | prompt processing, n_tokens = 142, progress = 0.14, t = 6.75 s / 21.03 tokens per second 35.57.020.126 I slot print_timing: id 3 | task 6530 | prompt processing, n_tokens = 345, progress = 0.35, t = 10.08 s / 34.22 tokens per second 35.59.050.757 I slot print_timing: id 0 | task 6523 | prompt eval time = 42768.30 ms / 992 tokens ( 43.11 ms per token, 23.19 tokens per second) 35.59.050.763 I slot print_timing: id 0 | task 6523 | eval time = 2031.06 ms / 2 tokens ( 2031.06 ms per token, 0.49 tokens per second) 35.59.050.764 I slot print_timing: id 0 | task 6523 | total time = 44799.37 ms / 994 tokens 35.59.050.764 I slot print_timing: id 0 | task 6523 | graphs reused = 5356 35.59.050.765 I slot print_timing: id 0 | task 6523 | graph reallocs = 0 / 0 (same size) / (changed size) 35.59.050.811 I slot release: id 0 | task 6523 | stop processing: n_tokens = 993, truncated = 0 35.59.051.037 I slot print_timing: id 1 | task 6524 | prompt eval time = 42768.45 ms / 1006 tokens ( 42.51 ms per token, 23.52 tokens per second) 35.59.051.039 I slot print_timing: id 1 | task 6524 | eval time = 2031.14 ms / 2 tokens ( 2031.14 ms per token, 0.49 tokens per second) 35.59.051.040 I slot print_timing: id 1 | task 6524 | total time = 44799.59 ms / 1008 tokens 35.59.051.040 I slot print_timing: id 1 | task 6524 | graphs reused = 5356 35.59.051.040 I slot print_timing: id 1 | task 6524 | graph reallocs = 0 / 0 (same size) / (changed size) 35.59.051.077 I slot release: id 1 | task 6524 | stop processing: n_tokens = 1007, truncated = 0 35.59.051.321 I slot print_timing: id 2 | task 6525 | prompt eval time = 42768.62 ms / 1034 tokens ( 41.36 ms per token, 24.18 tokens per second) 35.59.051.332 I slot print_timing: id 2 | task 6525 | eval time = 2031.21 ms / 2 tokens ( 2031.21 ms per token, 0.49 tokens per second) 35.59.051.335 I slot print_timing: id 2 | task 6525 | total time = 44799.82 ms / 1036 tokens 35.59.051.335 I slot print_timing: id 2 | task 6525 | graphs reused = 5356 35.59.051.335 I slot print_timing: id 2 | task 6525 | graph reallocs = 0 / 0 (same size) / (changed size) 35.59.051.367 I slot release: id 2 | task 6525 | stop processing: n_tokens = 1035, truncated = 0 35.59.051.374 I slot print_timing: id 3 | task 6530 | prompt processing, n_tokens = 483, progress = 0.48, t = 12.11 s / 39.88 tokens per second 35.59.065.157 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.895 (> 0.100 thold), f_keep = 0.895 35.59.065.196 I slot launch_slot_: id 0 | task 6535 | processing task, is_child = 0 35.59.065.250 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 812.092 MiB) 36.03.388.026 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 805.965 MiB) 36.03.423.736 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1007, t_last = 88947867751 36.03.423.866 I slot launch_slot_: id 1 | task 6536 | processing task, is_child = 0 36.03.423.926 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1035, t_last = 88947868041 36.03.423.994 I slot launch_slot_: id 2 | task 6537 | processing task, is_child = 0 36.03.431.733 I slot print_timing: id 3 | task 6530 | prompt processing, n_tokens = 861, progress = 0.86, t = 12.13 s / 71.00 tokens per second 36.10.432.747 I slot print_timing: id 0 | task 6535 | prompt processing, n_tokens = 128, progress = 1.00, t = 7.01 s / 18.26 tokens per second 36.10.865.404 I slot print_timing: id 1 | task 6536 | prompt processing, n_tokens = 193, progress = 0.22, t = 7.00 s / 27.57 tokens per second 36.10.870.141 I slot print_timing: id 2 | task 6537 | prompt processing, n_tokens = 115, progress = 0.11, t = 7.00 s / 16.43 tokens per second 36.10.874.609 I slot print_timing: id 3 | task 6530 | prompt processing, n_tokens = 995, progress = 1.00, t = 23.50 s / 42.35 tokens per second 36.15.246.368 I slot print_timing: id 1 | task 6536 | prompt processing, n_tokens = 327, progress = 0.37, t = 11.81 s / 27.68 tokens per second 36.15.246.382 I slot print_timing: id 2 | task 6537 | prompt processing, n_tokens = 293, progress = 0.29, t = 11.81 s / 24.80 tokens per second 36.18.860.625 I slot print_timing: id 0 | task 6535 | prompt eval time = 11822.14 ms / 132 tokens ( 89.56 ms per token, 11.17 tokens per second) 36.18.860.630 I slot print_timing: id 0 | task 6535 | eval time = 3614.48 ms / 2 tokens ( 3614.48 ms per token, 0.28 tokens per second) 36.18.860.631 I slot print_timing: id 0 | task 6535 | total time = 15436.62 ms / 134 tokens 36.18.860.631 I slot print_timing: id 0 | task 6535 | graphs reused = 5356 36.18.860.632 I slot print_timing: id 0 | task 6535 | graph reallocs = 0 / 0 (same size) / (changed size) 36.18.860.668 I slot release: id 0 | task 6535 | stop processing: n_tokens = 994, truncated = 0 36.18.860.882 I slot print_timing: id 3 | task 6530 | prompt eval time = 28308.63 ms / 999 tokens ( 28.34 ms per token, 35.29 tokens per second) 36.18.860.884 I slot print_timing: id 3 | task 6530 | eval time = 3614.52 ms / 2 tokens ( 3614.52 ms per token, 0.28 tokens per second) 36.18.860.885 I slot print_timing: id 3 | task 6530 | total time = 31923.15 ms / 1001 tokens 36.18.860.885 I slot print_timing: id 3 | task 6530 | graphs reused = 5356 36.18.860.885 I slot print_timing: id 3 | task 6530 | graph reallocs = 0 / 0 (same size) / (changed size) 36.18.860.913 I slot release: id 3 | task 6530 | stop processing: n_tokens = 1000, truncated = 0 36.18.860.921 I slot print_timing: id 1 | task 6536 | prompt processing, n_tokens = 363, progress = 0.41, t = 15.43 s / 23.53 tokens per second 36.18.866.941 I slot print_timing: id 2 | task 6537 | prompt processing, n_tokens = 502, progress = 0.49, t = 15.43 s / 32.54 tokens per second 36.25.016.197 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 994, t_last = 88967677342 36.25.016.257 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 859.484 MiB) 36.26.155.302 I slot launch_slot_: id 0 | task 6542 | processing task, is_child = 0 36.26.155.363 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 806.777 MiB) 36.26.183.691 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1000, t_last = 88967677587 36.26.183.797 I slot launch_slot_: id 3 | task 6543 | processing task, is_child = 0 36.26.183.876 I slot print_timing: id 1 | task 6536 | prompt processing, n_tokens = 730, progress = 0.83, t = 21.58 s / 33.82 tokens per second 36.26.188.397 I slot print_timing: id 2 | task 6537 | prompt processing, n_tokens = 773, progress = 0.76, t = 21.58 s / 35.81 tokens per second 36.32.412.195 I slot print_timing: id 0 | task 6542 | prompt processing, n_tokens = 115, progress = 0.13, t = 6.23 s / 18.46 tokens per second 36.33.556.596 I slot print_timing: id 1 | task 6536 | prompt processing, n_tokens = 875, progress = 1.00, t = 28.98 s / 30.19 tokens per second 36.33.561.114 I slot print_timing: id 2 | task 6537 | prompt processing, n_tokens = 1014, progress = 1.00, t = 28.98 s / 34.99 tokens per second 36.33.565.618 I slot print_timing: id 3 | task 6543 | prompt processing, n_tokens = 115, progress = 0.11, t = 6.22 s / 18.49 tokens per second 36.38.260.633 I slot print_timing: id 0 | task 6542 | prompt processing, n_tokens = 293, progress = 0.33, t = 12.08 s / 24.26 tokens per second 36.38.260.645 I slot print_timing: id 3 | task 6543 | prompt processing, n_tokens = 293, progress = 0.29, t = 12.07 s / 24.28 tokens per second 36.42.135.646 I slot print_timing: id 1 | task 6536 | prompt eval time = 34828.79 ms / 879 tokens ( 39.62 ms per token, 25.24 tokens per second) 36.42.135.649 I slot print_timing: id 1 | task 6536 | eval time = 3875.24 ms / 2 tokens ( 3875.24 ms per token, 0.26 tokens per second) 36.42.135.649 I slot print_timing: id 1 | task 6536 | total time = 38704.04 ms / 881 tokens 36.42.135.649 I slot print_timing: id 1 | task 6536 | graphs reused = 5356 36.42.135.650 I slot print_timing: id 1 | task 6536 | graph reallocs = 0 / 0 (same size) / (changed size) 36.42.135.702 I slot release: id 1 | task 6536 | stop processing: n_tokens = 880, truncated = 0 36.42.135.940 I slot print_timing: id 2 | task 6537 | prompt eval time = 34828.95 ms / 1018 tokens ( 34.21 ms per token, 29.23 tokens per second) 36.42.135.942 I slot print_timing: id 2 | task 6537 | eval time = 3875.32 ms / 2 tokens ( 3875.32 ms per token, 0.26 tokens per second) 36.42.135.942 I slot print_timing: id 2 | task 6537 | total time = 38704.27 ms / 1020 tokens 36.42.135.943 I slot print_timing: id 2 | task 6537 | graphs reused = 5356 36.42.135.943 I slot print_timing: id 2 | task 6537 | graph reallocs = 0 / 0 (same size) / (changed size) 36.42.136.002 I slot release: id 2 | task 6537 | stop processing: n_tokens = 1019, truncated = 0 36.42.136.009 I slot print_timing: id 0 | task 6542 | prompt processing, n_tokens = 380, progress = 0.42, t = 15.95 s / 23.82 tokens per second 36.42.142.049 I slot print_timing: id 3 | task 6543 | prompt processing, n_tokens = 493, progress = 0.49, t = 15.94 s / 30.92 tokens per second 36.46.825.869 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.813 (> 0.100 thold), f_keep = 0.786 36.46.825.952 I slot launch_slot_: id 2 | task 6548 | processing task, is_child = 0 36.46.826.008 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 792.772 MiB) 36.50.099.807 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 880, t_last = 88990952376 36.50.099.919 I slot launch_slot_: id 1 | task 6549 | processing task, is_child = 0 36.50.099.930 I slot print_timing: id 0 | task 6542 | prompt processing, n_tokens = 773, progress = 0.86, t = 20.64 s / 37.45 tokens per second 36.50.111.992 I slot print_timing: id 3 | task 6543 | prompt processing, n_tokens = 773, progress = 0.77, t = 20.63 s / 37.46 tokens per second 36.57.936.069 I slot print_timing: id 0 | task 6542 | prompt processing, n_tokens = 892, progress = 1.00, t = 31.75 s / 28.09 tokens per second 36.58.366.298 I slot print_timing: id 1 | task 6549 | prompt processing, n_tokens = 115, progress = 0.13, t = 7.83 s / 14.68 tokens per second 36.58.370.809 I slot print_timing: id 2 | task 6548 | prompt processing, n_tokens = 208, progress = 1.00, t = 7.83 s / 26.56 tokens per second 36.58.375.567 I slot print_timing: id 3 | task 6543 | prompt processing, n_tokens = 1005, progress = 1.00, t = 31.74 s / 31.66 tokens per second 37.00.898.068 I slot print_timing: id 1 | task 6549 | prompt processing, n_tokens = 293, progress = 0.32, t = 10.79 s / 27.15 tokens per second 37.02.396.750 I slot print_timing: id 0 | task 6542 | prompt eval time = 34713.83 ms / 896 tokens ( 38.74 ms per token, 25.81 tokens per second) 37.02.396.753 I slot print_timing: id 0 | task 6542 | eval time = 1499.12 ms / 2 tokens ( 1499.12 ms per token, 0.67 tokens per second) 37.02.396.753 I slot print_timing: id 0 | task 6542 | total time = 36212.94 ms / 898 tokens 37.02.396.754 I slot print_timing: id 0 | task 6542 | graphs reused = 5356 37.02.396.754 I slot print_timing: id 0 | task 6542 | graph reallocs = 0 / 0 (same size) / (changed size) 37.02.396.798 I slot release: id 0 | task 6542 | stop processing: n_tokens = 897, truncated = 0 37.02.397.037 I slot print_timing: id 2 | task 6548 | prompt eval time = 10793.41 ms / 212 tokens ( 50.91 ms per token, 19.64 tokens per second) 37.02.397.039 I slot print_timing: id 2 | task 6548 | eval time = 1499.20 ms / 2 tokens ( 1499.20 ms per token, 0.67 tokens per second) 37.02.397.040 I slot print_timing: id 2 | task 6548 | total time = 12292.60 ms / 214 tokens 37.02.397.040 I slot print_timing: id 2 | task 6548 | graphs reused = 5356 37.02.397.040 I slot print_timing: id 2 | task 6548 | graph reallocs = 0 / 0 (same size) / (changed size) 37.02.397.089 I slot release: id 2 | task 6548 | stop processing: n_tokens = 986, truncated = 0 37.02.397.330 I slot print_timing: id 3 | task 6543 | prompt eval time = 34705.24 ms / 1009 tokens ( 34.40 ms per token, 29.07 tokens per second) 37.02.397.332 I slot print_timing: id 3 | task 6543 | eval time = 1499.27 ms / 2 tokens ( 1499.27 ms per token, 0.67 tokens per second) 37.02.397.332 I slot print_timing: id 3 | task 6543 | total time = 36204.51 ms / 1011 tokens 37.02.397.333 I slot print_timing: id 3 | task 6543 | graphs reused = 5356 37.02.397.333 I slot print_timing: id 3 | task 6543 | graph reallocs = 0 / 0 (same size) / (changed size) 37.02.397.373 I slot release: id 3 | task 6543 | stop processing: n_tokens = 1010, truncated = 0 37.02.397.379 I slot print_timing: id 1 | task 6549 | prompt processing, n_tokens = 386, progress = 0.43, t = 12.29 s / 31.40 tokens per second 37.02.409.689 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.909 (> 0.100 thold), f_keep = 0.893 37.02.409.727 I slot launch_slot_: id 0 | task 6554 | processing task, is_child = 0 37.02.409.780 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 803.214 MiB) 37.07.081.964 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 792.960 MiB) 37.07.120.114 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 986, t_last = 89011213763 37.07.120.235 I slot launch_slot_: id 2 | task 6555 | processing task, is_child = 0 37.07.120.286 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1010, t_last = 89011214047 37.07.120.353 I slot launch_slot_: id 3 | task 6556 | processing task, is_child = 0 37.07.127.958 I slot print_timing: id 1 | task 6549 | prompt processing, n_tokens = 773, progress = 0.86, t = 12.31 s / 62.82 tokens per second 37.12.607.651 I slot print_timing: id 0 | task 6554 | prompt processing, n_tokens = 104, progress = 1.00, t = 5.49 s / 18.95 tokens per second 37.12.882.640 I slot print_timing: id 1 | task 6549 | prompt processing, n_tokens = 898, progress = 1.00, t = 22.50 s / 39.91 tokens per second 37.12.887.886 I slot print_timing: id 2 | task 6555 | prompt processing, n_tokens = 116, progress = 0.12, t = 5.48 s / 21.19 tokens per second 37.12.892.307 I slot print_timing: id 3 | task 6556 | prompt processing, n_tokens = 116, progress = 0.13, t = 5.48 s / 21.19 tokens per second 37.15.781.125 I slot print_timing: id 2 | task 6555 | prompt processing, n_tokens = 232, progress = 0.24, t = 8.65 s / 26.83 tokens per second 37.15.781.137 I slot print_timing: id 3 | task 6556 | prompt processing, n_tokens = 232, progress = 0.26, t = 8.65 s / 26.83 tokens per second 37.20.360.955 I slot print_timing: id 0 | task 6554 | prompt eval time = 8660.52 ms / 108 tokens ( 80.19 ms per token, 12.47 tokens per second) 37.20.360.960 I slot print_timing: id 0 | task 6554 | eval time = 4580.06 ms / 2 tokens ( 4580.06 ms per token, 0.22 tokens per second) 37.20.360.961 I slot print_timing: id 0 | task 6554 | total time = 13240.58 ms / 110 tokens 37.20.360.961 I slot print_timing: id 0 | task 6554 | graphs reused = 5356 37.20.360.962 I slot print_timing: id 0 | task 6554 | graph reallocs = 0 / 0 (same size) / (changed size) 37.20.361.003 I slot release: id 0 | task 6554 | stop processing: n_tokens = 882, truncated = 0 37.20.361.237 I slot print_timing: id 1 | task 6549 | prompt eval time = 25676.74 ms / 902 tokens ( 28.47 ms per token, 35.13 tokens per second) 37.20.361.240 I slot print_timing: id 1 | task 6549 | eval time = 4580.12 ms / 2 tokens ( 4580.12 ms per token, 0.22 tokens per second) 37.20.361.240 I slot print_timing: id 1 | task 6549 | total time = 30256.87 ms / 904 tokens 37.20.361.240 I slot print_timing: id 1 | task 6549 | graphs reused = 5356 37.20.361.241 I slot print_timing: id 1 | task 6549 | graph reallocs = 0 / 0 (same size) / (changed size) 37.20.361.266 I slot release: id 1 | task 6549 | stop processing: n_tokens = 903, truncated = 0 37.20.361.273 I slot print_timing: id 2 | task 6555 | prompt processing, n_tokens = 436, progress = 0.46, t = 13.23 s / 32.96 tokens per second 37.20.366.966 I slot print_timing: id 3 | task 6556 | prompt processing, n_tokens = 390, progress = 0.43, t = 13.23 s / 29.48 tokens per second 37.28.252.815 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 882, t_last = 89029177677 37.28.252.877 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 793.148 MiB) 37.29.021.937 I slot launch_slot_: id 0 | task 6561 | processing task, is_child = 0 37.29.021.992 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 793.523 MiB) 37.29.065.660 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 903, t_last = 89029177940 37.29.065.764 I slot launch_slot_: id 1 | task 6562 | processing task, is_child = 0 37.29.065.910 I slot print_timing: id 2 | task 6555 | prompt processing, n_tokens = 774, progress = 0.81, t = 21.12 s / 36.65 tokens per second 37.29.070.355 I slot print_timing: id 3 | task 6556 | prompt processing, n_tokens = 774, progress = 0.85, t = 21.12 s / 36.65 tokens per second 37.36.452.311 I slot print_timing: id 0 | task 6561 | prompt processing, n_tokens = 116, progress = 0.12, t = 7.39 s / 15.70 tokens per second 37.36.614.143 I slot print_timing: id 1 | task 6562 | prompt processing, n_tokens = 176, progress = 0.13, t = 7.39 s / 23.83 tokens per second 37.36.618.565 I slot print_timing: id 2 | task 6555 | prompt processing, n_tokens = 948, progress = 1.00, t = 29.32 s / 32.33 tokens per second 37.36.623.091 I slot print_timing: id 3 | task 6556 | prompt processing, n_tokens = 902, progress = 1.00, t = 29.32 s / 30.76 tokens per second 37.41.337.766 I slot print_timing: id 0 | task 6561 | prompt processing, n_tokens = 232, progress = 0.25, t = 12.27 s / 18.91 tokens per second 37.41.337.779 I slot print_timing: id 1 | task 6562 | prompt processing, n_tokens = 431, progress = 0.32, t = 12.27 s / 35.12 tokens per second 37.48.348.497 I slot print_timing: id 2 | task 6555 | prompt eval time = 34205.15 ms / 952 tokens ( 35.93 ms per token, 27.83 tokens per second) 37.48.348.501 I slot print_timing: id 2 | task 6555 | eval time = 7010.97 ms / 2 tokens ( 7010.97 ms per token, 0.14 tokens per second) 37.48.348.502 I slot print_timing: id 2 | task 6555 | total time = 41216.12 ms / 954 tokens 37.48.348.503 I slot print_timing: id 2 | task 6555 | graphs reused = 5356 37.48.348.503 I slot print_timing: id 2 | task 6555 | graph reallocs = 0 / 0 (same size) / (changed size) 37.48.348.566 I slot release: id 2 | task 6555 | stop processing: n_tokens = 953, truncated = 0 37.48.348.780 I slot print_timing: id 3 | task 6556 | prompt eval time = 34205.32 ms / 906 tokens ( 37.75 ms per token, 26.49 tokens per second) 37.48.348.786 I slot print_timing: id 3 | task 6556 | eval time = 7011.02 ms / 2 tokens ( 7011.02 ms per token, 0.14 tokens per second) 37.48.348.787 I slot print_timing: id 3 | task 6556 | total time = 41216.34 ms / 908 tokens 37.48.348.787 I slot print_timing: id 3 | task 6556 | graphs reused = 5356 37.48.348.787 I slot print_timing: id 3 | task 6556 | graph reallocs = 0 / 0 (same size) / (changed size) 37.48.348.820 I slot release: id 3 | task 6556 | stop processing: n_tokens = 907, truncated = 0 37.48.348.829 I slot print_timing: id 0 | task 6561 | prompt processing, n_tokens = 424, progress = 0.45, t = 19.28 s / 21.99 tokens per second 37.48.356.908 I slot print_timing: id 1 | task 6562 | prompt processing, n_tokens = 840, progress = 0.62, t = 19.28 s / 43.56 tokens per second 37.55.555.162 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 953, t_last = 89057165240 37.55.555.223 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 802.964 MiB) 37.56.319.036 I slot launch_slot_: id 2 | task 6567 | processing task, is_child = 0 37.56.319.089 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 811.092 MiB) 37.56.337.833 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 907, t_last = 89057165494 37.56.337.930 I slot launch_slot_: id 3 | task 6568 | processing task, is_child = 0 37.56.337.938 I slot print_timing: id 0 | task 6561 | prompt processing, n_tokens = 774, progress = 0.82, t = 26.49 s / 29.22 tokens per second 37.56.342.394 I slot print_timing: id 1 | task 6562 | prompt processing, n_tokens = 1152, progress = 0.85, t = 26.49 s / 43.49 tokens per second 38.04.746.901 I slot print_timing: id 0 | task 6561 | prompt processing, n_tokens = 936, progress = 1.00, t = 35.68 s / 26.23 tokens per second 38.05.179.193 I slot print_timing: id 1 | task 6562 | prompt processing, n_tokens = 1352, progress = 1.00, t = 35.68 s / 37.89 tokens per second 38.05.183.732 I slot print_timing: id 2 | task 6567 | prompt processing, n_tokens = 176, progress = 0.14, t = 8.40 s / 20.95 tokens per second 38.05.188.159 I slot print_timing: id 3 | task 6568 | prompt processing, n_tokens = 176, progress = 0.13, t = 8.40 s / 20.95 tokens per second 38.11.286.680 I slot print_timing: id 2 | task 6567 | prompt processing, n_tokens = 431, progress = 0.34, t = 14.94 s / 28.85 tokens per second 38.11.286.695 I slot print_timing: id 3 | task 6568 | prompt processing, n_tokens = 431, progress = 0.32, t = 14.94 s / 28.85 tokens per second 38.19.807.376 I slot print_timing: id 0 | task 6561 | prompt eval time = 42220.70 ms / 940 tokens ( 44.92 ms per token, 22.26 tokens per second) 38.19.807.382 I slot print_timing: id 0 | task 6561 | eval time = 8520.90 ms / 2 tokens ( 8520.90 ms per token, 0.12 tokens per second) 38.19.807.383 I slot print_timing: id 0 | task 6561 | total time = 50741.60 ms / 942 tokens 38.19.807.383 I slot print_timing: id 0 | task 6561 | graphs reused = 5356 38.19.807.384 I slot print_timing: id 0 | task 6561 | graph reallocs = 0 / 0 (same size) / (changed size) 38.19.807.432 I slot release: id 0 | task 6561 | stop processing: n_tokens = 941, truncated = 0 38.19.807.583 I slot print_timing: id 1 | task 6562 | prompt eval time = 42220.82 ms / 1356 tokens ( 31.14 ms per token, 32.12 tokens per second) 38.19.807.586 I slot print_timing: id 1 | task 6562 | eval time = 8520.92 ms / 2 tokens ( 8520.92 ms per token, 0.12 tokens per second) 38.19.807.586 I slot print_timing: id 1 | task 6562 | total time = 50741.74 ms / 1358 tokens 38.19.807.587 I slot print_timing: id 1 | task 6562 | graphs reused = 5356 38.19.807.587 I slot print_timing: id 1 | task 6562 | graph reallocs = 0 / 0 (same size) / (changed size) 38.19.807.649 I slot release: id 1 | task 6562 | stop processing: n_tokens = 1357, truncated = 0 38.19.807.660 I slot print_timing: id 2 | task 6567 | prompt processing, n_tokens = 743, progress = 0.59, t = 23.46 s / 31.67 tokens per second 38.19.813.894 I slot print_timing: id 3 | task 6568 | prompt processing, n_tokens = 826, progress = 0.62, t = 23.46 s / 35.21 tokens per second 38.27.401.771 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 941, t_last = 89088624106 38.27.401.835 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 812.842 MiB) 38.28.552.499 I slot launch_slot_: id 0 | task 6573 | processing task, is_child = 0 38.28.552.567 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 810.279 MiB) 38.28.572.051 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.870 38.28.572.109 I slot launch_slot_: id 1 | task 6574 | processing task, is_child = 0 38.28.579.724 I slot print_timing: id 2 | task 6567 | prompt processing, n_tokens = 1152, progress = 0.92, t = 31.05 s / 37.10 tokens per second 38.28.584.147 I slot print_timing: id 3 | task 6568 | prompt processing, n_tokens = 1152, progress = 0.86, t = 31.05 s / 37.10 tokens per second 38.34.707.381 I slot print_timing: id 0 | task 6573 | prompt processing, n_tokens = 139, progress = 0.18, t = 6.14 s / 22.66 tokens per second 38.35.861.426 I slot print_timing: id 1 | task 6574 | prompt processing, n_tokens = 144, progress = 1.00, t = 6.14 s / 23.47 tokens per second 38.35.865.947 I slot print_timing: id 2 | task 6567 | prompt processing, n_tokens = 1255, progress = 1.00, t = 38.36 s / 32.72 tokens per second 38.35.870.419 I slot print_timing: id 3 | task 6568 | prompt processing, n_tokens = 1338, progress = 1.00, t = 38.36 s / 34.88 tokens per second 38.38.038.646 I slot print_timing: id 0 | task 6573 | prompt processing, n_tokens = 276, progress = 0.35, t = 9.47 s / 29.16 tokens per second 38.42.916.422 I slot print_timing: id 1 | task 6574 | prompt eval time = 9465.99 ms / 148 tokens ( 63.96 ms per token, 15.63 tokens per second) 38.42.916.428 I slot print_timing: id 1 | task 6574 | eval time = 4878.23 ms / 2 tokens ( 4878.23 ms per token, 0.20 tokens per second) 38.42.916.428 I slot print_timing: id 1 | task 6574 | total time = 14344.22 ms / 150 tokens 38.42.916.429 I slot print_timing: id 1 | task 6574 | graphs reused = 5356 38.42.916.429 I slot print_timing: id 1 | task 6574 | graph reallocs = 0 / 0 (same size) / (changed size) 38.42.916.477 I slot release: id 1 | task 6574 | stop processing: n_tokens = 1301, truncated = 0 38.42.916.707 I slot print_timing: id 2 | task 6567 | prompt eval time = 41691.56 ms / 1259 tokens ( 33.11 ms per token, 30.20 tokens per second) 38.42.916.709 I slot print_timing: id 2 | task 6567 | eval time = 4878.30 ms / 2 tokens ( 4878.30 ms per token, 0.20 tokens per second) 38.42.916.709 I slot print_timing: id 2 | task 6567 | total time = 46569.86 ms / 1261 tokens 38.42.916.710 I slot print_timing: id 2 | task 6567 | graphs reused = 5356 38.42.916.710 I slot print_timing: id 2 | task 6567 | graph reallocs = 0 / 0 (same size) / (changed size) 38.42.916.744 I slot release: id 2 | task 6567 | stop processing: n_tokens = 1260, truncated = 0 38.42.916.985 I slot print_timing: id 3 | task 6568 | prompt eval time = 41691.72 ms / 1342 tokens ( 31.07 ms per token, 32.19 tokens per second) 38.42.916.987 I slot print_timing: id 3 | task 6568 | eval time = 4878.35 ms / 2 tokens ( 4878.35 ms per token, 0.20 tokens per second) 38.42.916.987 I slot print_timing: id 3 | task 6568 | total time = 46570.07 ms / 1344 tokens 38.42.916.988 I slot print_timing: id 3 | task 6568 | graphs reused = 5356 38.42.916.988 I slot print_timing: id 3 | task 6568 | graph reallocs = 0 / 0 (same size) / (changed size) 38.42.917.020 I slot release: id 3 | task 6568 | stop processing: n_tokens = 1343, truncated = 0 38.42.917.028 I slot print_timing: id 0 | task 6573 | prompt processing, n_tokens = 681, progress = 0.86, t = 14.34 s / 47.48 tokens per second 38.42.929.029 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1301, t_last = 89111733151 38.42.929.098 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 810.654 MiB) 38.44.402.325 I slot launch_slot_: id 1 | task 6579 | processing task, is_child = 0 38.44.402.397 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 803.151 MiB) 38.44.437.266 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 809.779 MiB) 38.44.477.776 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1260, t_last = 89111733418 38.44.477.898 I slot launch_slot_: id 2 | task 6580 | processing task, is_child = 0 38.44.477.962 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1343, t_last = 89111733694 38.44.478.041 I slot launch_slot_: id 3 | task 6581 | processing task, is_child = 0 38.44.478.048 I slot print_timing: id 0 | task 6573 | prompt processing, n_tokens = 788, progress = 0.99, t = 14.36 s / 54.89 tokens per second 38.49.959.476 I slot print_timing: id 1 | task 6579 | prompt processing, n_tokens = 139, progress = 0.17, t = 5.48 s / 25.38 tokens per second 38.49.965.514 I slot print_timing: id 2 | task 6580 | prompt processing, n_tokens = 149, progress = 0.17, t = 5.48 s / 27.21 tokens per second 38.49.969.932 I slot print_timing: id 3 | task 6581 | prompt processing, n_tokens = 149, progress = 0.17, t = 5.48 s / 27.21 tokens per second 38.55.168.606 I slot print_timing: id 0 | task 6573 | prompt eval time = 21387.35 ms / 792 tokens ( 27.00 ms per token, 37.03 tokens per second) 38.55.168.612 I slot print_timing: id 0 | task 6573 | eval time = 5209.14 ms / 2 tokens ( 5209.14 ms per token, 0.19 tokens per second) 38.55.168.613 I slot print_timing: id 0 | task 6573 | total time = 26596.48 ms / 794 tokens 38.55.168.613 I slot print_timing: id 0 | task 6573 | graphs reused = 5356 38.55.168.614 I slot print_timing: id 0 | task 6573 | graph reallocs = 0 / 0 (same size) / (changed size) 38.55.168.674 I slot release: id 0 | task 6573 | stop processing: n_tokens = 793, truncated = 0 38.55.168.687 I slot print_timing: id 1 | task 6579 | prompt processing, n_tokens = 287, progress = 0.36, t = 10.69 s / 26.86 tokens per second 38.55.168.695 I slot print_timing: id 2 | task 6580 | prompt processing, n_tokens = 285, progress = 0.33, t = 10.69 s / 26.67 tokens per second 38.55.168.700 I slot print_timing: id 3 | task 6581 | prompt processing, n_tokens = 285, progress = 0.32, t = 10.69 s / 26.67 tokens per second 38.56.944.943 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 793, t_last = 89123985349 38.56.944.993 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 811.279 MiB) 38.57.376.733 I slot launch_slot_: id 0 | task 6585 | processing task, is_child = 0 38.57.376.804 I slot print_timing: id 1 | task 6579 | prompt processing, n_tokens = 292, progress = 0.36, t = 12.46 s / 23.43 tokens per second 38.57.381.347 I slot print_timing: id 2 | task 6580 | prompt processing, n_tokens = 343, progress = 0.40, t = 12.46 s / 27.52 tokens per second 38.57.385.814 I slot print_timing: id 3 | task 6581 | prompt processing, n_tokens = 375, progress = 0.42, t = 12.46 s / 30.09 tokens per second 39.13.104.354 I slot print_timing: id 0 | task 6585 | prompt processing, n_tokens = 163, progress = 0.21, t = 15.73 s / 10.36 tokens per second 39.13.379.842 I slot print_timing: id 1 | task 6579 | prompt processing, n_tokens = 681, progress = 0.84, t = 28.62 s / 23.79 tokens per second 39.13.384.268 I slot print_timing: id 2 | task 6580 | prompt processing, n_tokens = 741, progress = 0.86, t = 28.62 s / 25.89 tokens per second 39.13.388.657 I slot print_timing: id 3 | task 6581 | prompt processing, n_tokens = 741, progress = 0.83, t = 28.62 s / 25.89 tokens per second 39.19.083.190 I slot print_timing: id 0 | task 6585 | prompt processing, n_tokens = 274, progress = 0.35, t = 21.71 s / 12.62 tokens per second 39.19.517.896 I slot print_timing: id 1 | task 6579 | prompt processing, n_tokens = 804, progress = 1.00, t = 34.60 s / 23.24 tokens per second 39.19.522.522 I slot print_timing: id 2 | task 6580 | prompt processing, n_tokens = 855, progress = 1.00, t = 34.60 s / 24.71 tokens per second 39.19.527.319 I slot print_timing: id 3 | task 6581 | prompt processing, n_tokens = 887, progress = 1.00, t = 34.60 s / 25.64 tokens per second 39.24.180.886 I slot print_timing: id 0 | task 6585 | prompt processing, n_tokens = 655, progress = 0.83, t = 26.80 s / 24.44 tokens per second 39.26.209.680 I slot print_timing: id 1 | task 6579 | prompt eval time = 39697.77 ms / 808 tokens ( 49.13 ms per token, 20.35 tokens per second) 39.26.209.683 I slot print_timing: id 1 | task 6579 | eval time = 2029.23 ms / 2 tokens ( 2029.23 ms per token, 0.49 tokens per second) 39.26.209.683 I slot print_timing: id 1 | task 6579 | total time = 41727.00 ms / 810 tokens 39.26.209.684 I slot print_timing: id 1 | task 6579 | graphs reused = 5356 39.26.209.684 I slot print_timing: id 1 | task 6579 | graph reallocs = 0 / 0 (same size) / (changed size) 39.26.209.723 I slot release: id 1 | task 6579 | stop processing: n_tokens = 809, truncated = 0 39.26.209.956 I slot print_timing: id 2 | task 6580 | prompt eval time = 39697.88 ms / 859 tokens ( 46.21 ms per token, 21.64 tokens per second) 39.26.209.958 I slot print_timing: id 2 | task 6580 | eval time = 2029.30 ms / 2 tokens ( 2029.30 ms per token, 0.49 tokens per second) 39.26.209.959 I slot print_timing: id 2 | task 6580 | total time = 41727.18 ms / 861 tokens 39.26.209.959 I slot print_timing: id 2 | task 6580 | graphs reused = 5356 39.26.209.959 I slot print_timing: id 2 | task 6580 | graph reallocs = 0 / 0 (same size) / (changed size) 39.26.209.995 I slot release: id 2 | task 6580 | stop processing: n_tokens = 860, truncated = 0 39.26.210.237 I slot print_timing: id 3 | task 6581 | prompt eval time = 39698.01 ms / 891 tokens ( 44.55 ms per token, 22.44 tokens per second) 39.26.210.241 I slot print_timing: id 3 | task 6581 | eval time = 2029.37 ms / 2 tokens ( 2029.37 ms per token, 0.49 tokens per second) 39.26.210.241 I slot print_timing: id 3 | task 6581 | total time = 41727.38 ms / 893 tokens 39.26.210.242 I slot print_timing: id 3 | task 6581 | graphs reused = 5356 39.26.210.242 I slot print_timing: id 3 | task 6581 | graph reallocs = 0 / 0 (same size) / (changed size) 39.26.210.266 I slot release: id 3 | task 6581 | stop processing: n_tokens = 892, truncated = 0 39.26.210.272 I slot print_timing: id 0 | task 6585 | prompt processing, n_tokens = 786, progress = 0.99, t = 28.83 s / 27.26 tokens per second 39.26.393.381 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 809, t_last = 89155026397 39.26.393.441 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 803.276 MiB) 39.26.413.246 I slot launch_slot_: id 1 | task 6591 | processing task, is_child = 0 39.26.413.296 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 804.589 MiB) 39.26.435.512 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 807.715 MiB) 39.26.454.932 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 860, t_last = 89155026669 39.26.455.036 I slot launch_slot_: id 2 | task 6592 | processing task, is_child = 0 39.26.455.082 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 892, t_last = 89155026940 39.26.455.146 I slot launch_slot_: id 3 | task 6593 | processing task, is_child = 0 39.32.423.177 I slot print_timing: id 0 | task 6585 | prompt eval time = 29016.63 ms / 790 tokens ( 36.73 ms per token, 27.23 tokens per second) 39.32.423.179 I slot print_timing: id 0 | task 6585 | eval time = 6029.80 ms / 2 tokens ( 6029.80 ms per token, 0.17 tokens per second) 39.32.423.180 I slot print_timing: id 0 | task 6585 | total time = 35046.43 ms / 792 tokens 39.32.423.180 I slot print_timing: id 0 | task 6585 | graphs reused = 5356 39.32.423.181 I slot print_timing: id 0 | task 6585 | graph reallocs = 0 / 0 (same size) / (changed size) 39.32.423.220 I slot release: id 0 | task 6585 | stop processing: n_tokens = 791, truncated = 0 39.32.423.232 I slot print_timing: id 1 | task 6591 | prompt processing, n_tokens = 163, progress = 0.21, t = 5.97 s / 27.31 tokens per second 39.32.429.927 I slot print_timing: id 2 | task 6592 | prompt processing, n_tokens = 163, progress = 0.21, t = 5.97 s / 27.31 tokens per second 39.32.434.469 I slot print_timing: id 3 | task 6593 | prompt processing, n_tokens = 163, progress = 0.19, t = 5.97 s / 27.31 tokens per second 39.35.878.483 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.852 (> 0.100 thold), f_keep = 0.863 39.35.878.550 I slot launch_slot_: id 0 | task 6596 | processing task, is_child = 0 39.36.316.167 I slot print_timing: id 1 | task 6591 | prompt processing, n_tokens = 262, progress = 0.34, t = 9.42 s / 27.80 tokens per second 39.36.320.626 I slot print_timing: id 2 | task 6592 | prompt processing, n_tokens = 258, progress = 0.33, t = 9.42 s / 27.38 tokens per second 39.36.325.020 I slot print_timing: id 3 | task 6593 | prompt processing, n_tokens = 287, progress = 0.34, t = 9.42 s / 30.46 tokens per second 39.47.941.577 I slot print_timing: id 0 | task 6596 | prompt processing, n_tokens = 143, progress = 1.00, t = 12.06 s / 11.85 tokens per second 39.48.110.463 I slot print_timing: id 1 | task 6591 | prompt processing, n_tokens = 655, progress = 0.84, t = 21.49 s / 30.48 tokens per second 39.48.114.877 I slot print_timing: id 2 | task 6592 | prompt processing, n_tokens = 655, progress = 0.85, t = 21.49 s / 30.48 tokens per second 39.48.119.274 I slot print_timing: id 3 | task 6593 | prompt processing, n_tokens = 339, progress = 0.40, t = 21.49 s / 15.78 tokens per second 39.55.181.606 I slot print_timing: id 1 | task 6591 | prompt processing, n_tokens = 774, progress = 0.99, t = 28.73 s / 26.94 tokens per second 39.55.187.085 I slot print_timing: id 2 | task 6592 | prompt processing, n_tokens = 770, progress = 0.99, t = 28.73 s / 26.80 tokens per second 39.55.191.558 I slot print_timing: id 3 | task 6593 | prompt processing, n_tokens = 655, progress = 0.77, t = 28.73 s / 22.80 tokens per second 39.57.883.812 I slot print_timing: id 0 | task 6596 | prompt eval time = 19303.04 ms / 147 tokens ( 131.31 ms per token, 7.62 tokens per second) 39.57.883.817 I slot print_timing: id 0 | task 6596 | eval time = 2702.21 ms / 2 tokens ( 2702.21 ms per token, 0.37 tokens per second) 39.57.883.817 I slot print_timing: id 0 | task 6596 | total time = 22005.25 ms / 149 tokens 39.57.883.818 I slot print_timing: id 0 | task 6596 | graphs reused = 5356 39.57.883.818 I slot print_timing: id 0 | task 6596 | graph reallocs = 0 / 0 (same size) / (changed size) 39.57.883.863 I slot release: id 0 | task 6596 | stop processing: n_tokens = 803, truncated = 0 39.57.884.240 I slot print_timing: id 3 | task 6593 | prompt processing, n_tokens = 851, progress = 1.00, t = 31.43 s / 27.08 tokens per second 39.58.254.775 I slot print_timing: id 1 | task 6591 | prompt eval time = 31428.88 ms / 778 tokens ( 40.40 ms per token, 24.75 tokens per second) 39.58.254.780 I slot print_timing: id 1 | task 6591 | eval time = 370.74 ms / 2 tokens ( 370.74 ms per token, 2.70 tokens per second) 39.58.254.781 I slot print_timing: id 1 | task 6591 | total time = 31799.62 ms / 780 tokens 39.58.254.781 I slot print_timing: id 1 | task 6591 | graphs reused = 5356 39.58.254.782 I slot print_timing: id 1 | task 6591 | graph reallocs = 0 / 0 (same size) / (changed size) 39.58.254.822 I slot release: id 1 | task 6591 | stop processing: n_tokens = 779, truncated = 0 39.58.254.962 I slot print_timing: id 2 | task 6592 | prompt eval time = 31429.01 ms / 774 tokens ( 40.61 ms per token, 24.63 tokens per second) 39.58.254.967 I slot print_timing: id 2 | task 6592 | eval time = 370.73 ms / 2 tokens ( 370.73 ms per token, 2.70 tokens per second) 39.58.254.967 I slot print_timing: id 2 | task 6592 | total time = 31799.74 ms / 776 tokens 39.58.254.967 I slot print_timing: id 2 | task 6592 | graphs reused = 5356 39.58.254.968 I slot print_timing: id 2 | task 6592 | graph reallocs = 0 / 0 (same size) / (changed size) 39.58.254.998 I slot release: id 2 | task 6592 | stop processing: n_tokens = 775, truncated = 0 39.58.255.188 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 803, t_last = 89186700537 39.58.255.243 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 804.839 MiB) 39.58.275.248 I slot launch_slot_: id 0 | task 6601 | processing task, is_child = 0 39.58.275.297 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 806.965 MiB) 39.58.293.526 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 832.975 MiB) 39.58.311.722 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 779, t_last = 89187071496 39.58.311.833 I slot launch_slot_: id 1 | task 6602 | processing task, is_child = 0 39.58.311.875 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 775, t_last = 89187071672 39.58.311.943 I slot launch_slot_: id 2 | task 6603 | processing task, is_child = 0 40.04.976.912 I slot print_timing: id 3 | task 6593 | prompt eval time = 31799.90 ms / 855 tokens ( 37.19 ms per token, 26.89 tokens per second) 40.04.976.914 I slot print_timing: id 3 | task 6593 | eval time = 6721.72 ms / 2 tokens ( 6721.72 ms per token, 0.15 tokens per second) 40.04.976.915 I slot print_timing: id 3 | task 6593 | total time = 38521.62 ms / 857 tokens 40.04.976.915 I slot print_timing: id 3 | task 6593 | graphs reused = 5356 40.04.976.915 I slot print_timing: id 3 | task 6593 | graph reallocs = 0 / 0 (same size) / (changed size) 40.04.976.954 I slot release: id 3 | task 6593 | stop processing: n_tokens = 856, truncated = 0 40.04.976.965 I slot print_timing: id 0 | task 6601 | prompt processing, n_tokens = 183, progress = 0.19, t = 6.66 s / 27.46 tokens per second 40.04.982.889 I slot print_timing: id 1 | task 6602 | prompt processing, n_tokens = 183, progress = 0.19, t = 6.66 s / 27.46 tokens per second 40.04.987.339 I slot print_timing: id 2 | task 6603 | prompt processing, n_tokens = 183, progress = 0.19, t = 6.66 s / 27.46 tokens per second 40.04.997.160 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 856, t_last = 89193793628 40.04.997.212 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 829.473 MiB) 40.10.380.397 I slot launch_slot_: id 3 | task 6606 | processing task, is_child = 0 40.10.380.408 I slot print_timing: id 0 | task 6601 | prompt processing, n_tokens = 333, progress = 0.34, t = 6.69 s / 49.81 tokens per second 40.10.380.420 I slot print_timing: id 1 | task 6602 | prompt processing, n_tokens = 333, progress = 0.35, t = 6.69 s / 49.81 tokens per second 40.10.380.427 I slot print_timing: id 2 | task 6603 | prompt processing, n_tokens = 333, progress = 0.35, t = 6.69 s / 49.81 tokens per second 40.15.642.168 I slot print_timing: id 0 | task 6601 | prompt processing, n_tokens = 455, progress = 0.47, t = 17.33 s / 26.25 tokens per second 40.16.784.776 I slot print_timing: id 1 | task 6602 | prompt processing, n_tokens = 448, progress = 0.46, t = 17.33 s / 25.85 tokens per second 40.16.789.231 I slot print_timing: id 2 | task 6603 | prompt processing, n_tokens = 428, progress = 0.45, t = 17.33 s / 24.70 tokens per second 40.16.793.694 I slot print_timing: id 3 | task 6606 | prompt processing, n_tokens = 183, progress = 0.19, t = 5.26 s / 34.78 tokens per second 40.32.010.464 I slot print_timing: id 0 | task 6601 | prompt processing, n_tokens = 836, progress = 0.86, t = 33.70 s / 24.81 tokens per second 40.32.438.333 I slot print_timing: id 1 | task 6602 | prompt processing, n_tokens = 836, progress = 0.87, t = 33.70 s / 24.81 tokens per second 40.32.442.897 I slot print_timing: id 2 | task 6603 | prompt processing, n_tokens = 836, progress = 0.89, t = 33.70 s / 24.81 tokens per second 40.32.447.484 I slot print_timing: id 3 | task 6606 | prompt processing, n_tokens = 333, progress = 0.35, t = 21.63 s / 15.40 tokens per second 40.38.421.110 I slot print_timing: id 0 | task 6601 | prompt processing, n_tokens = 967, progress = 1.00, t = 40.11 s / 24.11 tokens per second 40.38.595.687 I slot print_timing: id 1 | task 6602 | prompt processing, n_tokens = 960, progress = 1.00, t = 40.11 s / 23.93 tokens per second 40.38.600.215 I slot print_timing: id 2 | task 6603 | prompt processing, n_tokens = 940, progress = 1.00, t = 40.11 s / 23.44 tokens per second 40.38.604.799 I slot print_timing: id 3 | task 6606 | prompt processing, n_tokens = 431, progress = 0.46, t = 28.04 s / 15.37 tokens per second 40.43.637.455 I slot print_timing: id 3 | task 6606 | prompt processing, n_tokens = 836, progress = 0.88, t = 33.26 s / 25.14 tokens per second 40.45.321.214 I slot print_timing: id 0 | task 6601 | prompt eval time = 45325.08 ms / 971 tokens ( 46.68 ms per token, 21.42 tokens per second) 40.45.321.216 I slot print_timing: id 0 | task 6601 | eval time = 1684.18 ms / 2 tokens ( 1684.18 ms per token, 0.59 tokens per second) 40.45.321.216 I slot print_timing: id 0 | task 6601 | total time = 47009.26 ms / 973 tokens 40.45.321.217 I slot print_timing: id 0 | task 6601 | graphs reused = 5356 40.45.321.217 I slot print_timing: id 0 | task 6601 | graph reallocs = 0 / 0 (same size) / (changed size) 40.45.321.256 I slot release: id 0 | task 6601 | stop processing: n_tokens = 972, truncated = 0 40.45.321.406 I slot print_timing: id 1 | task 6602 | prompt eval time = 45325.22 ms / 964 tokens ( 47.02 ms per token, 21.27 tokens per second) 40.45.321.409 I slot print_timing: id 1 | task 6602 | eval time = 1684.17 ms / 2 tokens ( 1684.17 ms per token, 0.59 tokens per second) 40.45.321.409 I slot print_timing: id 1 | task 6602 | total time = 47009.39 ms / 966 tokens 40.45.321.409 I slot print_timing: id 1 | task 6602 | graphs reused = 5356 40.45.321.410 I slot print_timing: id 1 | task 6602 | graph reallocs = 0 / 0 (same size) / (changed size) 40.45.321.436 I slot release: id 1 | task 6602 | stop processing: n_tokens = 965, truncated = 0 40.45.321.658 I slot print_timing: id 2 | task 6603 | prompt eval time = 45325.38 ms / 944 tokens ( 48.01 ms per token, 20.83 tokens per second) 40.45.321.664 I slot print_timing: id 2 | task 6603 | eval time = 1684.21 ms / 2 tokens ( 1684.21 ms per token, 0.59 tokens per second) 40.45.321.665 I slot print_timing: id 2 | task 6603 | total time = 47009.59 ms / 946 tokens 40.45.321.665 I slot print_timing: id 2 | task 6603 | graphs reused = 5356 40.45.321.665 I slot print_timing: id 2 | task 6603 | graph reallocs = 0 / 0 (same size) / (changed size) 40.45.321.692 I slot release: id 2 | task 6603 | stop processing: n_tokens = 945, truncated = 0 40.45.321.700 I slot print_timing: id 3 | task 6606 | prompt processing, n_tokens = 943, progress = 1.00, t = 34.94 s / 26.99 tokens per second 40.45.506.242 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.892 (> 0.100 thold), f_keep = 0.889 40.45.506.280 I slot launch_slot_: id 0 | task 6613 | processing task, is_child = 0 40.45.506.335 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 826.910 MiB) 40.45.527.383 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 832.099 MiB) 40.45.550.052 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 965, t_last = 89234138110 40.45.550.160 I slot launch_slot_: id 1 | task 6614 | processing task, is_child = 0 40.45.550.209 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 945, t_last = 89234138366 40.45.550.284 I slot launch_slot_: id 2 | task 6615 | processing task, is_child = 0 40.51.516.330 I slot print_timing: id 3 | task 6606 | prompt eval time = 35125.80 ms / 947 tokens ( 37.09 ms per token, 26.96 tokens per second) 40.51.516.333 I slot print_timing: id 3 | task 6606 | eval time = 6010.09 ms / 2 tokens ( 6010.09 ms per token, 0.17 tokens per second) 40.51.516.333 I slot print_timing: id 3 | task 6606 | total time = 41135.89 ms / 949 tokens 40.51.516.334 I slot print_timing: id 3 | task 6606 | graphs reused = 5356 40.51.516.334 I slot print_timing: id 3 | task 6606 | graph reallocs = 0 / 0 (same size) / (changed size) 40.51.516.377 I slot release: id 3 | task 6606 | stop processing: n_tokens = 948, truncated = 0 40.51.516.389 I slot print_timing: id 0 | task 6613 | prompt processing, n_tokens = 129, progress = 1.00, t = 5.97 s / 21.62 tokens per second 40.51.523.532 I slot print_timing: id 1 | task 6614 | prompt processing, n_tokens = 162, progress = 0.20, t = 5.96 s / 27.19 tokens per second 40.51.527.954 I slot print_timing: id 2 | task 6615 | prompt processing, n_tokens = 162, progress = 0.20, t = 5.96 s / 27.19 tokens per second 40.54.808.426 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 948, t_last = 89240333051 40.54.808.484 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 797.712 MiB) 40.54.829.363 I slot launch_slot_: id 3 | task 6618 | processing task, is_child = 0 40.54.829.374 I slot print_timing: id 1 | task 6614 | prompt processing, n_tokens = 283, progress = 0.35, t = 9.25 s / 30.59 tokens per second 40.54.833.775 I slot print_timing: id 2 | task 6615 | prompt processing, n_tokens = 282, progress = 0.35, t = 9.25 s / 30.49 tokens per second 41.05.729.767 I slot print_timing: id 0 | task 6613 | prompt eval time = 9258.13 ms / 133 tokens ( 69.61 ms per token, 14.37 tokens per second) 41.05.729.774 I slot print_timing: id 0 | task 6613 | eval time = 10921.34 ms / 2 tokens (10921.34 ms per token, 0.09 tokens per second) 41.05.729.775 I slot print_timing: id 0 | task 6613 | total time = 20179.47 ms / 135 tokens 41.05.729.775 I slot print_timing: id 0 | task 6613 | graphs reused = 5356 41.05.729.776 I slot print_timing: id 0 | task 6613 | graph reallocs = 0 / 0 (same size) / (changed size) 41.05.729.811 I slot release: id 0 | task 6613 | stop processing: n_tokens = 970, truncated = 0 41.05.729.824 I slot print_timing: id 1 | task 6614 | prompt processing, n_tokens = 679, progress = 0.85, t = 20.17 s / 33.66 tokens per second 41.05.735.696 I slot print_timing: id 2 | task 6615 | prompt processing, n_tokens = 679, progress = 0.85, t = 20.17 s / 33.66 tokens per second 41.05.740.128 I slot print_timing: id 3 | task 6618 | prompt processing, n_tokens = 137, progress = 0.14, t = 10.89 s / 12.58 tokens per second 41.09.855.800 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 970, t_last = 89254546485 41.09.855.857 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 798.712 MiB) 41.10.997.241 I slot launch_slot_: id 0 | task 6621 | processing task, is_child = 0 41.10.997.338 I slot print_timing: id 1 | task 6614 | prompt processing, n_tokens = 795, progress = 0.99, t = 24.30 s / 32.72 tokens per second 41.11.001.850 I slot print_timing: id 2 | task 6615 | prompt processing, n_tokens = 794, progress = 0.99, t = 24.30 s / 32.68 tokens per second 41.11.006.331 I slot print_timing: id 3 | task 6618 | prompt processing, n_tokens = 335, progress = 0.34, t = 15.02 s / 22.31 tokens per second 41.14.642.549 I slot print_timing: id 0 | task 6621 | prompt processing, n_tokens = 137, progress = 0.14, t = 3.64 s / 37.59 tokens per second 41.14.651.034 I slot print_timing: id 3 | task 6618 | prompt processing, n_tokens = 459, progress = 0.47, t = 19.80 s / 23.18 tokens per second 41.21.690.005 I slot print_timing: id 1 | task 6614 | prompt eval time = 29084.09 ms / 799 tokens ( 36.40 ms per token, 27.47 tokens per second) 41.21.690.010 I slot print_timing: id 1 | task 6614 | eval time = 7047.69 ms / 2 tokens ( 7047.69 ms per token, 0.14 tokens per second) 41.21.690.012 I slot print_timing: id 1 | task 6614 | total time = 36131.78 ms / 801 tokens 41.21.690.012 I slot print_timing: id 1 | task 6614 | graphs reused = 5356 41.21.690.012 I slot print_timing: id 1 | task 6614 | graph reallocs = 0 / 0 (same size) / (changed size) 41.21.690.057 I slot release: id 1 | task 6614 | stop processing: n_tokens = 800, truncated = 0 41.21.690.282 I slot print_timing: id 2 | task 6615 | prompt eval time = 29084.25 ms / 798 tokens ( 36.45 ms per token, 27.44 tokens per second) 41.21.690.284 I slot print_timing: id 2 | task 6615 | eval time = 7047.74 ms / 2 tokens ( 7047.74 ms per token, 0.14 tokens per second) 41.21.690.284 I slot print_timing: id 2 | task 6615 | total time = 36131.99 ms / 800 tokens 41.21.690.285 I slot print_timing: id 2 | task 6615 | graphs reused = 5356 41.21.690.285 I slot print_timing: id 2 | task 6615 | graph reallocs = 0 / 0 (same size) / (changed size) 41.21.690.317 I slot release: id 2 | task 6615 | stop processing: n_tokens = 799, truncated = 0 41.21.690.326 I slot print_timing: id 0 | task 6621 | prompt processing, n_tokens = 335, progress = 0.35, t = 10.69 s / 31.33 tokens per second 41.21.690.335 I slot print_timing: id 3 | task 6618 | prompt processing, n_tokens = 826, progress = 0.85, t = 26.85 s / 30.76 tokens per second 41.23.157.397 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 800, t_last = 89270506731 41.23.157.450 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 801.901 MiB) 41.25.001.983 I slot launch_slot_: id 1 | task 6625 | processing task, is_child = 0 41.25.002.035 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 803.901 MiB) 41.25.021.160 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 799, t_last = 89270506991 41.25.021.257 I slot launch_slot_: id 2 | task 6626 | processing task, is_child = 0 41.25.021.269 I slot print_timing: id 0 | task 6621 | prompt processing, n_tokens = 437, progress = 0.46, t = 12.16 s / 35.94 tokens per second 41.25.025.823 I slot print_timing: id 3 | task 6618 | prompt processing, n_tokens = 971, progress = 1.00, t = 28.32 s / 34.29 tokens per second 41.33.144.190 I slot print_timing: id 0 | task 6621 | prompt processing, n_tokens = 826, progress = 0.87, t = 22.15 s / 37.30 tokens per second 41.33.150.837 I slot print_timing: id 1 | task 6625 | prompt processing, n_tokens = 137, progress = 0.14, t = 8.12 s / 16.88 tokens per second 41.33.155.260 I slot print_timing: id 2 | task 6626 | prompt processing, n_tokens = 139, progress = 0.15, t = 8.12 s / 17.12 tokens per second 41.39.488.057 I slot print_timing: id 3 | task 6618 | prompt eval time = 38305.98 ms / 975 tokens ( 39.29 ms per token, 25.45 tokens per second) 41.39.488.059 I slot print_timing: id 3 | task 6618 | eval time = 6343.87 ms / 2 tokens ( 6343.87 ms per token, 0.16 tokens per second) 41.39.488.060 I slot print_timing: id 3 | task 6618 | total time = 44649.85 ms / 977 tokens 41.39.488.060 I slot print_timing: id 3 | task 6618 | graphs reused = 5356 41.39.488.061 I slot print_timing: id 3 | task 6618 | graph reallocs = 0 / 0 (same size) / (changed size) 41.39.488.110 I slot release: id 3 | task 6618 | stop processing: n_tokens = 976, truncated = 0 41.39.488.122 I slot print_timing: id 0 | task 6621 | prompt processing, n_tokens = 949, progress = 1.00, t = 28.49 s / 33.31 tokens per second 41.39.495.353 I slot print_timing: id 1 | task 6625 | prompt processing, n_tokens = 335, progress = 0.35, t = 14.46 s / 23.16 tokens per second 41.39.495.365 I slot print_timing: id 2 | task 6626 | prompt processing, n_tokens = 304, progress = 0.33, t = 14.46 s / 21.02 tokens per second 41.42.379.848 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 976, t_last = 89288304784 41.42.379.910 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 798.337 MiB) 41.42.400.480 I slot launch_slot_: id 3 | task 6630 | processing task, is_child = 0 41.42.400.491 I slot print_timing: id 1 | task 6625 | prompt processing, n_tokens = 445, progress = 0.46, t = 17.35 s / 25.64 tokens per second 41.42.404.942 I slot print_timing: id 2 | task 6626 | prompt processing, n_tokens = 414, progress = 0.45, t = 17.35 s / 23.86 tokens per second 41.53.061.136 I slot print_timing: id 0 | task 6621 | prompt eval time = 31382.59 ms / 953 tokens ( 32.93 ms per token, 30.37 tokens per second) 41.53.061.142 I slot print_timing: id 0 | task 6621 | eval time = 10681.29 ms / 2 tokens (10681.29 ms per token, 0.09 tokens per second) 41.53.061.142 I slot print_timing: id 0 | task 6621 | total time = 42063.88 ms / 955 tokens 41.53.061.143 I slot print_timing: id 0 | task 6621 | graphs reused = 5356 41.53.061.143 I slot print_timing: id 0 | task 6621 | graph reallocs = 0 / 0 (same size) / (changed size) 41.53.061.187 I slot release: id 0 | task 6621 | stop processing: n_tokens = 954, truncated = 0 41.53.061.199 I slot print_timing: id 1 | task 6625 | prompt processing, n_tokens = 826, progress = 0.86, t = 28.04 s / 29.46 tokens per second 41.53.067.078 I slot print_timing: id 2 | task 6626 | prompt processing, n_tokens = 779, progress = 0.84, t = 28.04 s / 27.79 tokens per second 41.53.071.516 I slot print_timing: id 3 | task 6630 | prompt processing, n_tokens = 139, progress = 0.15, t = 10.65 s / 13.05 tokens per second 41.58.259.402 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 954, t_last = 89301877861 41.58.259.466 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 796.836 MiB) 41.58.685.656 I slot launch_slot_: id 0 | task 6633 | processing task, is_child = 0 41.58.685.739 I slot print_timing: id 1 | task 6625 | prompt processing, n_tokens = 957, progress = 1.00, t = 33.23 s / 28.80 tokens per second 41.58.690.241 I slot print_timing: id 2 | task 6626 | prompt processing, n_tokens = 926, progress = 1.00, t = 33.23 s / 27.86 tokens per second 41.58.694.775 I slot print_timing: id 3 | task 6630 | prompt processing, n_tokens = 304, progress = 0.34, t = 15.85 s / 19.18 tokens per second 42.01.981.950 I slot print_timing: id 0 | task 6633 | prompt processing, n_tokens = 139, progress = 0.15, t = 3.30 s / 42.17 tokens per second 42.01.989.495 I slot print_timing: id 3 | task 6630 | prompt processing, n_tokens = 382, progress = 0.43, t = 19.57 s / 19.52 tokens per second 42.09.031.652 I slot print_timing: id 1 | task 6625 | prompt eval time = 36956.00 ms / 961 tokens ( 38.46 ms per token, 26.00 tokens per second) 42.09.031.654 I slot print_timing: id 1 | task 6625 | eval time = 7049.94 ms / 2 tokens ( 7049.94 ms per token, 0.14 tokens per second) 42.09.031.655 I slot print_timing: id 1 | task 6625 | total time = 44005.94 ms / 963 tokens 42.09.031.655 I slot print_timing: id 1 | task 6625 | graphs reused = 5356 42.09.031.656 I slot print_timing: id 1 | task 6625 | graph reallocs = 0 / 0 (same size) / (changed size) 42.09.031.701 I slot release: id 1 | task 6625 | stop processing: n_tokens = 962, truncated = 0 42.09.031.940 I slot print_timing: id 2 | task 6626 | prompt eval time = 36956.17 ms / 930 tokens ( 39.74 ms per token, 25.16 tokens per second) 42.09.031.942 I slot print_timing: id 2 | task 6626 | eval time = 7050.00 ms / 2 tokens ( 7050.00 ms per token, 0.14 tokens per second) 42.09.031.943 I slot print_timing: id 2 | task 6626 | total time = 44006.17 ms / 932 tokens 42.09.031.943 I slot print_timing: id 2 | task 6626 | graphs reused = 5356 42.09.031.943 I slot print_timing: id 2 | task 6626 | graph reallocs = 0 / 0 (same size) / (changed size) 42.09.031.997 I slot release: id 2 | task 6626 | stop processing: n_tokens = 931, truncated = 0 42.09.032.006 I slot print_timing: id 0 | task 6633 | prompt processing, n_tokens = 304, progress = 0.34, t = 10.35 s / 29.38 tokens per second 42.09.032.015 I slot print_timing: id 3 | task 6630 | prompt processing, n_tokens = 779, progress = 0.87, t = 26.62 s / 29.26 tokens per second 42.10.179.736 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.867 42.10.179.794 I slot launch_slot_: id 2 | task 6637 | processing task, is_child = 0 42.10.179.857 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 796.586 MiB) 42.11.662.440 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 962, t_last = 89317848375 42.11.662.565 I slot launch_slot_: id 1 | task 6638 | processing task, is_child = 0 42.11.662.572 I slot print_timing: id 0 | task 6633 | prompt processing, n_tokens = 386, progress = 0.43, t = 11.49 s / 33.58 tokens per second 42.11.674.590 I slot print_timing: id 3 | task 6630 | prompt processing, n_tokens = 894, progress = 1.00, t = 27.77 s / 32.19 tokens per second 42.19.351.863 I slot print_timing: id 0 | task 6633 | prompt processing, n_tokens = 779, progress = 0.86, t = 20.67 s / 37.69 tokens per second 42.19.357.397 I slot print_timing: id 1 | task 6638 | prompt processing, n_tokens = 139, progress = 0.15, t = 7.68 s / 18.09 tokens per second 42.19.362.180 I slot print_timing: id 2 | task 6637 | prompt processing, n_tokens = 107, progress = 1.00, t = 7.68 s / 13.92 tokens per second 42.23.423.288 I slot print_timing: id 3 | task 6630 | prompt eval time = 36942.47 ms / 898 tokens ( 41.14 ms per token, 24.31 tokens per second) 42.23.423.294 I slot print_timing: id 3 | task 6630 | eval time = 4071.43 ms / 2 tokens ( 4071.43 ms per token, 0.25 tokens per second) 42.23.423.294 I slot print_timing: id 3 | task 6630 | total time = 41013.90 ms / 900 tokens 42.23.423.295 I slot print_timing: id 3 | task 6630 | graphs reused = 5356 42.23.423.295 I slot print_timing: id 3 | task 6630 | graph reallocs = 0 / 0 (same size) / (changed size) 42.23.423.335 I slot release: id 3 | task 6630 | stop processing: n_tokens = 899, truncated = 0 42.23.423.348 I slot print_timing: id 0 | task 6633 | prompt processing, n_tokens = 898, progress = 1.00, t = 24.74 s / 36.30 tokens per second 42.23.431.184 I slot print_timing: id 1 | task 6638 | prompt processing, n_tokens = 304, progress = 0.34, t = 11.76 s / 25.86 tokens per second 42.24.857.293 I slot print_timing: id 2 | task 6637 | prompt eval time = 11756.03 ms / 111 tokens ( 105.91 ms per token, 9.44 tokens per second) 42.24.857.296 I slot print_timing: id 2 | task 6637 | eval time = 1434.18 ms / 2 tokens ( 1434.18 ms per token, 0.70 tokens per second) 42.24.857.296 I slot print_timing: id 2 | task 6637 | total time = 13190.21 ms / 113 tokens 42.24.857.297 I slot print_timing: id 2 | task 6637 | graphs reused = 5356 42.24.857.297 I slot print_timing: id 2 | task 6637 | graph reallocs = 0 / 0 (same size) / (changed size) 42.24.857.349 I slot release: id 2 | task 6637 | stop processing: n_tokens = 891, truncated = 0 42.24.857.356 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 899, t_last = 89332240010 42.24.857.410 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 801.651 MiB) 42.24.879.712 I slot launch_slot_: id 3 | task 6642 | processing task, is_child = 0 42.24.879.772 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 808.466 MiB) 42.24.898.395 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 891, t_last = 89333674023 42.24.898.490 I slot launch_slot_: id 2 | task 6643 | processing task, is_child = 0 42.24.898.497 I slot print_timing: id 1 | task 6638 | prompt processing, n_tokens = 383, progress = 0.43, t = 13.19 s / 29.04 tokens per second 42.34.280.661 I slot print_timing: id 0 | task 6633 | prompt eval time = 26171.41 ms / 902 tokens ( 29.01 ms per token, 34.47 tokens per second) 42.34.280.663 I slot print_timing: id 0 | task 6633 | eval time = 9423.58 ms / 2 tokens ( 9423.58 ms per token, 0.11 tokens per second) 42.34.280.664 I slot print_timing: id 0 | task 6633 | total time = 35594.99 ms / 904 tokens 42.34.280.664 I slot print_timing: id 0 | task 6633 | graphs reused = 5356 42.34.280.665 I slot print_timing: id 0 | task 6633 | graph reallocs = 0 / 0 (same size) / (changed size) 42.34.280.705 I slot release: id 0 | task 6633 | stop processing: n_tokens = 903, truncated = 0 42.34.280.715 I slot print_timing: id 1 | task 6638 | prompt processing, n_tokens = 779, progress = 0.87, t = 22.61 s / 34.45 tokens per second 42.34.286.038 I slot print_timing: id 2 | task 6643 | prompt processing, n_tokens = 189, progress = 0.15, t = 9.38 s / 20.15 tokens per second 42.34.290.739 I slot print_timing: id 3 | task 6642 | prompt processing, n_tokens = 189, progress = 0.15, t = 9.38 s / 20.15 tokens per second 42.38.313.980 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 903, t_last = 89343097379 42.38.314.043 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 807.215 MiB) 42.40.874.419 I slot launch_slot_: id 0 | task 6646 | processing task, is_child = 0 42.40.874.513 I slot print_timing: id 1 | task 6638 | prompt processing, n_tokens = 895, progress = 1.00, t = 26.65 s / 33.59 tokens per second 42.40.879.392 I slot print_timing: id 2 | task 6643 | prompt processing, n_tokens = 402, progress = 0.33, t = 13.41 s / 29.98 tokens per second 42.40.879.404 I slot print_timing: id 3 | task 6642 | prompt processing, n_tokens = 402, progress = 0.33, t = 13.41 s / 29.98 tokens per second 42.50.536.612 I slot print_timing: id 0 | task 6646 | prompt processing, n_tokens = 189, progress = 0.15, t = 9.66 s / 19.56 tokens per second 42.50.542.073 I slot print_timing: id 2 | task 6643 | prompt processing, n_tokens = 720, progress = 0.58, t = 25.63 s / 28.09 tokens per second 42.50.546.849 I slot print_timing: id 3 | task 6642 | prompt processing, n_tokens = 709, progress = 0.58, t = 25.63 s / 27.66 tokens per second 43.01.472.764 I slot print_timing: id 1 | task 6638 | prompt eval time = 38869.60 ms / 899 tokens ( 43.24 ms per token, 23.13 tokens per second) 43.01.472.769 I slot print_timing: id 1 | task 6638 | eval time = 10936.16 ms / 2 tokens (10936.16 ms per token, 0.09 tokens per second) 43.01.472.770 I slot print_timing: id 1 | task 6638 | total time = 49805.76 ms / 901 tokens 43.01.472.770 I slot print_timing: id 1 | task 6638 | graphs reused = 5356 43.01.472.771 I slot print_timing: id 1 | task 6638 | graph reallocs = 0 / 0 (same size) / (changed size) 43.01.472.821 I slot release: id 1 | task 6638 | stop processing: n_tokens = 900, truncated = 0 43.01.472.835 I slot print_timing: id 0 | task 6646 | prompt processing, n_tokens = 402, progress = 0.31, t = 20.60 s / 19.52 tokens per second 43.01.472.849 I slot print_timing: id 2 | task 6643 | prompt processing, n_tokens = 1061, progress = 0.86, t = 36.57 s / 29.01 tokens per second 43.01.479.415 I slot print_timing: id 3 | task 6642 | prompt processing, n_tokens = 1061, progress = 0.87, t = 36.57 s / 29.01 tokens per second 43.09.416.935 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 900, t_last = 89370289495 43.09.417.003 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 807.403 MiB) 43.09.698.414 I slot launch_slot_: id 1 | task 6650 | processing task, is_child = 0 43.09.698.426 I slot print_timing: id 0 | task 6646 | prompt processing, n_tokens = 774, progress = 0.60, t = 28.54 s / 27.12 tokens per second 43.09.711.998 I slot print_timing: id 2 | task 6643 | prompt processing, n_tokens = 1232, progress = 1.00, t = 44.51 s / 27.68 tokens per second 43.09.716.558 I slot print_timing: id 3 | task 6642 | prompt processing, n_tokens = 1221, progress = 1.00, t = 44.51 s / 27.43 tokens per second 43.18.007.786 I slot print_timing: id 0 | task 6646 | prompt processing, n_tokens = 1061, progress = 0.82, t = 37.13 s / 28.57 tokens per second 43.18.015.509 I slot print_timing: id 1 | task 6650 | prompt processing, n_tokens = 402, progress = 0.16, t = 8.30 s / 48.46 tokens per second 43.27.622.200 I slot print_timing: id 2 | task 6643 | prompt eval time = 53104.36 ms / 1236 tokens ( 42.96 ms per token, 23.27 tokens per second) 43.27.622.202 I slot print_timing: id 2 | task 6643 | eval time = 9614.85 ms / 2 tokens ( 9614.85 ms per token, 0.10 tokens per second) 43.27.622.203 I slot print_timing: id 2 | task 6643 | total time = 62719.21 ms / 1238 tokens 43.27.622.203 I slot print_timing: id 2 | task 6643 | graphs reused = 5356 43.27.622.204 I slot print_timing: id 2 | task 6643 | graph reallocs = 0 / 0 (same size) / (changed size) 43.27.622.252 I slot release: id 2 | task 6643 | stop processing: n_tokens = 1237, truncated = 0 43.27.622.518 I slot print_timing: id 3 | task 6642 | prompt eval time = 53104.71 ms / 1225 tokens ( 43.35 ms per token, 23.07 tokens per second) 43.27.622.521 I slot print_timing: id 3 | task 6642 | eval time = 9614.75 ms / 2 tokens ( 9614.75 ms per token, 0.10 tokens per second) 43.27.622.521 I slot print_timing: id 3 | task 6642 | total time = 62719.46 ms / 1227 tokens 43.27.622.522 I slot print_timing: id 3 | task 6642 | graphs reused = 5356 43.27.622.522 I slot print_timing: id 3 | task 6642 | graph reallocs = 0 / 0 (same size) / (changed size) 43.27.622.552 I slot release: id 3 | task 6642 | stop processing: n_tokens = 1226, truncated = 0 43.27.622.561 I slot print_timing: id 0 | task 6646 | prompt processing, n_tokens = 1286, progress = 1.00, t = 46.75 s / 27.51 tokens per second 43.27.638.852 I slot print_timing: id 1 | task 6650 | prompt processing, n_tokens = 961, progress = 0.37, t = 17.91 s / 53.66 tokens per second 43.40.482.934 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1237, t_last = 89396438926 43.40.483.004 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 808.778 MiB) 43.40.519.982 I slot launch_slot_: id 2 | task 6654 | processing task, is_child = 0 43.40.520.047 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 798.149 MiB) 43.40.555.360 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1226, t_last = 89396439226 43.40.555.477 I slot launch_slot_: id 3 | task 6655 | processing task, is_child = 0 43.40.555.488 I slot print_timing: id 1 | task 6650 | prompt processing, n_tokens = 2071, progress = 0.80, t = 30.77 s / 67.30 tokens per second 43.52.782.525 I slot print_timing: id 0 | task 6646 | prompt eval time = 59608.50 ms / 1290 tokens ( 46.21 ms per token, 21.64 tokens per second) 43.52.782.528 I slot print_timing: id 0 | task 6646 | eval time = 12299.60 ms / 2 tokens (12299.60 ms per token, 0.08 tokens per second) 43.52.782.529 I slot print_timing: id 0 | task 6646 | total time = 71908.09 ms / 1292 tokens 43.52.782.529 I slot print_timing: id 0 | task 6646 | graphs reused = 5356 43.52.782.529 I slot print_timing: id 0 | task 6646 | graph reallocs = 0 / 0 (same size) / (changed size) 43.52.782.587 I slot release: id 0 | task 6646 | stop processing: n_tokens = 1291, truncated = 0 43.52.782.598 I slot print_timing: id 1 | task 6650 | prompt processing, n_tokens = 2288, progress = 0.88, t = 43.07 s / 53.12 tokens per second 43.52.787.813 I slot print_timing: id 2 | task 6654 | prompt processing, n_tokens = 402, progress = 0.15, t = 12.22 s / 32.89 tokens per second 43.52.792.521 I slot print_timing: id 3 | task 6655 | prompt processing, n_tokens = 402, progress = 0.16, t = 12.22 s / 32.89 tokens per second 44.08.753.150 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1291, t_last = 89421599261 44.08.753.224 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 798.087 MiB) 44.09.059.550 I slot launch_slot_: id 0 | task 6658 | processing task, is_child = 0 44.09.059.661 I slot print_timing: id 1 | task 6650 | prompt processing, n_tokens = 2583, progress = 1.00, t = 59.04 s / 43.75 tokens per second 44.09.064.333 I slot print_timing: id 2 | task 6654 | prompt processing, n_tokens = 961, progress = 0.35, t = 28.19 s / 34.09 tokens per second 44.09.064.361 I slot print_timing: id 3 | task 6655 | prompt processing, n_tokens = 961, progress = 0.38, t = 28.19 s / 34.09 tokens per second 44.32.838.329 I slot print_timing: id 0 | task 6658 | prompt processing, n_tokens = 402, progress = 0.15, t = 23.78 s / 16.91 tokens per second 44.32.844.828 I slot print_timing: id 2 | task 6654 | prompt processing, n_tokens = 2226, progress = 0.81, t = 52.28 s / 42.58 tokens per second 44.32.849.271 I slot print_timing: id 3 | task 6655 | prompt processing, n_tokens = 1338, progress = 0.54, t = 52.28 s / 25.59 tokens per second 44.47.905.288 I slot print_timing: id 1 | task 6650 | prompt eval time = 83126.38 ms / 2587 tokens ( 32.13 ms per token, 31.12 tokens per second) 44.47.905.290 I slot print_timing: id 1 | task 6650 | eval time = 15066.97 ms / 2 tokens (15066.97 ms per token, 0.07 tokens per second) 44.47.905.290 I slot print_timing: id 1 | task 6650 | total time = 98193.35 ms / 2589 tokens 44.47.905.291 I slot print_timing: id 1 | task 6650 | graphs reused = 5356 44.47.905.291 I slot print_timing: id 1 | task 6650 | graph reallocs = 0 / 0 (same size) / (changed size) 44.47.905.453 I slot release: id 1 | task 6650 | stop processing: n_tokens = 2588, truncated = 0 44.47.905.470 I slot print_timing: id 0 | task 6658 | prompt processing, n_tokens = 961, progress = 0.36, t = 38.85 s / 24.74 tokens per second 44.47.905.499 I slot print_timing: id 2 | task 6654 | prompt processing, n_tokens = 2288, progress = 0.83, t = 67.35 s / 33.97 tokens per second 44.47.911.957 I slot print_timing: id 3 | task 6655 | prompt processing, n_tokens = 1984, progress = 0.79, t = 67.35 s / 29.46 tokens per second 45.08.268.966 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 2588, t_last = 89476722128 45.08.269.091 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 809.153 MiB) 45.08.269.096 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 807.778 MiB) 45.10.154.809 I slot launch_slot_: id 1 | task 6662 | processing task, is_child = 0 45.10.154.830 I slot print_timing: id 0 | task 6658 | prompt processing, n_tokens = 2139, progress = 0.81, t = 59.21 s / 36.13 tokens per second 45.10.159.449 I slot print_timing: id 2 | task 6654 | prompt processing, n_tokens = 2738, progress = 1.00, t = 87.71 s / 31.22 tokens per second 45.10.164.168 I slot print_timing: id 3 | task 6655 | prompt processing, n_tokens = 2288, progress = 0.92, t = 87.71 s / 26.09 tokens per second 45.17.534.971 I slot print_timing: id 0 | task 6658 | prompt processing, n_tokens = 2288, progress = 0.86, t = 68.48 s / 33.41 tokens per second 45.17.540.738 I slot print_timing: id 1 | task 6662 | prompt processing, n_tokens = 208, progress = 0.12, t = 7.38 s / 28.20 tokens per second 45.17.545.505 I slot print_timing: id 3 | task 6655 | prompt processing, n_tokens = 2496, progress = 1.00, t = 96.97 s / 25.74 tokens per second 45.25.923.786 I slot print_timing: id 2 | task 6654 | prompt eval time = 96975.06 ms / 2742 tokens ( 35.37 ms per token, 28.28 tokens per second) 45.25.923.792 I slot print_timing: id 2 | task 6654 | eval time = 8388.82 ms / 2 tokens ( 8388.82 ms per token, 0.12 tokens per second) 45.25.923.792 I slot print_timing: id 2 | task 6654 | total time = 105363.88 ms / 2744 tokens 45.25.923.793 I slot print_timing: id 2 | task 6654 | graphs reused = 5356 45.25.923.793 I slot print_timing: id 2 | task 6654 | graph reallocs = 0 / 0 (same size) / (changed size) 45.25.923.892 I slot release: id 2 | task 6654 | stop processing: n_tokens = 2743, truncated = 0 45.25.924.157 I slot print_timing: id 0 | task 6658 | prompt processing, n_tokens = 2651, progress = 1.00, t = 76.86 s / 34.49 tokens per second 45.25.931.869 I slot print_timing: id 1 | task 6662 | prompt processing, n_tokens = 520, progress = 0.29, t = 15.76 s / 32.99 tokens per second 45.34.837.887 I slot print_timing: id 3 | task 6655 | prompt eval time = 105364.16 ms / 2500 tokens ( 42.15 ms per token, 23.73 tokens per second) 45.34.837.895 I slot print_timing: id 3 | task 6655 | eval time = 8913.74 ms / 2 tokens ( 8913.74 ms per token, 0.11 tokens per second) 45.34.837.896 I slot print_timing: id 3 | task 6655 | total time = 114277.89 ms / 2502 tokens 45.34.837.896 I slot print_timing: id 3 | task 6655 | graphs reused = 5356 45.34.837.897 I slot print_timing: id 3 | task 6655 | graph reallocs = 0 / 0 (same size) / (changed size) 45.34.837.988 I slot release: id 3 | task 6655 | stop processing: n_tokens = 2501, truncated = 0 45.34.837.998 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 2743, t_last = 89514740566 45.34.838.119 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 808.278 MiB) 45.34.878.059 I slot launch_slot_: id 2 | task 6666 | processing task, is_child = 0 45.34.878.168 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 804.339 MiB) 45.34.918.392 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 2501, t_last = 89523654662 45.34.918.550 I slot launch_slot_: id 3 | task 6667 | processing task, is_child = 0 45.34.918.562 I slot print_timing: id 1 | task 6662 | prompt processing, n_tokens = 1263, progress = 0.71, t = 24.66 s / 51.21 tokens per second 45.42.497.962 I slot print_timing: id 0 | task 6658 | prompt eval time = 85778.13 ms / 2655 tokens ( 32.31 ms per token, 30.95 tokens per second) 45.42.497.964 I slot print_timing: id 0 | task 6658 | eval time = 7660.27 ms / 2 tokens ( 7660.27 ms per token, 0.13 tokens per second) 45.42.497.965 I slot print_timing: id 0 | task 6658 | total time = 93438.40 ms / 2657 tokens 45.42.497.966 I slot print_timing: id 0 | task 6658 | graphs reused = 5356 45.42.497.966 I slot print_timing: id 0 | task 6658 | graph reallocs = 0 / 0 (same size) / (changed size) 45.42.498.071 I slot release: id 0 | task 6658 | stop processing: n_tokens = 2656, truncated = 0 45.42.498.084 I slot print_timing: id 1 | task 6662 | prompt processing, n_tokens = 1447, progress = 0.81, t = 32.34 s / 44.75 tokens per second 45.42.504.806 I slot print_timing: id 2 | task 6666 | prompt processing, n_tokens = 208, progress = 0.11, t = 7.57 s / 27.46 tokens per second 45.42.509.679 I slot print_timing: id 3 | task 6667 | prompt processing, n_tokens = 208, progress = 0.10, t = 7.57 s / 27.46 tokens per second 45.53.448.880 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 2656, t_last = 89531314746 45.53.449.010 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 803.839 MiB) 45.53.751.186 I slot launch_slot_: id 0 | task 6670 | processing task, is_child = 0 45.53.751.375 I slot print_timing: id 1 | task 6662 | prompt processing, n_tokens = 1775, progress = 1.00, t = 43.29 s / 41.00 tokens per second 45.53.755.959 I slot print_timing: id 2 | task 6666 | prompt processing, n_tokens = 520, progress = 0.28, t = 18.53 s / 28.07 tokens per second 45.53.755.980 I slot print_timing: id 3 | task 6667 | prompt processing, n_tokens = 520, progress = 0.25, t = 18.53 s / 28.07 tokens per second 46.16.438.761 I slot print_timing: id 0 | task 6670 | prompt processing, n_tokens = 208, progress = 0.11, t = 22.69 s / 9.17 tokens per second 46.16.445.779 I slot print_timing: id 2 | task 6666 | prompt processing, n_tokens = 1325, progress = 0.72, t = 41.52 s / 31.92 tokens per second 46.16.450.191 I slot print_timing: id 3 | task 6667 | prompt processing, n_tokens = 1447, progress = 0.71, t = 41.52 s / 34.85 tokens per second 46.23.217.778 I slot print_timing: id 1 | task 6662 | prompt eval time = 66279.46 ms / 1779 tokens ( 37.26 ms per token, 26.84 tokens per second) 46.23.217.780 I slot print_timing: id 1 | task 6662 | eval time = 6779.03 ms / 2 tokens ( 6779.03 ms per token, 0.15 tokens per second) 46.23.217.780 I slot print_timing: id 1 | task 6662 | total time = 73058.49 ms / 1781 tokens 46.23.217.781 I slot print_timing: id 1 | task 6662 | graphs reused = 5356 46.23.217.781 I slot print_timing: id 1 | task 6662 | graph reallocs = 0 / 0 (same size) / (changed size) 46.23.217.860 I slot release: id 1 | task 6662 | stop processing: n_tokens = 1780, truncated = 0 46.23.217.872 I slot print_timing: id 0 | task 6670 | prompt processing, n_tokens = 520, progress = 0.28, t = 29.47 s / 17.65 tokens per second 46.23.217.895 I slot print_timing: id 2 | task 6666 | prompt processing, n_tokens = 1447, progress = 0.79, t = 48.29 s / 29.96 tokens per second 46.23.223.912 I slot print_timing: id 3 | task 6667 | prompt processing, n_tokens = 1532, progress = 0.75, t = 48.29 s / 31.72 tokens per second 46.41.654.801 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.756 (> 0.100 thold), f_keep = 0.834 46.41.654.875 I slot launch_slot_: id 1 | task 6674 | processing task, is_child = 0 46.41.654.886 I slot print_timing: id 0 | task 6670 | prompt processing, n_tokens = 1336, progress = 0.72, t = 47.90 s / 27.89 tokens per second 46.43.172.369 I slot print_timing: id 2 | task 6666 | prompt processing, n_tokens = 1837, progress = 1.00, t = 66.73 s / 27.53 tokens per second 46.43.176.958 I slot print_timing: id 3 | task 6667 | prompt processing, n_tokens = 2044, progress = 1.00, t = 66.73 s / 30.63 tokens per second 46.50.874.201 I slot print_timing: id 0 | task 6670 | prompt processing, n_tokens = 1447, progress = 0.78, t = 57.12 s / 25.33 tokens per second 46.50.880.923 I slot print_timing: id 1 | task 6674 | prompt processing, n_tokens = 511, progress = 1.00, t = 7.71 s / 66.29 tokens per second 46.55.998.617 I slot print_timing: id 2 | task 6666 | prompt eval time = 75950.91 ms / 1841 tokens ( 41.26 ms per token, 24.24 tokens per second) 46.55.998.622 I slot print_timing: id 2 | task 6666 | eval time = 5124.67 ms / 2 tokens ( 5124.67 ms per token, 0.20 tokens per second) 46.55.998.622 I slot print_timing: id 2 | task 6666 | total time = 81075.58 ms / 1843 tokens 46.55.998.623 I slot print_timing: id 2 | task 6666 | graphs reused = 5356 46.55.998.623 I slot print_timing: id 2 | task 6666 | graph reallocs = 0 / 0 (same size) / (changed size) 46.55.998.689 I slot release: id 2 | task 6666 | stop processing: n_tokens = 1842, truncated = 0 46.55.998.887 I slot print_timing: id 3 | task 6667 | prompt eval time = 75950.98 ms / 2048 tokens ( 37.09 ms per token, 26.96 tokens per second) 46.55.998.890 I slot print_timing: id 3 | task 6667 | eval time = 5124.70 ms / 2 tokens ( 5124.70 ms per token, 0.20 tokens per second) 46.55.998.890 I slot print_timing: id 3 | task 6667 | total time = 81075.67 ms / 2050 tokens 46.55.998.891 I slot print_timing: id 3 | task 6667 | graphs reused = 5356 46.55.998.891 I slot print_timing: id 3 | task 6667 | graph reallocs = 0 / 0 (same size) / (changed size) 46.55.998.989 I slot release: id 3 | task 6667 | stop processing: n_tokens = 2049, truncated = 0 46.55.999.000 I slot print_timing: id 0 | task 6670 | prompt processing, n_tokens = 1848, progress = 1.00, t = 62.25 s / 29.69 tokens per second 46.56.283.708 I slot print_timing: id 1 | task 6674 | prompt eval time = 12833.69 ms / 515 tokens ( 24.92 ms per token, 40.13 tokens per second) 46.56.283.711 I slot print_timing: id 1 | task 6674 | eval time = 285.23 ms / 2 tokens ( 285.23 ms per token, 3.51 tokens per second) 46.56.283.712 I slot print_timing: id 1 | task 6674 | total time = 13118.92 ms / 517 tokens 46.56.283.712 I slot print_timing: id 1 | task 6674 | graphs reused = 5356 46.56.283.713 I slot print_timing: id 1 | task 6674 | graph reallocs = 0 / 0 (same size) / (changed size) 46.56.283.812 I slot release: id 1 | task 6674 | stop processing: n_tokens = 1963, truncated = 0 46.56.283.822 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1842, t_last = 89604815365 46.56.283.913 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 804.589 MiB) 46.56.325.775 I slot launch_slot_: id 2 | task 6678 | processing task, is_child = 0 46.56.325.865 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 804.402 MiB) 46.56.364.406 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 825.472 MiB) 46.56.403.479 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.833 (> 0.100 thold), f_keep = 0.756 46.56.403.543 I slot launch_slot_: id 1 | task 6679 | processing task, is_child = 0 46.56.403.631 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 2049, t_last = 89604815665 46.56.403.738 I slot launch_slot_: id 3 | task 6680 | processing task, is_child = 0 47.03.923.178 I slot print_timing: id 0 | task 6670 | prompt eval time = 62532.36 ms / 1852 tokens ( 33.76 ms per token, 29.62 tokens per second) 47.03.923.183 I slot print_timing: id 0 | task 6670 | eval time = 7639.61 ms / 2 tokens ( 7639.61 ms per token, 0.13 tokens per second) 47.03.923.184 I slot print_timing: id 0 | task 6670 | total time = 70171.97 ms / 1854 tokens 47.03.923.185 I slot print_timing: id 0 | task 6670 | graphs reused = 5356 47.03.923.185 I slot print_timing: id 0 | task 6670 | graph reallocs = 0 / 0 (same size) / (changed size) 47.03.923.291 I slot release: id 0 | task 6670 | stop processing: n_tokens = 1853, truncated = 0 47.03.923.304 I slot print_timing: id 1 | task 6679 | prompt processing, n_tokens = 330, progress = 1.00, t = 7.52 s / 43.89 tokens per second 47.03.929.409 I slot print_timing: id 2 | task 6678 | prompt processing, n_tokens = 130, progress = 0.18, t = 7.51 s / 17.31 tokens per second 47.03.934.514 I slot print_timing: id 3 | task 6680 | prompt processing, n_tokens = 130, progress = 0.17, t = 7.51 s / 17.31 tokens per second 47.06.529.236 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1853, t_last = 89612739966 47.06.529.340 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 824.784 MiB) 47.06.679.730 I slot launch_slot_: id 0 | task 6683 | processing task, is_child = 0 47.06.679.908 I slot print_timing: id 2 | task 6678 | prompt processing, n_tokens = 210, progress = 0.29, t = 10.12 s / 20.76 tokens per second 47.06.685.540 I slot print_timing: id 3 | task 6680 | prompt processing, n_tokens = 232, progress = 0.31, t = 10.12 s / 22.93 tokens per second 47.17.759.857 I slot print_timing: id 1 | task 6679 | prompt eval time = 10125.49 ms / 334 tokens ( 30.32 ms per token, 32.99 tokens per second) 47.17.759.859 I slot print_timing: id 1 | task 6679 | eval time = 11230.62 ms / 2 tokens (11230.62 ms per token, 0.09 tokens per second) 47.17.759.860 I slot print_timing: id 1 | task 6679 | total time = 21356.11 ms / 336 tokens 47.17.759.860 I slot print_timing: id 1 | task 6679 | graphs reused = 5356 47.17.759.861 I slot print_timing: id 1 | task 6679 | graph reallocs = 0 / 0 (same size) / (changed size) 47.17.759.979 I slot release: id 1 | task 6679 | stop processing: n_tokens = 1782, truncated = 0 47.17.759.994 I slot print_timing: id 0 | task 6683 | prompt processing, n_tokens = 130, progress = 0.17, t = 11.08 s / 11.73 tokens per second 47.17.780.259 I slot print_timing: id 2 | task 6678 | prompt processing, n_tokens = 615, progress = 0.85, t = 21.35 s / 28.81 tokens per second 47.17.789.163 I slot print_timing: id 3 | task 6680 | prompt processing, n_tokens = 615, progress = 0.82, t = 21.35 s / 28.81 tokens per second 47.21.855.966 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1782, t_last = 89626576654 47.21.856.065 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 828.848 MiB) 47.22.884.666 I slot launch_slot_: id 1 | task 6686 | processing task, is_child = 0 47.22.884.682 I slot print_timing: id 0 | task 6683 | prompt processing, n_tokens = 245, progress = 0.32, t = 15.18 s / 16.14 tokens per second 47.22.934.697 I slot print_timing: id 2 | task 6678 | prompt processing, n_tokens = 722, progress = 0.99, t = 25.44 s / 28.38 tokens per second 47.22.952.861 I slot print_timing: id 3 | task 6680 | prompt processing, n_tokens = 744, progress = 0.99, t = 25.44 s / 29.24 tokens per second 47.29.126.866 I slot print_timing: id 0 | task 6683 | prompt processing, n_tokens = 615, progress = 0.81, t = 22.41 s / 27.45 tokens per second 47.29.153.723 I slot print_timing: id 1 | task 6686 | prompt processing, n_tokens = 130, progress = 0.18, t = 6.15 s / 21.14 tokens per second 47.32.015.273 I slot print_timing: id 2 | task 6678 | prompt eval time = 32714.88 ms / 726 tokens ( 45.06 ms per token, 22.19 tokens per second) 47.32.015.278 I slot print_timing: id 2 | task 6678 | eval time = 2888.99 ms / 2 tokens ( 2888.99 ms per token, 0.35 tokens per second) 47.32.015.278 I slot print_timing: id 2 | task 6678 | total time = 35603.88 ms / 728 tokens 47.32.015.279 I slot print_timing: id 2 | task 6678 | graphs reused = 5356 47.32.015.279 I slot print_timing: id 2 | task 6678 | graph reallocs = 0 / 0 (same size) / (changed size) 47.32.015.339 I slot release: id 2 | task 6678 | stop processing: n_tokens = 727, truncated = 0 47.32.015.623 I slot print_timing: id 3 | task 6680 | prompt eval time = 32715.33 ms / 748 tokens ( 43.74 ms per token, 22.86 tokens per second) 47.32.015.626 I slot print_timing: id 3 | task 6680 | eval time = 2888.78 ms / 2 tokens ( 2888.78 ms per token, 0.35 tokens per second) 47.32.015.627 I slot print_timing: id 3 | task 6680 | total time = 35604.11 ms / 750 tokens 47.32.015.627 I slot print_timing: id 3 | task 6680 | graphs reused = 5356 47.32.015.628 I slot print_timing: id 3 | task 6680 | graph reallocs = 0 / 0 (same size) / (changed size) 47.32.015.661 I slot release: id 3 | task 6680 | stop processing: n_tokens = 749, truncated = 0 47.32.015.670 I slot print_timing: id 0 | task 6683 | prompt processing, n_tokens = 757, progress = 0.99, t = 25.34 s / 29.88 tokens per second 47.32.072.894 I slot print_timing: id 1 | task 6686 | prompt processing, n_tokens = 209, progress = 0.29, t = 9.08 s / 23.02 tokens per second 47.36.956.720 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.870 (> 0.100 thold), f_keep = 0.884 47.36.956.796 I slot launch_slot_: id 2 | task 6690 | processing task, is_child = 0 47.36.956.851 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 909.940 MiB) 47.37.151.791 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 749, t_last = 89640832335 47.37.151.896 I slot launch_slot_: id 3 | task 6691 | processing task, is_child = 0 47.37.151.905 I slot print_timing: id 1 | task 6686 | prompt processing, n_tokens = 615, progress = 0.85, t = 14.02 s / 43.86 tokens per second 47.41.662.194 I slot print_timing: id 0 | task 6683 | prompt eval time = 30276.95 ms / 761 tokens ( 39.79 ms per token, 25.13 tokens per second) 47.41.662.197 I slot print_timing: id 0 | task 6683 | eval time = 4705.48 ms / 2 tokens ( 4705.48 ms per token, 0.21 tokens per second) 47.41.662.197 I slot print_timing: id 0 | task 6683 | total time = 34982.43 ms / 763 tokens 47.41.662.198 I slot print_timing: id 0 | task 6683 | graphs reused = 5356 47.41.662.198 I slot print_timing: id 0 | task 6683 | graph reallocs = 0 / 0 (same size) / (changed size) 47.41.662.232 I slot release: id 0 | task 6683 | stop processing: n_tokens = 762, truncated = 0 47.41.662.243 I slot print_timing: id 1 | task 6686 | prompt processing, n_tokens = 721, progress = 0.99, t = 18.73 s / 38.50 tokens per second 47.41.668.479 I slot print_timing: id 2 | task 6690 | prompt processing, n_tokens = 120, progress = 0.99, t = 4.50 s / 26.69 tokens per second 47.41.681.707 I slot print_timing: id 3 | task 6691 | prompt processing, n_tokens = 117, progress = 0.15, t = 4.47 s / 26.17 tokens per second 47.43.831.220 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 762, t_last = 89650478906 47.43.831.274 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 919.631 MiB) 47.43.956.478 I slot launch_slot_: id 0 | task 6694 | processing task, is_child = 0 47.43.956.556 I slot print_timing: id 3 | task 6691 | prompt processing, n_tokens = 257, progress = 0.32, t = 6.64 s / 38.70 tokens per second 47.46.737.214 I slot print_timing: id 1 | task 6686 | prompt eval time = 20896.46 ms / 725 tokens ( 28.82 ms per token, 34.69 tokens per second) 47.46.737.217 I slot print_timing: id 1 | task 6686 | eval time = 2906.22 ms / 2 tokens ( 2906.22 ms per token, 0.34 tokens per second) 47.46.737.218 I slot print_timing: id 1 | task 6686 | total time = 23802.67 ms / 727 tokens 47.46.737.219 I slot print_timing: id 1 | task 6686 | graphs reused = 5356 47.46.737.219 I slot print_timing: id 1 | task 6686 | graph reallocs = 0 / 0 (same size) / (changed size) 47.46.737.255 I slot release: id 1 | task 6686 | stop processing: n_tokens = 726, truncated = 0 47.46.737.494 I slot print_timing: id 2 | task 6690 | prompt eval time = 6666.11 ms / 124 tokens ( 53.76 ms per token, 18.60 tokens per second) 47.46.737.496 I slot print_timing: id 2 | task 6690 | eval time = 2906.28 ms / 2 tokens ( 2906.28 ms per token, 0.34 tokens per second) 47.46.737.496 I slot print_timing: id 2 | task 6690 | total time = 9572.39 ms / 126 tokens 47.46.737.497 I slot print_timing: id 2 | task 6690 | graphs reused = 5356 47.46.737.497 I slot print_timing: id 2 | task 6690 | graph reallocs = 0 / 0 (same size) / (changed size) 47.46.737.521 I slot release: id 2 | task 6690 | stop processing: n_tokens = 740, truncated = 0 47.46.749.224 I slot print_timing: id 3 | task 6691 | prompt processing, n_tokens = 282, progress = 0.35, t = 9.55 s / 29.54 tokens per second 47.48.948.071 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 726, t_last = 89655553929 47.48.948.121 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 904.501 MiB) 47.52.938.232 I slot launch_slot_: id 1 | task 6697 | processing task, is_child = 0 47.52.938.282 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 914.192 MiB) 47.53.069.081 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 740, t_last = 89655554195 47.53.069.185 I slot launch_slot_: id 2 | task 6698 | processing task, is_child = 0 47.53.069.196 I slot print_timing: id 0 | task 6694 | prompt processing, n_tokens = 352, progress = 0.34, t = 4.99 s / 70.52 tokens per second 47.53.069.313 I slot print_timing: id 3 | task 6691 | prompt processing, n_tokens = 631, progress = 0.79, t = 11.76 s / 53.67 tokens per second 48.00.689.173 I slot print_timing: id 0 | task 6694 | prompt processing, n_tokens = 526, progress = 0.50, t = 16.73 s / 31.44 tokens per second 48.00.866.928 I slot print_timing: id 1 | task 6697 | prompt processing, n_tokens = 155, progress = 0.19, t = 7.62 s / 20.34 tokens per second 48.00.879.612 I slot print_timing: id 2 | task 6698 | prompt processing, n_tokens = 155, progress = 0.19, t = 7.62 s / 20.34 tokens per second 48.00.884.073 I slot print_timing: id 3 | task 6691 | prompt processing, n_tokens = 794, progress = 0.99, t = 23.50 s / 33.79 tokens per second 48.08.414.509 I slot print_timing: id 0 | task 6694 | prompt processing, n_tokens = 893, progress = 0.86, t = 24.46 s / 36.51 tokens per second 48.08.421.308 I slot print_timing: id 1 | task 6697 | prompt processing, n_tokens = 277, progress = 0.35, t = 15.35 s / 18.05 tokens per second 48.08.421.315 I slot print_timing: id 2 | task 6698 | prompt processing, n_tokens = 277, progress = 0.34, t = 15.34 s / 18.05 tokens per second 48.11.064.251 I slot print_timing: id 3 | task 6691 | prompt eval time = 31223.74 ms / 798 tokens ( 39.13 ms per token, 25.56 tokens per second) 48.11.064.253 I slot print_timing: id 3 | task 6691 | eval time = 2649.75 ms / 2 tokens ( 2649.75 ms per token, 0.38 tokens per second) 48.11.064.254 I slot print_timing: id 3 | task 6691 | total time = 33873.49 ms / 800 tokens 48.11.064.254 I slot print_timing: id 3 | task 6691 | graphs reused = 5356 48.11.064.255 I slot print_timing: id 3 | task 6691 | graph reallocs = 0 / 0 (same size) / (changed size) 48.11.064.322 I slot release: id 3 | task 6691 | stop processing: n_tokens = 799, truncated = 0 48.11.064.333 I slot print_timing: id 0 | task 6694 | prompt processing, n_tokens = 1038, progress = 1.00, t = 27.11 s / 38.29 tokens per second 48.11.072.091 I slot print_timing: id 1 | task 6697 | prompt processing, n_tokens = 283, progress = 0.35, t = 17.99 s / 15.73 tokens per second 48.11.083.987 I slot print_timing: id 2 | task 6698 | prompt processing, n_tokens = 293, progress = 0.36, t = 17.99 s / 16.28 tokens per second 48.20.272.089 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 799, t_last = 89679880996 48.20.272.146 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 863.298 MiB) 48.20.375.060 I slot launch_slot_: id 3 | task 6703 | processing task, is_child = 0 48.20.375.081 I slot print_timing: id 1 | task 6697 | prompt processing, n_tokens = 679, progress = 0.85, t = 27.20 s / 24.96 tokens per second 48.20.379.563 I slot print_timing: id 2 | task 6698 | prompt processing, n_tokens = 679, progress = 0.84, t = 27.20 s / 24.96 tokens per second 48.25.318.349 I slot print_timing: id 0 | task 6694 | prompt eval time = 36315.59 ms / 1042 tokens ( 34.85 ms per token, 28.69 tokens per second) 48.25.318.356 I slot print_timing: id 0 | task 6694 | eval time = 5046.26 ms / 2 tokens ( 5046.26 ms per token, 0.20 tokens per second) 48.25.318.356 I slot print_timing: id 0 | task 6694 | total time = 41361.85 ms / 1044 tokens 48.25.318.357 I slot print_timing: id 0 | task 6694 | graphs reused = 5356 48.25.318.357 I slot print_timing: id 0 | task 6694 | graph reallocs = 0 / 0 (same size) / (changed size) 48.25.318.447 I slot release: id 0 | task 6694 | stop processing: n_tokens = 1043, truncated = 0 48.25.318.461 I slot print_timing: id 1 | task 6697 | prompt processing, n_tokens = 795, progress = 0.99, t = 32.25 s / 24.65 tokens per second 48.25.325.262 I slot print_timing: id 2 | task 6698 | prompt processing, n_tokens = 805, progress = 1.00, t = 32.25 s / 24.96 tokens per second 48.25.329.747 I slot print_timing: id 3 | task 6703 | prompt processing, n_tokens = 138, progress = 0.16, t = 4.93 s / 27.97 tokens per second 48.27.831.134 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1043, t_last = 89694135123 48.27.831.201 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 870.863 MiB) 48.27.924.021 I slot launch_slot_: id 0 | task 6706 | processing task, is_child = 0 48.27.924.105 I slot print_timing: id 3 | task 6703 | prompt processing, n_tokens = 319, progress = 0.38, t = 7.45 s / 42.84 tokens per second 48.30.207.145 I slot print_timing: id 1 | task 6697 | prompt eval time = 34761.69 ms / 799 tokens ( 43.51 ms per token, 22.99 tokens per second) 48.30.207.148 I slot print_timing: id 1 | task 6697 | eval time = 2376.24 ms / 2 tokens ( 2376.24 ms per token, 0.42 tokens per second) 48.30.207.148 I slot print_timing: id 1 | task 6697 | total time = 37137.93 ms / 801 tokens 48.30.207.148 I slot print_timing: id 1 | task 6697 | graphs reused = 5356 48.30.207.149 I slot print_timing: id 1 | task 6697 | graph reallocs = 0 / 0 (same size) / (changed size) 48.30.207.218 I slot release: id 1 | task 6697 | stop processing: n_tokens = 800, truncated = 0 48.30.207.469 I slot print_timing: id 2 | task 6698 | prompt eval time = 34761.87 ms / 809 tokens ( 42.97 ms per token, 23.27 tokens per second) 48.30.207.471 I slot print_timing: id 2 | task 6698 | eval time = 2376.34 ms / 2 tokens ( 2376.34 ms per token, 0.42 tokens per second) 48.30.207.472 I slot print_timing: id 2 | task 6698 | total time = 37138.21 ms / 811 tokens 48.30.207.472 I slot print_timing: id 2 | task 6698 | graphs reused = 5356 48.30.207.473 I slot print_timing: id 2 | task 6698 | graph reallocs = 0 / 0 (same size) / (changed size) 48.30.207.509 I slot release: id 2 | task 6698 | stop processing: n_tokens = 810, truncated = 0 48.30.213.925 I slot print_timing: id 3 | task 6703 | prompt processing, n_tokens = 329, progress = 0.39, t = 9.82 s / 33.49 tokens per second 48.32.404.400 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 800, t_last = 89699023892 48.37.083.079 I slot launch_slot_: id 1 | task 6709 | processing task, is_child = 0 48.37.083.130 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 876.240 MiB) 48.37.174.737 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 810, t_last = 89699024183 48.37.174.842 I slot launch_slot_: id 2 | task 6710 | processing task, is_child = 0 48.37.174.851 I slot print_timing: id 0 | task 6706 | prompt processing, n_tokens = 319, progress = 0.38, t = 4.48 s / 71.20 tokens per second 48.37.174.970 I slot print_timing: id 3 | task 6703 | prompt processing, n_tokens = 723, progress = 0.86, t = 12.02 s / 60.15 tokens per second 48.41.516.958 I slot print_timing: id 0 | task 6706 | prompt processing, n_tokens = 323, progress = 0.38, t = 13.59 s / 23.76 tokens per second 48.42.283.496 I slot print_timing: id 1 | task 6709 | prompt processing, n_tokens = 138, progress = 0.15, t = 4.34 s / 31.78 tokens per second 48.42.287.920 I slot print_timing: id 2 | task 6710 | prompt processing, n_tokens = 138, progress = 0.15, t = 4.34 s / 31.78 tokens per second 48.42.292.338 I slot print_timing: id 3 | task 6703 | prompt processing, n_tokens = 841, progress = 1.00, t = 21.13 s / 39.80 tokens per second 48.51.440.866 I slot print_timing: id 0 | task 6706 | prompt processing, n_tokens = 723, progress = 0.86, t = 23.52 s / 30.74 tokens per second 48.51.446.655 I slot print_timing: id 1 | task 6709 | prompt processing, n_tokens = 319, progress = 0.35, t = 14.27 s / 22.36 tokens per second 48.51.446.666 I slot print_timing: id 2 | task 6710 | prompt processing, n_tokens = 319, progress = 0.35, t = 14.27 s / 22.36 tokens per second 48.55.328.879 I slot print_timing: id 3 | task 6703 | prompt eval time = 31056.84 ms / 845 tokens ( 36.75 ms per token, 27.21 tokens per second) 48.55.328.882 I slot print_timing: id 3 | task 6703 | eval time = 3888.02 ms / 2 tokens ( 3888.02 ms per token, 0.26 tokens per second) 48.55.328.882 I slot print_timing: id 3 | task 6703 | total time = 34944.86 ms / 847 tokens 48.55.328.883 I slot print_timing: id 3 | task 6703 | graphs reused = 5356 48.55.328.883 I slot print_timing: id 3 | task 6703 | graph reallocs = 0 / 0 (same size) / (changed size) 48.55.328.959 I slot release: id 3 | task 6703 | stop processing: n_tokens = 846, truncated = 0 48.55.328.971 I slot print_timing: id 0 | task 6706 | prompt processing, n_tokens = 835, progress = 1.00, t = 27.40 s / 30.47 tokens per second 48.55.336.311 I slot print_timing: id 1 | task 6709 | prompt processing, n_tokens = 394, progress = 0.43, t = 18.15 s / 21.70 tokens per second 48.55.340.770 I slot print_timing: id 2 | task 6710 | prompt processing, n_tokens = 385, progress = 0.43, t = 18.15 s / 21.21 tokens per second 49.03.482.085 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.871 (> 0.100 thold), f_keep = 0.888 49.03.482.149 I slot launch_slot_: id 3 | task 6715 | processing task, is_child = 0 49.03.482.157 I slot print_timing: id 1 | task 6709 | prompt processing, n_tokens = 723, progress = 0.79, t = 26.31 s / 27.48 tokens per second 49.03.498.969 I slot print_timing: id 2 | task 6710 | prompt processing, n_tokens = 723, progress = 0.80, t = 26.31 s / 27.48 tokens per second 49.09.902.010 I slot print_timing: id 0 | task 6706 | prompt eval time = 35558.05 ms / 839 tokens ( 42.38 ms per token, 23.60 tokens per second) 49.09.902.013 I slot print_timing: id 0 | task 6706 | eval time = 6419.92 ms / 2 tokens ( 6419.92 ms per token, 0.16 tokens per second) 49.09.902.013 I slot print_timing: id 0 | task 6706 | total time = 41977.97 ms / 841 tokens 49.09.902.014 I slot print_timing: id 0 | task 6706 | graphs reused = 5356 49.09.902.014 I slot print_timing: id 0 | task 6706 | graph reallocs = 0 / 0 (same size) / (changed size) 49.09.902.051 I slot release: id 0 | task 6706 | stop processing: n_tokens = 840, truncated = 0 49.09.902.063 I slot print_timing: id 1 | task 6709 | prompt processing, n_tokens = 906, progress = 1.00, t = 32.73 s / 27.68 tokens per second 49.09.908.770 I slot print_timing: id 2 | task 6710 | prompt processing, n_tokens = 897, progress = 1.00, t = 32.73 s / 27.41 tokens per second 49.09.922.534 I slot print_timing: id 3 | task 6715 | prompt processing, n_tokens = 135, progress = 1.00, t = 6.39 s / 21.13 tokens per second 49.10.256.770 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 840, t_last = 89738718725 49.10.256.830 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 863.986 MiB) 49.10.372.032 I slot launch_slot_: id 0 | task 6718 | processing task, is_child = 0 49.12.054.129 I slot print_timing: id 1 | task 6709 | prompt eval time = 33081.40 ms / 910 tokens ( 36.35 ms per token, 27.51 tokens per second) 49.12.054.132 I slot print_timing: id 1 | task 6709 | eval time = 1797.86 ms / 2 tokens ( 1797.86 ms per token, 0.56 tokens per second) 49.12.054.132 I slot print_timing: id 1 | task 6709 | total time = 34879.26 ms / 912 tokens 49.12.054.133 I slot print_timing: id 1 | task 6709 | graphs reused = 5356 49.12.054.133 I slot print_timing: id 1 | task 6709 | graph reallocs = 0 / 0 (same size) / (changed size) 49.12.054.183 I slot release: id 1 | task 6709 | stop processing: n_tokens = 911, truncated = 0 49.12.054.409 I slot print_timing: id 2 | task 6710 | prompt eval time = 33081.50 ms / 901 tokens ( 36.72 ms per token, 27.24 tokens per second) 49.12.054.411 I slot print_timing: id 2 | task 6710 | eval time = 1797.99 ms / 2 tokens ( 1797.99 ms per token, 0.56 tokens per second) 49.12.054.411 I slot print_timing: id 2 | task 6710 | total time = 34879.49 ms / 903 tokens 49.12.054.412 I slot print_timing: id 2 | task 6710 | graphs reused = 5356 49.12.054.412 I slot print_timing: id 2 | task 6710 | graph reallocs = 0 / 0 (same size) / (changed size) 49.12.054.449 I slot release: id 2 | task 6710 | stop processing: n_tokens = 902, truncated = 0 49.12.054.734 I slot print_timing: id 3 | task 6715 | prompt eval time = 6743.40 ms / 139 tokens ( 48.51 ms per token, 20.61 tokens per second) 49.12.054.735 I slot print_timing: id 3 | task 6715 | eval time = 1797.97 ms / 2 tokens ( 1797.97 ms per token, 0.56 tokens per second) 49.12.054.736 I slot print_timing: id 3 | task 6715 | total time = 8541.37 ms / 141 tokens 49.12.054.736 I slot print_timing: id 3 | task 6715 | graphs reused = 5356 49.12.054.736 I slot print_timing: id 3 | task 6715 | graph reallocs = 0 / 0 (same size) / (changed size) 49.12.054.760 I slot release: id 3 | task 6715 | stop processing: n_tokens = 863, truncated = 0 49.12.066.279 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 911, t_last = 89740870857 49.12.066.333 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 859.547 MiB) 49.12.832.322 I slot launch_slot_: id 1 | task 6721 | processing task, is_child = 0 49.12.832.378 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 794.961 MiB) 49.12.864.944 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 795.773 MiB) 49.12.891.806 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 902, t_last = 89740871123 49.12.891.912 I slot launch_slot_: id 2 | task 6722 | processing task, is_child = 0 49.12.891.957 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 863, t_last = 89740871434 49.12.892.026 I slot launch_slot_: id 3 | task 6723 | processing task, is_child = 0 49.18.508.744 I slot print_timing: id 0 | task 6718 | prompt processing, n_tokens = 583, progress = 0.85, t = 8.14 s / 71.65 tokens per second 49.22.103.214 I slot print_timing: id 1 | task 6721 | prompt processing, n_tokens = 122, progress = 0.16, t = 5.61 s / 21.74 tokens per second 49.22.107.663 I slot print_timing: id 2 | task 6722 | prompt processing, n_tokens = 119, progress = 0.14, t = 5.61 s / 21.20 tokens per second 49.22.112.082 I slot print_timing: id 3 | task 6723 | prompt processing, n_tokens = 119, progress = 0.14, t = 5.61 s / 21.20 tokens per second 49.28.014.374 I slot print_timing: id 0 | task 6718 | prompt processing, n_tokens = 684, progress = 0.99, t = 17.64 s / 38.77 tokens per second 49.28.183.241 I slot print_timing: id 1 | task 6721 | prompt processing, n_tokens = 253, progress = 0.33, t = 15.12 s / 16.74 tokens per second 49.28.187.648 I slot print_timing: id 2 | task 6722 | prompt processing, n_tokens = 246, progress = 0.30, t = 15.12 s / 16.27 tokens per second 49.28.187.658 I slot print_timing: id 3 | task 6723 | prompt processing, n_tokens = 246, progress = 0.29, t = 15.12 s / 16.27 tokens per second 49.34.752.872 I slot print_timing: id 1 | task 6721 | prompt processing, n_tokens = 632, progress = 0.82, t = 21.86 s / 28.92 tokens per second 49.34.758.660 I slot print_timing: id 2 | task 6722 | prompt processing, n_tokens = 309, progress = 0.37, t = 21.86 s / 14.14 tokens per second 49.34.763.093 I slot print_timing: id 3 | task 6723 | prompt processing, n_tokens = 335, progress = 0.39, t = 21.86 s / 15.33 tokens per second 49.45.493.789 I slot print_timing: id 0 | task 6718 | prompt eval time = 24380.81 ms / 688 tokens ( 35.44 ms per token, 28.22 tokens per second) 49.45.493.792 I slot print_timing: id 0 | task 6718 | eval time = 10740.93 ms / 2 tokens (10740.93 ms per token, 0.09 tokens per second) 49.45.493.793 I slot print_timing: id 0 | task 6718 | total time = 35121.74 ms / 690 tokens 49.45.493.794 I slot print_timing: id 0 | task 6718 | graphs reused = 5356 49.45.493.794 I slot print_timing: id 0 | task 6718 | graph reallocs = 0 / 0 (same size) / (changed size) 49.45.493.859 I slot release: id 0 | task 6718 | stop processing: n_tokens = 689, truncated = 0 49.45.493.872 I slot print_timing: id 1 | task 6721 | prompt processing, n_tokens = 765, progress = 0.99, t = 32.60 s / 23.47 tokens per second 49.45.500.958 I slot print_timing: id 2 | task 6722 | prompt processing, n_tokens = 708, progress = 0.86, t = 32.60 s / 21.72 tokens per second 49.45.505.379 I slot print_timing: id 3 | task 6723 | prompt processing, n_tokens = 708, progress = 0.83, t = 32.60 s / 21.72 tokens per second 49.48.841.654 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 689, t_last = 89774310533 49.48.841.710 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 793.523 MiB) 49.48.868.782 I slot launch_slot_: id 0 | task 6729 | processing task, is_child = 0 49.48.868.852 I slot print_timing: id 2 | task 6722 | prompt processing, n_tokens = 821, progress = 1.00, t = 35.94 s / 22.84 tokens per second 49.48.873.561 I slot print_timing: id 3 | task 6723 | prompt processing, n_tokens = 847, progress = 1.00, t = 35.94 s / 23.56 tokens per second 49.50.736.250 I slot print_timing: id 1 | task 6721 | prompt eval time = 35945.21 ms / 769 tokens ( 46.74 ms per token, 21.39 tokens per second) 49.50.736.253 I slot print_timing: id 1 | task 6721 | eval time = 1894.60 ms / 2 tokens ( 1894.60 ms per token, 0.53 tokens per second) 49.50.736.254 I slot print_timing: id 1 | task 6721 | total time = 37839.81 ms / 771 tokens 49.50.736.255 I slot print_timing: id 1 | task 6721 | graphs reused = 5356 49.50.736.255 I slot print_timing: id 1 | task 6721 | graph reallocs = 0 / 0 (same size) / (changed size) 49.50.736.335 I slot release: id 1 | task 6721 | stop processing: n_tokens = 770, truncated = 0 49.52.390.889 I slot print_timing: id 2 | task 6722 | prompt eval time = 37840.01 ms / 825 tokens ( 45.87 ms per token, 21.80 tokens per second) 49.52.390.892 I slot print_timing: id 2 | task 6722 | eval time = 1654.36 ms / 2 tokens ( 1654.36 ms per token, 0.60 tokens per second) 49.52.390.893 I slot print_timing: id 2 | task 6722 | total time = 39494.38 ms / 827 tokens 49.52.390.894 I slot print_timing: id 2 | task 6722 | graphs reused = 5356 49.52.390.894 I slot print_timing: id 2 | task 6722 | graph reallocs = 0 / 0 (same size) / (changed size) 49.52.390.957 I slot release: id 2 | task 6722 | stop processing: n_tokens = 826, truncated = 0 49.52.391.191 I slot print_timing: id 3 | task 6723 | prompt eval time = 37840.13 ms / 851 tokens ( 44.47 ms per token, 22.49 tokens per second) 49.52.391.199 I slot print_timing: id 3 | task 6723 | eval time = 1654.49 ms / 2 tokens ( 1654.49 ms per token, 0.60 tokens per second) 49.52.391.199 I slot print_timing: id 3 | task 6723 | total time = 39494.62 ms / 853 tokens 49.52.391.200 I slot print_timing: id 3 | task 6723 | graphs reused = 5356 49.52.391.200 I slot print_timing: id 3 | task 6723 | graph reallocs = 0 / 0 (same size) / (changed size) 49.52.391.230 I slot release: id 3 | task 6723 | stop processing: n_tokens = 852, truncated = 0 49.52.391.235 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 770, t_last = 89779553010 49.52.391.291 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 794.398 MiB) 49.52.424.181 I slot launch_slot_: id 1 | task 6732 | processing task, is_child = 0 49.52.424.232 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 798.087 MiB) 49.52.448.846 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 813.342 MiB) 49.52.471.385 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 826, t_last = 89781207631 49.52.471.492 I slot launch_slot_: id 2 | task 6733 | processing task, is_child = 0 49.52.471.537 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 852, t_last = 89781207904 49.52.471.598 I slot launch_slot_: id 3 | task 6734 | processing task, is_child = 0 49.52.471.604 I slot print_timing: id 0 | task 6729 | prompt processing, n_tokens = 236, progress = 0.31, t = 3.52 s / 67.01 tokens per second 49.57.537.834 I slot print_timing: id 0 | task 6729 | prompt processing, n_tokens = 632, progress = 0.84, t = 8.67 s / 72.90 tokens per second 50.01.135.030 I slot print_timing: id 1 | task 6732 | prompt processing, n_tokens = 105, progress = 0.15, t = 5.06 s / 20.74 tokens per second 50.01.139.467 I slot print_timing: id 2 | task 6733 | prompt processing, n_tokens = 105, progress = 0.15, t = 5.06 s / 20.74 tokens per second 50.01.143.893 I slot print_timing: id 3 | task 6734 | prompt processing, n_tokens = 105, progress = 0.14, t = 5.06 s / 20.74 tokens per second 50.06.176.074 I slot print_timing: id 0 | task 6729 | prompt processing, n_tokens = 748, progress = 0.99, t = 17.31 s / 43.22 tokens per second 50.06.603.326 I slot print_timing: id 1 | task 6732 | prompt processing, n_tokens = 197, progress = 0.28, t = 13.70 s / 14.38 tokens per second 50.06.607.986 I slot print_timing: id 2 | task 6733 | prompt processing, n_tokens = 203, progress = 0.28, t = 13.70 s / 14.82 tokens per second 50.06.612.628 I slot print_timing: id 3 | task 6734 | prompt processing, n_tokens = 220, progress = 0.30, t = 13.70 s / 16.06 tokens per second 50.21.045.318 I slot print_timing: id 1 | task 6732 | prompt processing, n_tokens = 603, progress = 0.85, t = 28.57 s / 21.11 tokens per second 50.21.052.132 I slot print_timing: id 2 | task 6733 | prompt processing, n_tokens = 603, progress = 0.84, t = 28.57 s / 21.11 tokens per second 50.21.056.563 I slot print_timing: id 3 | task 6734 | prompt processing, n_tokens = 603, progress = 0.82, t = 28.57 s / 21.11 tokens per second 50.25.643.512 I slot print_timing: id 0 | task 6729 | prompt eval time = 32176.51 ms / 752 tokens ( 42.79 ms per token, 23.37 tokens per second) 50.25.643.515 I slot print_timing: id 0 | task 6729 | eval time = 4598.20 ms / 2 tokens ( 4598.20 ms per token, 0.22 tokens per second) 50.25.643.516 I slot print_timing: id 0 | task 6729 | total time = 36774.71 ms / 754 tokens 50.25.643.516 I slot print_timing: id 0 | task 6729 | graphs reused = 5356 50.25.643.517 I slot print_timing: id 0 | task 6729 | graph reallocs = 0 / 0 (same size) / (changed size) 50.25.643.575 I slot release: id 0 | task 6729 | stop processing: n_tokens = 753, truncated = 0 50.25.643.587 I slot print_timing: id 1 | task 6732 | prompt processing, n_tokens = 709, progress = 0.99, t = 33.17 s / 21.38 tokens per second 50.25.649.019 I slot print_timing: id 2 | task 6733 | prompt processing, n_tokens = 715, progress = 0.99, t = 33.17 s / 21.56 tokens per second 50.25.654.293 I slot print_timing: id 3 | task 6734 | prompt processing, n_tokens = 732, progress = 0.99, t = 33.17 s / 22.07 tokens per second 50.25.978.889 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 753, t_last = 89814460249 50.25.978.951 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 798.149 MiB) 50.26.000.146 I slot launch_slot_: id 0 | task 6740 | processing task, is_child = 0 50.27.652.712 I slot print_timing: id 1 | task 6732 | prompt eval time = 33502.47 ms / 713 tokens ( 46.99 ms per token, 21.28 tokens per second) 50.27.652.718 I slot print_timing: id 1 | task 6732 | eval time = 1674.18 ms / 2 tokens ( 1674.18 ms per token, 0.60 tokens per second) 50.27.652.719 I slot print_timing: id 1 | task 6732 | total time = 35176.65 ms / 715 tokens 50.27.652.719 I slot print_timing: id 1 | task 6732 | graphs reused = 5356 50.27.652.720 I slot print_timing: id 1 | task 6732 | graph reallocs = 0 / 0 (same size) / (changed size) 50.27.652.770 I slot release: id 1 | task 6732 | stop processing: n_tokens = 714, truncated = 0 50.27.652.999 I slot print_timing: id 2 | task 6733 | prompt eval time = 33502.55 ms / 719 tokens ( 46.60 ms per token, 21.46 tokens per second) 50.27.653.002 I slot print_timing: id 2 | task 6733 | eval time = 1674.32 ms / 2 tokens ( 1674.32 ms per token, 0.60 tokens per second) 50.27.653.002 I slot print_timing: id 2 | task 6733 | total time = 35176.87 ms / 721 tokens 50.27.653.003 I slot print_timing: id 2 | task 6733 | graphs reused = 5356 50.27.653.003 I slot print_timing: id 2 | task 6733 | graph reallocs = 0 / 0 (same size) / (changed size) 50.27.653.031 I slot release: id 2 | task 6733 | stop processing: n_tokens = 720, truncated = 0 50.27.653.264 I slot print_timing: id 3 | task 6734 | prompt eval time = 33502.70 ms / 736 tokens ( 45.52 ms per token, 21.97 tokens per second) 50.27.653.266 I slot print_timing: id 3 | task 6734 | eval time = 1674.38 ms / 2 tokens ( 1674.38 ms per token, 0.60 tokens per second) 50.27.653.267 I slot print_timing: id 3 | task 6734 | total time = 35177.08 ms / 738 tokens 50.27.653.267 I slot print_timing: id 3 | task 6734 | graphs reused = 5356 50.27.653.268 I slot print_timing: id 3 | task 6734 | graph reallocs = 0 / 0 (same size) / (changed size) 50.27.653.295 I slot release: id 3 | task 6734 | stop processing: n_tokens = 737, truncated = 0 50.27.664.839 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.890 (> 0.100 thold), f_keep = 0.884 50.27.664.870 I slot launch_slot_: id 1 | task 6743 | processing task, is_child = 0 50.27.664.914 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 798.775 MiB) 50.28.808.412 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 800.650 MiB) 50.28.839.231 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.893 (> 0.100 thold), f_keep = 0.876 50.28.839.302 I slot launch_slot_: id 2 | task 6744 | processing task, is_child = 0 50.28.839.346 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.883 (> 0.100 thold), f_keep = 0.856 50.28.839.369 I slot launch_slot_: id 3 | task 6745 | processing task, is_child = 0 50.37.414.140 I slot print_timing: id 0 | task 6740 | prompt processing, n_tokens = 603, progress = 0.85, t = 11.41 s / 52.83 tokens per second 50.37.590.613 I slot print_timing: id 1 | task 6743 | prompt processing, n_tokens = 102, progress = 0.99, t = 8.57 s / 11.91 tokens per second 50.37.595.164 I slot print_timing: id 2 | task 6744 | prompt processing, n_tokens = 100, progress = 0.99, t = 8.56 s / 11.68 tokens per second 50.37.603.953 I slot print_timing: id 3 | task 6745 | prompt processing, n_tokens = 108, progress = 0.99, t = 8.55 s / 12.63 tokens per second 50.39.413.944 I slot print_timing: id 0 | task 6740 | prompt processing, n_tokens = 706, progress = 0.99, t = 13.41 s / 52.63 tokens per second 50.39.784.463 I slot print_timing: id 1 | task 6743 | prompt eval time = 10565.41 ms / 106 tokens ( 99.67 ms per token, 10.03 tokens per second) 50.39.784.466 I slot print_timing: id 1 | task 6743 | eval time = 370.95 ms / 2 tokens ( 370.95 ms per token, 2.70 tokens per second) 50.39.784.467 I slot print_timing: id 1 | task 6743 | total time = 10936.36 ms / 108 tokens 50.39.784.467 I slot print_timing: id 1 | task 6743 | graphs reused = 5356 50.39.784.468 I slot print_timing: id 1 | task 6743 | graph reallocs = 0 / 0 (same size) / (changed size) 50.39.784.498 I slot release: id 1 | task 6743 | stop processing: n_tokens = 710, truncated = 0 50.39.784.684 I slot print_timing: id 2 | task 6744 | prompt eval time = 10558.06 ms / 104 tokens ( 101.52 ms per token, 9.85 tokens per second) 50.39.784.686 I slot print_timing: id 2 | task 6744 | eval time = 370.97 ms / 2 tokens ( 370.97 ms per token, 2.70 tokens per second) 50.39.784.687 I slot print_timing: id 2 | task 6744 | total time = 10929.03 ms / 106 tokens 50.39.784.687 I slot print_timing: id 2 | task 6744 | graphs reused = 5356 50.39.784.687 I slot print_timing: id 2 | task 6744 | graph reallocs = 0 / 0 (same size) / (changed size) 50.39.784.724 I slot release: id 2 | task 6744 | stop processing: n_tokens = 708, truncated = 0 50.39.784.961 I slot print_timing: id 3 | task 6745 | prompt eval time = 10550.69 ms / 112 tokens ( 94.20 ms per token, 10.62 tokens per second) 50.39.784.963 I slot print_timing: id 3 | task 6745 | eval time = 371.03 ms / 2 tokens ( 371.03 ms per token, 2.70 tokens per second) 50.39.784.964 I slot print_timing: id 3 | task 6745 | total time = 10921.72 ms / 114 tokens 50.39.784.964 I slot print_timing: id 3 | task 6745 | graphs reused = 5356 50.39.784.964 I slot print_timing: id 3 | task 6745 | graph reallocs = 0 / 0 (same size) / (changed size) 50.39.784.985 I slot release: id 3 | task 6745 | stop processing: n_tokens = 716, truncated = 0 50.39.885.847 I slot print_timing: id 0 | task 6740 | prompt eval time = 13784.17 ms / 710 tokens ( 19.41 ms per token, 51.51 tokens per second) 50.39.885.849 I slot print_timing: id 0 | task 6740 | eval time = 101.52 ms / 2 tokens ( 101.52 ms per token, 9.85 tokens per second) 50.39.885.849 I slot print_timing: id 0 | task 6740 | total time = 13885.69 ms / 712 tokens 50.39.885.850 I slot print_timing: id 0 | task 6740 | graphs reused = 5356 50.39.885.850 I slot print_timing: id 0 | task 6740 | graph reallocs = 0 / 0 (same size) / (changed size) 50.39.885.882 I slot release: id 0 | task 6740 | stop processing: n_tokens = 711, truncated = 0 50.39.885.890 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.840 (> 0.100 thold), f_keep = 0.887 50.39.885.916 I slot launch_slot_: id 0 | task 6750 | processing task, is_child = 0 50.39.885.961 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 805.089 MiB) 50.39.923.142 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 804.527 MiB) 50.39.941.111 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 802.088 MiB) 50.39.959.084 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.883 (> 0.100 thold), f_keep = 0.893 50.39.959.150 I slot launch_slot_: id 2 | task 6751 | processing task, is_child = 0 50.39.959.240 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.893 50.39.959.261 I slot launch_slot_: id 1 | task 6752 | processing task, is_child = 0 50.39.959.301 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.890 (> 0.100 thold), f_keep = 0.881 50.39.959.322 I slot launch_slot_: id 3 | task 6753 | processing task, is_child = 0 50.45.369.436 I slot print_timing: id 0 | task 6750 | prompt processing, n_tokens = 144, progress = 0.99, t = 5.41 s / 26.62 tokens per second 50.46.127.662 I slot print_timing: id 1 | task 6752 | prompt processing, n_tokens = 110, progress = 0.99, t = 5.40 s / 20.36 tokens per second 50.46.132.147 I slot print_timing: id 2 | task 6751 | prompt processing, n_tokens = 109, progress = 0.99, t = 5.40 s / 20.20 tokens per second 50.46.136.616 I slot print_timing: id 3 | task 6753 | prompt processing, n_tokens = 102, progress = 0.99, t = 5.39 s / 18.93 tokens per second 50.46.690.143 I slot print_timing: id 0 | task 6750 | prompt eval time = 6524.76 ms / 148 tokens ( 44.09 ms per token, 22.68 tokens per second) 50.46.690.145 I slot print_timing: id 0 | task 6750 | eval time = 206.06 ms / 2 tokens ( 206.06 ms per token, 4.85 tokens per second) 50.46.690.146 I slot print_timing: id 0 | task 6750 | total time = 6730.81 ms / 150 tokens 50.46.690.146 I slot print_timing: id 0 | task 6750 | graphs reused = 5356 50.46.690.147 I slot print_timing: id 0 | task 6750 | graph reallocs = 0 / 0 (same size) / (changed size) 50.46.690.187 I slot release: id 0 | task 6750 | stop processing: n_tokens = 752, truncated = 0 50.46.690.333 I slot print_timing: id 1 | task 6752 | prompt eval time = 6517.41 ms / 114 tokens ( 57.17 ms per token, 17.49 tokens per second) 50.46.690.335 I slot print_timing: id 1 | task 6752 | eval time = 206.07 ms / 2 tokens ( 206.07 ms per token, 4.85 tokens per second) 50.46.690.335 I slot print_timing: id 1 | task 6752 | total time = 6723.48 ms / 116 tokens 50.46.690.336 I slot print_timing: id 1 | task 6752 | graphs reused = 5356 50.46.690.336 I slot print_timing: id 1 | task 6752 | graph reallocs = 0 / 0 (same size) / (changed size) 50.46.690.375 I slot release: id 1 | task 6752 | stop processing: n_tokens = 718, truncated = 0 50.46.690.545 I slot print_timing: id 2 | task 6751 | prompt eval time = 6510.04 ms / 113 tokens ( 57.61 ms per token, 17.36 tokens per second) 50.46.690.550 I slot print_timing: id 2 | task 6751 | eval time = 206.11 ms / 2 tokens ( 206.11 ms per token, 4.85 tokens per second) 50.46.690.550 I slot print_timing: id 2 | task 6751 | total time = 6716.15 ms / 115 tokens 50.46.690.550 I slot print_timing: id 2 | task 6751 | graphs reused = 5356 50.46.690.551 I slot print_timing: id 2 | task 6751 | graph reallocs = 0 / 0 (same size) / (changed size) 50.46.690.578 I slot release: id 2 | task 6751 | stop processing: n_tokens = 717, truncated = 0 50.46.690.746 I slot print_timing: id 3 | task 6753 | prompt eval time = 6502.76 ms / 106 tokens ( 61.35 ms per token, 16.30 tokens per second) 50.46.690.749 I slot print_timing: id 3 | task 6753 | eval time = 206.12 ms / 2 tokens ( 206.12 ms per token, 4.85 tokens per second) 50.46.690.749 I slot print_timing: id 3 | task 6753 | total time = 6708.87 ms / 108 tokens 50.46.690.749 I slot print_timing: id 3 | task 6753 | graphs reused = 5356 50.46.690.750 I slot print_timing: id 3 | task 6753 | graph reallocs = 0 / 0 (same size) / (changed size) 50.46.690.776 I slot release: id 3 | task 6753 | stop processing: n_tokens = 710, truncated = 0 50.46.700.709 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 752, t_last = 89835506861 50.46.700.761 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 791.209 MiB) 50.46.720.704 I slot launch_slot_: id 0 | task 6758 | processing task, is_child = 0 50.46.720.754 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 796.274 MiB) 50.46.739.566 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 799.775 MiB) 50.46.757.860 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 801.401 MiB) 50.46.776.109 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 718, t_last = 89835507049 50.46.776.204 I slot launch_slot_: id 1 | task 6757 | processing task, is_child = 0 50.46.776.286 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 717, t_last = 89835507252 50.46.776.349 I slot launch_slot_: id 2 | task 6759 | processing task, is_child = 0 50.46.776.393 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 710, t_last = 89835507450 50.46.776.459 I slot launch_slot_: id 3 | task 6760 | processing task, is_child = 0 50.55.025.199 I slot print_timing: id 0 | task 6758 | prompt processing, n_tokens = 180, progress = 0.20, t = 8.25 s / 21.82 tokens per second 50.55.211.355 I slot print_timing: id 1 | task 6757 | prompt processing, n_tokens = 180, progress = 0.20, t = 8.25 s / 21.82 tokens per second 50.55.215.882 I slot print_timing: id 2 | task 6759 | prompt processing, n_tokens = 183, progress = 0.17, t = 8.25 s / 22.19 tokens per second 50.55.220.686 I slot print_timing: id 3 | task 6760 | prompt processing, n_tokens = 183, progress = 0.17, t = 8.25 s / 22.19 tokens per second 51.00.648.498 I slot print_timing: id 0 | task 6758 | prompt processing, n_tokens = 296, progress = 0.33, t = 13.87 s / 21.34 tokens per second 51.00.648.511 I slot print_timing: id 1 | task 6757 | prompt processing, n_tokens = 296, progress = 0.34, t = 13.87 s / 21.34 tokens per second 51.00.648.518 I slot print_timing: id 2 | task 6759 | prompt processing, n_tokens = 364, progress = 0.33, t = 13.87 s / 26.24 tokens per second 51.00.648.527 I slot print_timing: id 3 | task 6760 | prompt processing, n_tokens = 364, progress = 0.34, t = 13.87 s / 26.24 tokens per second 51.09.377.844 I slot print_timing: id 0 | task 6758 | prompt processing, n_tokens = 380, progress = 0.42, t = 22.60 s / 16.81 tokens per second 51.09.653.304 I slot print_timing: id 1 | task 6757 | prompt processing, n_tokens = 364, progress = 0.41, t = 22.60 s / 16.11 tokens per second 51.09.657.847 I slot print_timing: id 2 | task 6759 | prompt processing, n_tokens = 575, progress = 0.53, t = 22.60 s / 25.44 tokens per second 51.09.662.307 I slot print_timing: id 3 | task 6760 | prompt processing, n_tokens = 566, progress = 0.52, t = 22.60 s / 25.04 tokens per second 51.26.513.932 I slot print_timing: id 0 | task 6758 | prompt processing, n_tokens = 762, progress = 0.85, t = 39.74 s / 19.18 tokens per second 51.26.791.038 I slot print_timing: id 1 | task 6757 | prompt processing, n_tokens = 762, progress = 0.87, t = 39.74 s / 19.18 tokens per second 51.26.795.698 I slot print_timing: id 2 | task 6759 | prompt processing, n_tokens = 905, progress = 0.83, t = 39.74 s / 22.77 tokens per second 51.26.800.369 I slot print_timing: id 3 | task 6760 | prompt processing, n_tokens = 905, progress = 0.84, t = 39.74 s / 22.77 tokens per second 51.34.040.712 I slot print_timing: id 0 | task 6758 | prompt processing, n_tokens = 892, progress = 1.00, t = 47.26 s / 18.87 tokens per second 51.34.317.369 I slot print_timing: id 1 | task 6757 | prompt processing, n_tokens = 876, progress = 1.00, t = 47.26 s / 18.53 tokens per second 51.34.321.865 I slot print_timing: id 2 | task 6759 | prompt processing, n_tokens = 1087, progress = 1.00, t = 47.26 s / 23.00 tokens per second 51.34.326.409 I slot print_timing: id 3 | task 6760 | prompt processing, n_tokens = 1078, progress = 1.00, t = 47.26 s / 22.81 tokens per second 51.34.882.097 I slot print_timing: id 0 | task 6758 | prompt eval time = 47898.93 ms / 896 tokens ( 53.46 ms per token, 18.71 tokens per second) 51.34.882.101 I slot print_timing: id 0 | task 6758 | eval time = 206.69 ms / 2 tokens ( 206.69 ms per token, 4.84 tokens per second) 51.34.882.102 I slot print_timing: id 0 | task 6758 | total time = 48105.63 ms / 898 tokens 51.34.882.102 I slot print_timing: id 0 | task 6758 | graphs reused = 5356 51.34.882.103 I slot print_timing: id 0 | task 6758 | graph reallocs = 0 / 0 (same size) / (changed size) 51.34.882.160 I slot release: id 0 | task 6758 | stop processing: n_tokens = 897, truncated = 0 51.34.882.311 I slot print_timing: id 1 | task 6757 | prompt eval time = 47899.08 ms / 880 tokens ( 54.43 ms per token, 18.37 tokens per second) 51.34.882.314 I slot print_timing: id 1 | task 6757 | eval time = 206.71 ms / 2 tokens ( 206.71 ms per token, 4.84 tokens per second) 51.34.882.314 I slot print_timing: id 1 | task 6757 | total time = 48105.79 ms / 882 tokens 51.34.882.315 I slot print_timing: id 1 | task 6757 | graphs reused = 5356 51.34.882.315 I slot print_timing: id 1 | task 6757 | graph reallocs = 0 / 0 (same size) / (changed size) 51.34.882.337 I slot release: id 1 | task 6757 | stop processing: n_tokens = 881, truncated = 0 51.34.882.502 I slot print_timing: id 2 | task 6759 | prompt eval time = 47899.22 ms / 1091 tokens ( 43.90 ms per token, 22.78 tokens per second) 51.34.882.504 I slot print_timing: id 2 | task 6759 | eval time = 206.70 ms / 2 tokens ( 206.70 ms per token, 4.84 tokens per second) 51.34.882.504 I slot print_timing: id 2 | task 6759 | total time = 48105.92 ms / 1093 tokens 51.34.882.504 I slot print_timing: id 2 | task 6759 | graphs reused = 5356 51.34.882.505 I slot print_timing: id 2 | task 6759 | graph reallocs = 0 / 0 (same size) / (changed size) 51.34.882.546 I slot release: id 2 | task 6759 | stop processing: n_tokens = 1092, truncated = 0 51.34.882.706 I slot print_timing: id 3 | task 6760 | prompt eval time = 47899.37 ms / 1082 tokens ( 44.27 ms per token, 22.59 tokens per second) 51.34.882.707 I slot print_timing: id 3 | task 6760 | eval time = 206.70 ms / 2 tokens ( 206.70 ms per token, 4.84 tokens per second) 51.34.882.708 I slot print_timing: id 3 | task 6760 | total time = 48106.07 ms / 1084 tokens 51.34.882.708 I slot print_timing: id 3 | task 6760 | graphs reused = 5356 51.34.882.708 I slot print_timing: id 3 | task 6760 | graph reallocs = 0 / 0 (same size) / (changed size) 51.34.882.730 I slot release: id 3 | task 6760 | stop processing: n_tokens = 1083, truncated = 0 51.34.892.750 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.895 51.34.892.779 I slot launch_slot_: id 2 | task 6768 | processing task, is_child = 0 51.34.892.829 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 795.211 MiB) 51.34.925.922 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 793.148 MiB) 51.34.949.879 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 794.210 MiB) 51.34.984.035 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.901 51.34.984.092 I slot launch_slot_: id 3 | task 6769 | processing task, is_child = 0 51.34.984.188 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 897, t_last = 89883698834 51.34.988.984 I slot launch_slot_: id 0 | task 6770 | processing task, is_child = 0 51.34.989.037 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 881, t_last = 89883699011 51.34.989.103 I slot launch_slot_: id 1 | task 6771 | processing task, is_child = 0 51.43.434.299 I slot print_timing: id 0 | task 6770 | prompt processing, n_tokens = 170, progress = 1.00, t = 8.45 s / 20.13 tokens per second 51.43.605.299 I slot print_timing: id 1 | task 6771 | prompt processing, n_tokens = 183, progress = 0.17, t = 8.44 s / 21.69 tokens per second 51.43.610.276 I slot print_timing: id 2 | task 6768 | prompt processing, n_tokens = 171, progress = 1.00, t = 8.44 s / 20.27 tokens per second 51.43.615.498 I slot print_timing: id 3 | task 6769 | prompt processing, n_tokens = 176, progress = 1.00, t = 8.43 s / 20.88 tokens per second 51.46.143.902 I slot print_timing: id 1 | task 6771 | prompt processing, n_tokens = 364, progress = 0.34, t = 11.15 s / 32.66 tokens per second 51.48.692.258 I slot print_timing: id 0 | task 6770 | prompt eval time = 11154.33 ms / 174 tokens ( 64.11 ms per token, 15.60 tokens per second) 51.48.692.261 I slot print_timing: id 0 | task 6770 | eval time = 2548.82 ms / 2 tokens ( 2548.82 ms per token, 0.39 tokens per second) 51.48.692.261 I slot print_timing: id 0 | task 6770 | total time = 13703.14 ms / 176 tokens 51.48.692.262 I slot print_timing: id 0 | task 6770 | graphs reused = 5356 51.48.692.262 I slot print_timing: id 0 | task 6770 | graph reallocs = 0 / 0 (same size) / (changed size) 51.48.692.304 I slot release: id 0 | task 6770 | stop processing: n_tokens = 1080, truncated = 0 51.48.692.494 I slot print_timing: id 2 | task 6768 | prompt eval time = 11146.97 ms / 175 tokens ( 63.70 ms per token, 15.70 tokens per second) 51.48.692.498 I slot print_timing: id 2 | task 6768 | eval time = 2548.83 ms / 2 tokens ( 2548.83 ms per token, 0.39 tokens per second) 51.48.692.498 I slot print_timing: id 2 | task 6768 | total time = 13695.80 ms / 177 tokens 51.48.692.498 I slot print_timing: id 2 | task 6768 | graphs reused = 5356 51.48.692.499 I slot print_timing: id 2 | task 6768 | graph reallocs = 0 / 0 (same size) / (changed size) 51.48.692.530 I slot release: id 2 | task 6768 | stop processing: n_tokens = 1081, truncated = 0 51.48.692.762 I slot print_timing: id 3 | task 6769 | prompt eval time = 11139.73 ms / 180 tokens ( 61.89 ms per token, 16.16 tokens per second) 51.48.692.764 I slot print_timing: id 3 | task 6769 | eval time = 2548.87 ms / 2 tokens ( 2548.87 ms per token, 0.39 tokens per second) 51.48.692.764 I slot print_timing: id 3 | task 6769 | total time = 13688.60 ms / 182 tokens 51.48.692.764 I slot print_timing: id 3 | task 6769 | graphs reused = 5356 51.48.692.765 I slot print_timing: id 3 | task 6769 | graph reallocs = 0 / 0 (same size) / (changed size) 51.48.692.792 I slot release: id 3 | task 6769 | stop processing: n_tokens = 1086, truncated = 0 51.48.692.801 I slot print_timing: id 1 | task 6771 | prompt processing, n_tokens = 555, progress = 0.52, t = 13.70 s / 40.52 tokens per second 51.48.704.193 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.911 (> 0.100 thold), f_keep = 0.905 51.48.704.232 I slot launch_slot_: id 0 | task 6776 | processing task, is_child = 0 51.52.708.107 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 792.522 MiB) 51.52.730.236 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.904 51.52.730.317 I slot launch_slot_: id 2 | task 6777 | processing task, is_child = 0 51.52.730.373 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.898 (> 0.100 thold), f_keep = 0.900 51.52.730.396 I slot launch_slot_: id 3 | task 6778 | processing task, is_child = 0 51.52.738.430 I slot print_timing: id 1 | task 6771 | prompt processing, n_tokens = 905, progress = 0.85, t = 13.71 s / 66.02 tokens per second 52.01.007.730 I slot print_timing: id 0 | task 6776 | prompt processing, n_tokens = 164, progress = 1.00, t = 8.28 s / 19.81 tokens per second 52.01.181.351 I slot print_timing: id 1 | task 6771 | prompt processing, n_tokens = 1067, progress = 1.00, t = 26.01 s / 41.02 tokens per second 52.01.185.891 I slot print_timing: id 2 | task 6777 | prompt processing, n_tokens = 173, progress = 1.00, t = 8.26 s / 20.93 tokens per second 52.01.190.406 I slot print_timing: id 3 | task 6778 | prompt processing, n_tokens = 179, progress = 1.00, t = 8.26 s / 21.68 tokens per second 52.01.746.213 I slot print_timing: id 0 | task 6776 | prompt eval time = 8809.12 ms / 168 tokens ( 52.44 ms per token, 19.07 tokens per second) 52.01.746.215 I slot print_timing: id 0 | task 6776 | eval time = 206.68 ms / 2 tokens ( 206.68 ms per token, 4.84 tokens per second) 52.01.746.216 I slot print_timing: id 0 | task 6776 | total time = 9015.81 ms / 170 tokens 52.01.746.217 I slot print_timing: id 0 | task 6776 | graphs reused = 5356 52.01.746.217 I slot print_timing: id 0 | task 6776 | graph reallocs = 0 / 0 (same size) / (changed size) 52.01.746.263 I slot release: id 0 | task 6776 | stop processing: n_tokens = 1074, truncated = 0 52.01.746.411 I slot print_timing: id 1 | task 6771 | prompt eval time = 26543.05 ms / 1071 tokens ( 24.78 ms per token, 40.35 tokens per second) 52.01.746.413 I slot print_timing: id 1 | task 6771 | eval time = 206.73 ms / 2 tokens ( 206.73 ms per token, 4.84 tokens per second) 52.01.746.413 I slot print_timing: id 1 | task 6771 | total time = 26749.77 ms / 1073 tokens 52.01.746.418 I slot print_timing: id 1 | task 6771 | graphs reused = 5356 52.01.746.418 I slot print_timing: id 1 | task 6771 | graph reallocs = 0 / 0 (same size) / (changed size) 52.01.746.443 I slot release: id 1 | task 6771 | stop processing: n_tokens = 1072, truncated = 0 52.01.746.610 I slot print_timing: id 2 | task 6777 | prompt eval time = 8796.91 ms / 177 tokens ( 49.70 ms per token, 20.12 tokens per second) 52.01.746.612 I slot print_timing: id 2 | task 6777 | eval time = 206.77 ms / 2 tokens ( 206.77 ms per token, 4.84 tokens per second) 52.01.746.612 I slot print_timing: id 2 | task 6777 | total time = 9003.68 ms / 179 tokens 52.01.746.613 I slot print_timing: id 2 | task 6777 | graphs reused = 5356 52.01.746.613 I slot print_timing: id 2 | task 6777 | graph reallocs = 0 / 0 (same size) / (changed size) 52.01.746.636 I slot release: id 2 | task 6777 | stop processing: n_tokens = 1083, truncated = 0 52.01.746.820 I slot print_timing: id 3 | task 6778 | prompt eval time = 8789.39 ms / 183 tokens ( 48.03 ms per token, 20.82 tokens per second) 52.01.746.822 I slot print_timing: id 3 | task 6778 | eval time = 206.77 ms / 2 tokens ( 206.77 ms per token, 4.84 tokens per second) 52.01.746.822 I slot print_timing: id 3 | task 6778 | total time = 8996.17 ms / 185 tokens 52.01.746.823 I slot print_timing: id 3 | task 6778 | graphs reused = 5356 52.01.746.823 I slot print_timing: id 3 | task 6778 | graph reallocs = 0 / 0 (same size) / (changed size) 52.01.746.844 I slot release: id 3 | task 6778 | stop processing: n_tokens = 1089, truncated = 0 52.01.756.035 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.910 52.01.756.063 I slot launch_slot_: id 0 | task 6782 | processing task, is_child = 0 52.01.756.120 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 792.397 MiB) 52.01.777.564 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 792.897 MiB) 52.01.799.649 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 795.148 MiB) 52.01.822.724 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.902 (> 0.100 thold), f_keep = 0.911 52.01.822.771 I slot launch_slot_: id 1 | task 6783 | processing task, is_child = 0 52.01.822.893 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.909 (> 0.100 thold), f_keep = 0.902 52.01.822.914 I slot launch_slot_: id 2 | task 6784 | processing task, is_child = 0 52.01.822.970 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.897 52.01.822.989 I slot launch_slot_: id 3 | task 6785 | processing task, is_child = 0 52.09.877.075 I slot print_timing: id 0 | task 6782 | prompt processing, n_tokens = 167, progress = 1.00, t = 8.05 s / 20.73 tokens per second 52.10.048.182 I slot print_timing: id 1 | task 6783 | prompt processing, n_tokens = 174, progress = 1.00, t = 8.05 s / 21.63 tokens per second 52.10.053.239 I slot print_timing: id 2 | task 6784 | prompt processing, n_tokens = 166, progress = 1.00, t = 8.04 s / 20.65 tokens per second 52.10.058.320 I slot print_timing: id 3 | task 6785 | prompt processing, n_tokens = 171, progress = 1.00, t = 8.03 s / 21.30 tokens per second 52.10.614.887 I slot print_timing: id 0 | task 6782 | prompt eval time = 8585.36 ms / 171 tokens ( 50.21 ms per token, 19.92 tokens per second) 52.10.614.893 I slot print_timing: id 0 | task 6782 | eval time = 206.53 ms / 2 tokens ( 206.53 ms per token, 4.84 tokens per second) 52.10.614.893 I slot print_timing: id 0 | task 6782 | total time = 8791.89 ms / 173 tokens 52.10.614.894 I slot print_timing: id 0 | task 6782 | graphs reused = 5356 52.10.614.894 I slot print_timing: id 0 | task 6782 | graph reallocs = 0 / 0 (same size) / (changed size) 52.10.614.947 I slot release: id 0 | task 6782 | stop processing: n_tokens = 1077, truncated = 0 52.10.615.096 I slot print_timing: id 1 | task 6783 | prompt eval time = 8577.44 ms / 178 tokens ( 48.19 ms per token, 20.75 tokens per second) 52.10.615.098 I slot print_timing: id 1 | task 6783 | eval time = 206.55 ms / 2 tokens ( 206.55 ms per token, 4.84 tokens per second) 52.10.615.098 I slot print_timing: id 1 | task 6783 | total time = 8784.00 ms / 180 tokens 52.10.615.098 I slot print_timing: id 1 | task 6783 | graphs reused = 5356 52.10.615.099 I slot print_timing: id 1 | task 6783 | graph reallocs = 0 / 0 (same size) / (changed size) 52.10.615.126 I slot release: id 1 | task 6783 | stop processing: n_tokens = 1084, truncated = 0 52.10.615.301 I slot print_timing: id 2 | task 6784 | prompt eval time = 8569.51 ms / 170 tokens ( 50.41 ms per token, 19.84 tokens per second) 52.10.615.302 I slot print_timing: id 2 | task 6784 | eval time = 206.56 ms / 2 tokens ( 206.56 ms per token, 4.84 tokens per second) 52.10.615.302 I slot print_timing: id 2 | task 6784 | total time = 8776.07 ms / 172 tokens 52.10.615.303 I slot print_timing: id 2 | task 6784 | graphs reused = 5356 52.10.615.303 I slot print_timing: id 2 | task 6784 | graph reallocs = 0 / 0 (same size) / (changed size) 52.10.615.331 I slot release: id 2 | task 6784 | stop processing: n_tokens = 1076, truncated = 0 52.10.615.503 I slot print_timing: id 3 | task 6785 | prompt eval time = 8561.87 ms / 175 tokens ( 48.92 ms per token, 20.44 tokens per second) 52.10.615.505 I slot print_timing: id 3 | task 6785 | eval time = 206.55 ms / 2 tokens ( 206.55 ms per token, 4.84 tokens per second) 52.10.615.506 I slot print_timing: id 3 | task 6785 | total time = 8768.42 ms / 177 tokens 52.10.615.506 I slot print_timing: id 3 | task 6785 | graphs reused = 5356 52.10.615.507 I slot print_timing: id 3 | task 6785 | graph reallocs = 0 / 0 (same size) / (changed size) 52.10.615.534 I slot release: id 3 | task 6785 | stop processing: n_tokens = 1081, truncated = 0 52.10.625.830 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1077, t_last = 89919431622 52.10.625.892 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 793.022 MiB) 52.10.648.806 I slot launch_slot_: id 0 | task 6789 | processing task, is_child = 0 52.10.648.867 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 792.960 MiB) 52.10.670.759 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 792.522 MiB) 52.10.690.137 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 804.214 MiB) 52.10.723.005 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.901 52.10.723.061 I slot launch_slot_: id 1 | task 6791 | processing task, is_child = 0 52.10.723.171 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.908 52.10.723.191 I slot launch_slot_: id 2 | task 6790 | processing task, is_child = 0 52.10.723.242 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1081, t_last = 89919432208 52.10.723.314 I slot launch_slot_: id 3 | task 6792 | processing task, is_child = 0 52.19.613.515 I slot print_timing: id 0 | task 6789 | prompt processing, n_tokens = 210, progress = 0.20, t = 8.89 s / 23.62 tokens per second 52.20.374.233 I slot print_timing: id 1 | task 6791 | prompt processing, n_tokens = 169, progress = 1.00, t = 8.89 s / 19.01 tokens per second 52.20.379.380 I slot print_timing: id 2 | task 6790 | prompt processing, n_tokens = 170, progress = 1.00, t = 8.88 s / 19.14 tokens per second 52.20.384.111 I slot print_timing: id 3 | task 6792 | prompt processing, n_tokens = 210, progress = 0.21, t = 8.87 s / 23.66 tokens per second 52.25.093.072 I slot print_timing: id 0 | task 6789 | prompt processing, n_tokens = 393, progress = 0.38, t = 14.37 s / 27.35 tokens per second 52.25.093.088 I slot print_timing: id 3 | task 6792 | prompt processing, n_tokens = 393, progress = 0.39, t = 14.35 s / 27.38 tokens per second 52.28.231.112 I slot print_timing: id 1 | task 6791 | prompt eval time = 14369.42 ms / 173 tokens ( 83.06 ms per token, 12.04 tokens per second) 52.28.231.114 I slot print_timing: id 1 | task 6791 | eval time = 3138.28 ms / 2 tokens ( 3138.28 ms per token, 0.32 tokens per second) 52.28.231.115 I slot print_timing: id 1 | task 6791 | total time = 17507.70 ms / 175 tokens 52.28.231.115 I slot print_timing: id 1 | task 6791 | graphs reused = 5356 52.28.231.116 I slot print_timing: id 1 | task 6791 | graph reallocs = 0 / 0 (same size) / (changed size) 52.28.231.156 I slot release: id 1 | task 6791 | stop processing: n_tokens = 1079, truncated = 0 52.28.231.385 I slot print_timing: id 2 | task 6790 | prompt eval time = 14362.04 ms / 174 tokens ( 82.54 ms per token, 12.12 tokens per second) 52.28.231.387 I slot print_timing: id 2 | task 6790 | eval time = 3138.32 ms / 2 tokens ( 3138.32 ms per token, 0.32 tokens per second) 52.28.231.388 I slot print_timing: id 2 | task 6790 | total time = 17500.36 ms / 176 tokens 52.28.231.388 I slot print_timing: id 2 | task 6790 | graphs reused = 5356 52.28.231.388 I slot print_timing: id 2 | task 6790 | graph reallocs = 0 / 0 (same size) / (changed size) 52.28.231.414 I slot release: id 2 | task 6790 | stop processing: n_tokens = 1080, truncated = 0 52.28.231.423 I slot print_timing: id 0 | task 6789 | prompt processing, n_tokens = 515, progress = 0.50, t = 17.51 s / 29.42 tokens per second 52.28.237.822 I slot print_timing: id 3 | task 6792 | prompt processing, n_tokens = 501, progress = 0.49, t = 17.49 s / 28.64 tokens per second 52.32.556.765 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1079, t_last = 89937047830 52.32.556.843 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 803.214 MiB) 52.36.881.515 I slot launch_slot_: id 1 | task 6797 | processing task, is_child = 0 52.36.881.583 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 815.718 MiB) 52.36.902.704 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1080, t_last = 89937048088 52.36.902.817 I slot launch_slot_: id 2 | task 6798 | processing task, is_child = 0 52.36.902.827 I slot print_timing: id 0 | task 6789 | prompt processing, n_tokens = 878, progress = 0.85, t = 21.83 s / 40.21 tokens per second 52.36.907.813 I slot print_timing: id 3 | task 6792 | prompt processing, n_tokens = 878, progress = 0.86, t = 21.82 s / 40.24 tokens per second 52.43.857.084 I slot print_timing: id 0 | task 6789 | prompt processing, n_tokens = 1027, progress = 1.00, t = 33.13 s / 31.00 tokens per second 52.45.337.352 I slot print_timing: id 1 | task 6797 | prompt processing, n_tokens = 210, progress = 0.20, t = 6.95 s / 30.22 tokens per second 52.45.341.773 I slot print_timing: id 2 | task 6798 | prompt processing, n_tokens = 210, progress = 0.19, t = 6.95 s / 30.22 tokens per second 52.45.346.172 I slot print_timing: id 3 | task 6792 | prompt processing, n_tokens = 1013, progress = 1.00, t = 33.12 s / 30.59 tokens per second 52.49.982.443 I slot print_timing: id 1 | task 6797 | prompt processing, n_tokens = 393, progress = 0.37, t = 13.07 s / 30.06 tokens per second 52.49.982.456 I slot print_timing: id 2 | task 6798 | prompt processing, n_tokens = 393, progress = 0.36, t = 13.07 s / 30.06 tokens per second 52.55.011.437 I slot print_timing: id 0 | task 6789 | prompt eval time = 39258.89 ms / 1031 tokens ( 38.08 ms per token, 26.26 tokens per second) 52.55.011.440 I slot print_timing: id 0 | task 6789 | eval time = 5029.22 ms / 2 tokens ( 5029.22 ms per token, 0.20 tokens per second) 52.55.011.441 I slot print_timing: id 0 | task 6789 | total time = 44288.11 ms / 1033 tokens 52.55.011.441 I slot print_timing: id 0 | task 6789 | graphs reused = 5356 52.55.011.442 I slot print_timing: id 0 | task 6789 | graph reallocs = 0 / 0 (same size) / (changed size) 52.55.011.500 I slot release: id 0 | task 6789 | stop processing: n_tokens = 1032, truncated = 0 52.55.011.689 I slot print_timing: id 3 | task 6792 | prompt eval time = 39243.89 ms / 1017 tokens ( 38.59 ms per token, 25.91 tokens per second) 52.55.011.693 I slot print_timing: id 3 | task 6792 | eval time = 5029.26 ms / 2 tokens ( 5029.26 ms per token, 0.20 tokens per second) 52.55.011.694 I slot print_timing: id 3 | task 6792 | total time = 44273.15 ms / 1019 tokens 52.55.011.694 I slot print_timing: id 3 | task 6792 | graphs reused = 5356 52.55.011.694 I slot print_timing: id 3 | task 6792 | graph reallocs = 0 / 0 (same size) / (changed size) 52.55.011.725 I slot release: id 3 | task 6792 | stop processing: n_tokens = 1018, truncated = 0 52.55.011.734 I slot print_timing: id 1 | task 6797 | prompt processing, n_tokens = 555, progress = 0.52, t = 18.10 s / 30.66 tokens per second 52.55.017.923 I slot print_timing: id 2 | task 6798 | prompt processing, n_tokens = 590, progress = 0.53, t = 18.10 s / 32.59 tokens per second 53.01.510.188 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.880 (> 0.100 thold), f_keep = 0.878 53.01.510.262 I slot launch_slot_: id 0 | task 6803 | processing task, is_child = 0 53.01.510.320 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 816.031 MiB) 53.02.270.574 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.867 (> 0.100 thold), f_keep = 0.890 53.02.270.642 I slot launch_slot_: id 3 | task 6804 | processing task, is_child = 0 53.02.278.212 I slot print_timing: id 1 | task 6797 | prompt processing, n_tokens = 878, progress = 0.82, t = 24.60 s / 35.69 tokens per second 53.02.282.624 I slot print_timing: id 2 | task 6798 | prompt processing, n_tokens = 878, progress = 0.79, t = 24.60 s / 35.69 tokens per second 53.10.783.606 I slot print_timing: id 0 | task 6803 | prompt processing, n_tokens = 148, progress = 1.00, t = 8.51 s / 17.39 tokens per second 53.11.546.575 I slot print_timing: id 1 | task 6797 | prompt processing, n_tokens = 1067, progress = 1.00, t = 33.88 s / 31.50 tokens per second 53.11.551.102 I slot print_timing: id 2 | task 6798 | prompt processing, n_tokens = 1102, progress = 1.00, t = 33.88 s / 32.53 tokens per second 53.11.555.603 I slot print_timing: id 3 | task 6804 | prompt processing, n_tokens = 163, progress = 1.00, t = 8.50 s / 19.18 tokens per second 53.12.111.497 I slot print_timing: id 0 | task 6803 | prompt eval time = 9634.14 ms / 152 tokens ( 63.38 ms per token, 15.78 tokens per second) 53.12.111.499 I slot print_timing: id 0 | task 6803 | eval time = 206.70 ms / 2 tokens ( 206.70 ms per token, 4.84 tokens per second) 53.12.111.500 I slot print_timing: id 0 | task 6803 | total time = 9840.84 ms / 154 tokens 53.12.111.500 I slot print_timing: id 0 | task 6803 | graphs reused = 5356 53.12.111.500 I slot print_timing: id 0 | task 6803 | graph reallocs = 0 / 0 (same size) / (changed size) 53.12.111.562 I slot release: id 0 | task 6803 | stop processing: n_tokens = 1031, truncated = 0 53.12.111.714 I slot print_timing: id 1 | task 6797 | prompt eval time = 34997.35 ms / 1071 tokens ( 32.68 ms per token, 30.60 tokens per second) 53.12.111.717 I slot print_timing: id 1 | task 6797 | eval time = 206.74 ms / 2 tokens ( 206.74 ms per token, 4.84 tokens per second) 53.12.111.718 I slot print_timing: id 1 | task 6797 | total time = 35204.09 ms / 1073 tokens 53.12.111.718 I slot print_timing: id 1 | task 6797 | graphs reused = 5356 53.12.111.718 I slot print_timing: id 1 | task 6797 | graph reallocs = 0 / 0 (same size) / (changed size) 53.12.111.749 I slot release: id 1 | task 6797 | stop processing: n_tokens = 1072, truncated = 0 53.12.111.918 I slot print_timing: id 2 | task 6798 | prompt eval time = 34997.47 ms / 1106 tokens ( 31.64 ms per token, 31.60 tokens per second) 53.12.111.920 I slot print_timing: id 2 | task 6798 | eval time = 206.73 ms / 2 tokens ( 206.73 ms per token, 4.84 tokens per second) 53.12.111.920 I slot print_timing: id 2 | task 6798 | total time = 35204.20 ms / 1108 tokens 53.12.111.920 I slot print_timing: id 2 | task 6798 | graphs reused = 5356 53.12.111.921 I slot print_timing: id 2 | task 6798 | graph reallocs = 0 / 0 (same size) / (changed size) 53.12.111.954 I slot release: id 2 | task 6798 | stop processing: n_tokens = 1107, truncated = 0 53.12.112.116 I slot print_timing: id 3 | task 6804 | prompt eval time = 9618.30 ms / 167 tokens ( 57.59 ms per token, 17.36 tokens per second) 53.12.112.118 I slot print_timing: id 3 | task 6804 | eval time = 206.73 ms / 2 tokens ( 206.73 ms per token, 4.84 tokens per second) 53.12.112.119 I slot print_timing: id 3 | task 6804 | total time = 9825.03 ms / 169 tokens 53.12.112.119 I slot print_timing: id 3 | task 6804 | graphs reused = 5356 53.12.112.119 I slot print_timing: id 3 | task 6804 | graph reallocs = 0 / 0 (same size) / (changed size) 53.12.112.141 I slot release: id 3 | task 6804 | stop processing: n_tokens = 1046, truncated = 0 53.12.120.851 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1031, t_last = 89980928237 53.12.120.912 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 815.156 MiB) 53.12.140.351 I slot launch_slot_: id 0 | task 6808 | processing task, is_child = 0 53.12.140.410 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 815.843 MiB) 53.12.159.256 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 816.218 MiB) 53.12.179.063 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 815.468 MiB) 53.12.197.792 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1072, t_last = 89980928423 53.12.197.896 I slot launch_slot_: id 1 | task 6809 | processing task, is_child = 0 53.12.197.995 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1107, t_last = 89980928628 53.12.198.071 I slot launch_slot_: id 2 | task 6810 | processing task, is_child = 0 53.12.198.126 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1046, t_last = 89980928816 53.12.198.200 I slot launch_slot_: id 3 | task 6811 | processing task, is_child = 0 53.17.891.039 I slot print_timing: id 0 | task 6808 | prompt processing, n_tokens = 136, progress = 0.19, t = 5.69 s / 23.89 tokens per second 53.18.348.399 I slot print_timing: id 1 | task 6809 | prompt processing, n_tokens = 136, progress = 0.18, t = 5.69 s / 23.89 tokens per second 53.18.352.945 I slot print_timing: id 2 | task 6810 | prompt processing, n_tokens = 136, progress = 0.18, t = 5.69 s / 23.89 tokens per second 53.18.357.752 I slot print_timing: id 3 | task 6811 | prompt processing, n_tokens = 136, progress = 0.17, t = 5.69 s / 23.89 tokens per second 53.23.214.479 I slot print_timing: id 0 | task 6808 | prompt processing, n_tokens = 213, progress = 0.29, t = 11.02 s / 19.34 tokens per second 53.23.641.979 I slot print_timing: id 1 | task 6809 | prompt processing, n_tokens = 224, progress = 0.30, t = 11.02 s / 20.33 tokens per second 53.23.646.401 I slot print_timing: id 2 | task 6810 | prompt processing, n_tokens = 237, progress = 0.31, t = 11.02 s / 21.51 tokens per second 53.23.650.842 I slot print_timing: id 3 | task 6811 | prompt processing, n_tokens = 259, progress = 0.32, t = 11.02 s / 23.51 tokens per second 53.38.041.643 I slot print_timing: id 0 | task 6808 | prompt processing, n_tokens = 623, progress = 0.85, t = 25.84 s / 24.11 tokens per second 53.38.319.876 I slot print_timing: id 1 | task 6809 | prompt processing, n_tokens = 623, progress = 0.84, t = 25.84 s / 24.11 tokens per second 53.38.324.297 I slot print_timing: id 2 | task 6810 | prompt processing, n_tokens = 623, progress = 0.83, t = 25.84 s / 24.11 tokens per second 53.38.328.751 I slot print_timing: id 3 | task 6811 | prompt processing, n_tokens = 281, progress = 0.35, t = 25.84 s / 10.87 tokens per second 53.44.310.165 I slot print_timing: id 0 | task 6808 | prompt processing, n_tokens = 725, progress = 0.99, t = 32.11 s / 22.58 tokens per second 53.46.872.285 I slot print_timing: id 1 | task 6809 | prompt processing, n_tokens = 736, progress = 0.99, t = 32.11 s / 22.92 tokens per second 53.46.876.857 I slot print_timing: id 2 | task 6810 | prompt processing, n_tokens = 749, progress = 0.99, t = 32.11 s / 23.32 tokens per second 53.46.881.351 I slot print_timing: id 3 | task 6811 | prompt processing, n_tokens = 623, progress = 0.78, t = 32.11 s / 19.40 tokens per second 53.49.408.840 I slot print_timing: id 3 | task 6811 | prompt processing, n_tokens = 793, progress = 0.99, t = 37.21 s / 21.31 tokens per second 53.49.791.494 I slot print_timing: id 0 | task 6808 | prompt eval time = 37210.20 ms / 729 tokens ( 51.04 ms per token, 19.59 tokens per second) 53.49.791.496 I slot print_timing: id 0 | task 6808 | eval time = 383.08 ms / 2 tokens ( 383.08 ms per token, 2.61 tokens per second) 53.49.791.496 I slot print_timing: id 0 | task 6808 | total time = 37593.28 ms / 731 tokens 53.49.791.497 I slot print_timing: id 0 | task 6808 | graphs reused = 5356 53.49.791.497 I slot print_timing: id 0 | task 6808 | graph reallocs = 0 / 0 (same size) / (changed size) 53.49.791.550 I slot release: id 0 | task 6808 | stop processing: n_tokens = 730, truncated = 0 53.49.791.709 I slot print_timing: id 1 | task 6809 | prompt eval time = 37210.31 ms / 740 tokens ( 50.28 ms per token, 19.89 tokens per second) 53.49.791.711 I slot print_timing: id 1 | task 6809 | eval time = 383.11 ms / 2 tokens ( 383.11 ms per token, 2.61 tokens per second) 53.49.791.712 I slot print_timing: id 1 | task 6809 | total time = 37593.42 ms / 742 tokens 53.49.791.712 I slot print_timing: id 1 | task 6809 | graphs reused = 5356 53.49.791.712 I slot print_timing: id 1 | task 6809 | graph reallocs = 0 / 0 (same size) / (changed size) 53.49.791.740 I slot release: id 1 | task 6809 | stop processing: n_tokens = 741, truncated = 0 53.49.791.920 I slot print_timing: id 2 | task 6810 | prompt eval time = 37210.45 ms / 753 tokens ( 49.42 ms per token, 20.24 tokens per second) 53.49.791.922 I slot print_timing: id 2 | task 6810 | eval time = 383.09 ms / 2 tokens ( 383.09 ms per token, 2.61 tokens per second) 53.49.791.922 I slot print_timing: id 2 | task 6810 | total time = 37593.54 ms / 755 tokens 53.49.791.923 I slot print_timing: id 2 | task 6810 | graphs reused = 5356 53.49.791.923 I slot print_timing: id 2 | task 6810 | graph reallocs = 0 / 0 (same size) / (changed size) 53.49.791.948 I slot release: id 2 | task 6810 | stop processing: n_tokens = 754, truncated = 0 53.49.893.068 I slot print_timing: id 3 | task 6811 | prompt eval time = 37593.76 ms / 797 tokens ( 47.17 ms per token, 21.20 tokens per second) 53.49.893.070 I slot print_timing: id 3 | task 6811 | eval time = 100.85 ms / 2 tokens ( 100.85 ms per token, 9.92 tokens per second) 53.49.893.071 I slot print_timing: id 3 | task 6811 | total time = 37694.61 ms / 799 tokens 53.49.893.071 I slot print_timing: id 3 | task 6811 | graphs reused = 5356 53.49.893.071 I slot print_timing: id 3 | task 6811 | graph reallocs = 0 / 0 (same size) / (changed size) 53.49.893.107 I slot release: id 3 | task 6811 | stop processing: n_tokens = 798, truncated = 0 53.49.893.115 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.873 (> 0.100 thold), f_keep = 0.892 53.49.893.152 I slot launch_slot_: id 0 | task 6819 | processing task, is_child = 0 53.49.893.196 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 815.906 MiB) 53.49.912.152 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 815.406 MiB) 53.49.932.135 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 815.718 MiB) 53.49.953.240 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.881 53.49.953.303 I slot launch_slot_: id 1 | task 6820 | processing task, is_child = 0 53.49.953.390 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.863 53.49.953.412 I slot launch_slot_: id 2 | task 6821 | processing task, is_child = 0 53.49.953.462 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.862 (> 0.100 thold), f_keep = 0.816 53.49.953.485 I slot launch_slot_: id 3 | task 6822 | processing task, is_child = 0 53.55.538.553 I slot print_timing: id 0 | task 6819 | prompt processing, n_tokens = 119, progress = 0.99, t = 5.59 s / 21.31 tokens per second 53.55.966.934 I slot print_timing: id 1 | task 6820 | prompt processing, n_tokens = 112, progress = 0.99, t = 5.58 s / 20.08 tokens per second 53.55.971.458 I slot print_timing: id 2 | task 6821 | prompt processing, n_tokens = 106, progress = 0.99, t = 5.57 s / 19.03 tokens per second 53.55.975.989 I slot print_timing: id 3 | task 6822 | prompt processing, n_tokens = 128, progress = 0.99, t = 5.56 s / 23.01 tokens per second 53.56.529.772 I slot print_timing: id 0 | task 6819 | prompt eval time = 6370.10 ms / 123 tokens ( 51.79 ms per token, 19.31 tokens per second) 53.56.529.774 I slot print_timing: id 0 | task 6819 | eval time = 206.18 ms / 2 tokens ( 206.18 ms per token, 4.85 tokens per second) 53.56.529.774 I slot print_timing: id 0 | task 6819 | total time = 6576.28 ms / 125 tokens 53.56.529.775 I slot print_timing: id 0 | task 6819 | graphs reused = 5356 53.56.529.775 I slot print_timing: id 0 | task 6819 | graph reallocs = 0 / 0 (same size) / (changed size) 53.56.529.817 I slot release: id 0 | task 6819 | stop processing: n_tokens = 747, truncated = 0 53.56.529.964 I slot print_timing: id 1 | task 6820 | prompt eval time = 6362.60 ms / 116 tokens ( 54.85 ms per token, 18.23 tokens per second) 53.56.529.966 I slot print_timing: id 1 | task 6820 | eval time = 206.21 ms / 2 tokens ( 206.21 ms per token, 4.85 tokens per second) 53.56.529.967 I slot print_timing: id 1 | task 6820 | total time = 6568.81 ms / 118 tokens 53.56.529.967 I slot print_timing: id 1 | task 6820 | graphs reused = 5356 53.56.529.967 I slot print_timing: id 1 | task 6820 | graph reallocs = 0 / 0 (same size) / (changed size) 53.56.529.996 I slot release: id 1 | task 6820 | stop processing: n_tokens = 740, truncated = 0 53.56.530.165 I slot print_timing: id 2 | task 6821 | prompt eval time = 6355.17 ms / 110 tokens ( 57.77 ms per token, 17.31 tokens per second) 53.56.530.167 I slot print_timing: id 2 | task 6821 | eval time = 206.23 ms / 2 tokens ( 206.23 ms per token, 4.85 tokens per second) 53.56.530.167 I slot print_timing: id 2 | task 6821 | total time = 6561.39 ms / 112 tokens 53.56.530.167 I slot print_timing: id 2 | task 6821 | graphs reused = 5356 53.56.530.168 I slot print_timing: id 2 | task 6821 | graph reallocs = 0 / 0 (same size) / (changed size) 53.56.530.192 I slot release: id 2 | task 6821 | stop processing: n_tokens = 734, truncated = 0 53.56.530.366 I slot print_timing: id 3 | task 6822 | prompt eval time = 6347.76 ms / 132 tokens ( 48.09 ms per token, 20.79 tokens per second) 53.56.530.368 I slot print_timing: id 3 | task 6822 | eval time = 206.21 ms / 2 tokens ( 206.21 ms per token, 4.85 tokens per second) 53.56.530.368 I slot print_timing: id 3 | task 6822 | total time = 6553.98 ms / 134 tokens 53.56.530.368 I slot print_timing: id 3 | task 6822 | graphs reused = 5356 53.56.530.369 I slot print_timing: id 3 | task 6822 | graph reallocs = 0 / 0 (same size) / (changed size) 53.56.530.387 I slot release: id 3 | task 6822 | stop processing: n_tokens = 756, truncated = 0 53.56.538.975 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.871 (> 0.100 thold), f_keep = 0.871 53.56.539.000 I slot launch_slot_: id 0 | task 6826 | processing task, is_child = 0 53.56.539.049 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 815.593 MiB) 53.56.557.291 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 815.656 MiB) 53.56.575.538 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 811.779 MiB) 53.56.593.674 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 740, t_last = 90025346670 53.56.593.777 I slot launch_slot_: id 1 | task 6827 | processing task, is_child = 0 53.56.593.859 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 734, t_last = 90025346866 53.56.593.917 I slot launch_slot_: id 2 | task 6829 | processing task, is_child = 0 53.56.593.959 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 756, t_last = 90025347061 53.56.594.014 I slot launch_slot_: id 3 | task 6828 | processing task, is_child = 0 54.01.962.549 I slot print_timing: id 0 | task 6826 | prompt processing, n_tokens = 120, progress = 0.99, t = 5.37 s / 22.35 tokens per second 54.03.491.363 I slot print_timing: id 1 | task 6827 | prompt processing, n_tokens = 162, progress = 0.17, t = 5.36 s / 30.22 tokens per second 54.03.495.813 I slot print_timing: id 2 | task 6829 | prompt processing, n_tokens = 162, progress = 0.16, t = 5.36 s / 30.22 tokens per second 54.03.500.217 I slot print_timing: id 3 | task 6828 | prompt processing, n_tokens = 162, progress = 0.17, t = 5.36 s / 30.22 tokens per second 54.10.421.184 I slot print_timing: id 1 | task 6827 | prompt processing, n_tokens = 350, progress = 0.37, t = 13.82 s / 25.33 tokens per second 54.10.421.199 I slot print_timing: id 2 | task 6829 | prompt processing, n_tokens = 350, progress = 0.35, t = 13.82 s / 25.33 tokens per second 54.10.421.205 I slot print_timing: id 3 | task 6828 | prompt processing, n_tokens = 350, progress = 0.36, t = 13.82 s / 25.33 tokens per second 54.15.068.854 I slot print_timing: id 0 | task 6826 | prompt eval time = 13827.15 ms / 124 tokens ( 111.51 ms per token, 8.97 tokens per second) 54.15.068.857 I slot print_timing: id 0 | task 6826 | eval time = 4647.68 ms / 2 tokens ( 4647.68 ms per token, 0.22 tokens per second) 54.15.068.857 I slot print_timing: id 0 | task 6826 | total time = 18474.83 ms / 126 tokens 54.15.068.858 I slot print_timing: id 0 | task 6826 | graphs reused = 5356 54.15.068.858 I slot print_timing: id 0 | task 6826 | graph reallocs = 0 / 0 (same size) / (changed size) 54.15.068.894 I slot release: id 0 | task 6826 | stop processing: n_tokens = 748, truncated = 0 54.15.068.905 I slot print_timing: id 1 | task 6827 | prompt processing, n_tokens = 439, progress = 0.46, t = 18.47 s / 23.77 tokens per second 54.15.075.198 I slot print_timing: id 2 | task 6829 | prompt processing, n_tokens = 474, progress = 0.48, t = 18.47 s / 25.67 tokens per second 54.15.079.887 I slot print_timing: id 3 | task 6828 | prompt processing, n_tokens = 457, progress = 0.47, t = 18.47 s / 24.75 tokens per second 54.27.950.258 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 748, t_last = 90043885568 54.27.950.314 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 812.592 MiB) 54.28.378.577 I slot launch_slot_: id 0 | task 6834 | processing task, is_child = 0 54.28.378.661 I slot print_timing: id 1 | task 6827 | prompt processing, n_tokens = 820, progress = 0.86, t = 31.35 s / 26.16 tokens per second 54.28.383.107 I slot print_timing: id 2 | task 6829 | prompt processing, n_tokens = 820, progress = 0.83, t = 31.35 s / 26.16 tokens per second 54.28.387.534 I slot print_timing: id 3 | task 6828 | prompt processing, n_tokens = 820, progress = 0.84, t = 31.35 s / 26.16 tokens per second 54.35.642.684 I slot print_timing: id 0 | task 6834 | prompt processing, n_tokens = 162, progress = 0.16, t = 7.26 s / 22.30 tokens per second 54.36.071.990 I slot print_timing: id 1 | task 6827 | prompt processing, n_tokens = 951, progress = 1.00, t = 39.04 s / 24.36 tokens per second 54.36.076.811 I slot print_timing: id 2 | task 6829 | prompt processing, n_tokens = 986, progress = 1.00, t = 39.04 s / 25.26 tokens per second 54.36.081.684 I slot print_timing: id 3 | task 6828 | prompt processing, n_tokens = 969, progress = 1.00, t = 39.04 s / 24.82 tokens per second 54.38.613.147 I slot print_timing: id 0 | task 6834 | prompt processing, n_tokens = 350, progress = 0.34, t = 10.23 s / 34.20 tokens per second 54.40.991.694 I slot print_timing: id 1 | task 6827 | prompt eval time = 42011.11 ms / 955 tokens ( 43.99 ms per token, 22.73 tokens per second) 54.40.991.696 I slot print_timing: id 1 | task 6827 | eval time = 2378.96 ms / 2 tokens ( 2378.96 ms per token, 0.42 tokens per second) 54.40.991.697 I slot print_timing: id 1 | task 6827 | total time = 44390.07 ms / 957 tokens 54.40.991.697 I slot print_timing: id 1 | task 6827 | graphs reused = 5356 54.40.991.698 I slot print_timing: id 1 | task 6827 | graph reallocs = 0 / 0 (same size) / (changed size) 54.40.991.758 I slot release: id 1 | task 6827 | stop processing: n_tokens = 956, truncated = 0 54.40.991.923 I slot print_timing: id 2 | task 6829 | prompt eval time = 42011.25 ms / 990 tokens ( 42.44 ms per token, 23.57 tokens per second) 54.40.991.928 I slot print_timing: id 2 | task 6829 | eval time = 2379.00 ms / 2 tokens ( 2379.00 ms per token, 0.42 tokens per second) 54.40.991.928 I slot print_timing: id 2 | task 6829 | total time = 44390.25 ms / 992 tokens 54.40.991.929 I slot print_timing: id 2 | task 6829 | graphs reused = 5356 54.40.991.929 I slot print_timing: id 2 | task 6829 | graph reallocs = 0 / 0 (same size) / (changed size) 54.40.991.957 I slot release: id 2 | task 6829 | stop processing: n_tokens = 991, truncated = 0 54.40.992.127 I slot print_timing: id 3 | task 6828 | prompt eval time = 42011.42 ms / 973 tokens ( 43.18 ms per token, 23.16 tokens per second) 54.40.992.130 I slot print_timing: id 3 | task 6828 | eval time = 2378.99 ms / 2 tokens ( 2378.99 ms per token, 0.42 tokens per second) 54.40.992.130 I slot print_timing: id 3 | task 6828 | total time = 44390.41 ms / 975 tokens 54.40.992.130 I slot print_timing: id 3 | task 6828 | graphs reused = 5356 54.40.992.131 I slot print_timing: id 3 | task 6828 | graph reallocs = 0 / 0 (same size) / (changed size) 54.40.992.159 I slot release: id 3 | task 6828 | stop processing: n_tokens = 974, truncated = 0 54.40.992.167 I slot print_timing: id 0 | task 6834 | prompt processing, n_tokens = 528, progress = 0.51, t = 12.61 s / 41.86 tokens per second 54.41.002.787 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 956, t_last = 90069808432 54.41.002.841 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 815.156 MiB) 54.44.609.653 I slot launch_slot_: id 1 | task 6839 | processing task, is_child = 0 54.44.609.711 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 817.344 MiB) 54.44.628.467 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 813.530 MiB) 54.44.647.278 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 991, t_last = 90069808631 54.44.647.388 I slot launch_slot_: id 2 | task 6840 | processing task, is_child = 0 54.44.647.441 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 974, t_last = 90069808833 54.44.647.513 I slot launch_slot_: id 3 | task 6841 | processing task, is_child = 0 54.44.647.520 I slot print_timing: id 0 | task 6834 | prompt processing, n_tokens = 820, progress = 0.79, t = 12.62 s / 64.95 tokens per second 54.54.294.844 I slot print_timing: id 0 | task 6834 | prompt processing, n_tokens = 1040, progress = 1.00, t = 25.92 s / 40.13 tokens per second 54.56.471.064 I slot print_timing: id 1 | task 6839 | prompt processing, n_tokens = 204, progress = 0.18, t = 9.64 s / 21.16 tokens per second 54.56.475.597 I slot print_timing: id 2 | task 6840 | prompt processing, n_tokens = 204, progress = 0.18, t = 9.64 s / 21.16 tokens per second 54.56.480.023 I slot print_timing: id 3 | task 6841 | prompt processing, n_tokens = 372, progress = 0.18, t = 9.64 s / 38.58 tokens per second 55.03.356.399 I slot print_timing: id 1 | task 6839 | prompt processing, n_tokens = 350, progress = 0.31, t = 18.70 s / 18.71 tokens per second 55.03.356.417 I slot print_timing: id 2 | task 6840 | prompt processing, n_tokens = 350, progress = 0.30, t = 18.70 s / 18.71 tokens per second 55.03.356.426 I slot print_timing: id 3 | task 6841 | prompt processing, n_tokens = 640, progress = 0.31, t = 18.70 s / 34.22 tokens per second 55.21.015.712 I slot print_timing: id 0 | task 6834 | prompt eval time = 34977.80 ms / 1044 tokens ( 33.50 ms per token, 29.85 tokens per second) 55.21.015.715 I slot print_timing: id 0 | task 6834 | eval time = 17659.32 ms / 2 tokens (17659.32 ms per token, 0.06 tokens per second) 55.21.015.715 I slot print_timing: id 0 | task 6834 | total time = 52637.12 ms / 1046 tokens 55.21.015.716 I slot print_timing: id 0 | task 6834 | graphs reused = 5356 55.21.015.716 I slot print_timing: id 0 | task 6834 | graph reallocs = 0 / 0 (same size) / (changed size) 55.21.015.786 I slot release: id 0 | task 6834 | stop processing: n_tokens = 1045, truncated = 0 55.21.015.801 I slot print_timing: id 1 | task 6839 | prompt processing, n_tokens = 608, progress = 0.54, t = 36.36 s / 16.72 tokens per second 55.21.039.983 I slot print_timing: id 2 | task 6840 | prompt processing, n_tokens = 645, progress = 0.56, t = 36.36 s / 17.74 tokens per second 55.21.044.426 I slot print_timing: id 3 | task 6841 | prompt processing, n_tokens = 1575, progress = 0.75, t = 36.36 s / 43.31 tokens per second 55.31.328.856 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1045, t_last = 90109832460 55.31.328.928 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 794.460 MiB) 55.32.093.895 I slot launch_slot_: id 0 | task 6846 | processing task, is_child = 0 55.32.093.992 I slot print_timing: id 1 | task 6839 | prompt processing, n_tokens = 977, progress = 0.87, t = 46.68 s / 20.93 tokens per second 55.32.098.407 I slot print_timing: id 2 | task 6840 | prompt processing, n_tokens = 977, progress = 0.84, t = 46.68 s / 20.93 tokens per second 55.32.102.821 I slot print_timing: id 3 | task 6841 | prompt processing, n_tokens = 1761, progress = 0.84, t = 46.68 s / 37.73 tokens per second 55.42.714.319 I slot print_timing: id 0 | task 6846 | prompt processing, n_tokens = 372, progress = 0.18, t = 10.62 s / 35.03 tokens per second 55.44.582.285 I slot print_timing: id 1 | task 6839 | prompt processing, n_tokens = 1120, progress = 1.00, t = 58.06 s / 19.29 tokens per second 55.44.586.794 I slot print_timing: id 2 | task 6840 | prompt processing, n_tokens = 1157, progress = 1.00, t = 58.06 s / 19.93 tokens per second 55.44.600.514 I slot print_timing: id 3 | task 6841 | prompt processing, n_tokens = 2087, progress = 1.00, t = 58.06 s / 35.94 tokens per second 55.48.314.341 I slot print_timing: id 0 | task 6846 | prompt processing, n_tokens = 640, progress = 0.31, t = 16.22 s / 39.46 tokens per second 55.59.288.634 I slot print_timing: id 1 | task 6839 | prompt eval time = 63661.41 ms / 1124 tokens ( 56.64 ms per token, 17.66 tokens per second) 55.59.288.640 I slot print_timing: id 1 | task 6839 | eval time = 10975.23 ms / 2 tokens (10975.23 ms per token, 0.09 tokens per second) 55.59.288.641 I slot print_timing: id 1 | task 6839 | total time = 74636.65 ms / 1126 tokens 55.59.288.641 I slot print_timing: id 1 | task 6839 | graphs reused = 5356 55.59.288.642 I slot print_timing: id 1 | task 6839 | graph reallocs = 0 / 0 (same size) / (changed size) 55.59.288.702 I slot release: id 1 | task 6839 | stop processing: n_tokens = 1125, truncated = 0 55.59.289.156 I slot print_timing: id 2 | task 6840 | prompt eval time = 63661.77 ms / 1161 tokens ( 54.83 ms per token, 18.24 tokens per second) 55.59.289.159 I slot print_timing: id 2 | task 6840 | eval time = 10975.33 ms / 2 tokens (10975.33 ms per token, 0.09 tokens per second) 55.59.289.159 I slot print_timing: id 2 | task 6840 | total time = 74637.10 ms / 1163 tokens 55.59.289.160 I slot print_timing: id 2 | task 6840 | graphs reused = 5356 55.59.289.160 I slot print_timing: id 2 | task 6840 | graph reallocs = 0 / 0 (same size) / (changed size) 55.59.289.192 I slot release: id 2 | task 6840 | stop processing: n_tokens = 1162, truncated = 0 55.59.289.816 I slot print_timing: id 3 | task 6841 | prompt eval time = 63662.19 ms / 2091 tokens ( 30.45 ms per token, 32.85 tokens per second) 55.59.289.820 I slot print_timing: id 3 | task 6841 | eval time = 10975.50 ms / 2 tokens (10975.50 ms per token, 0.09 tokens per second) 55.59.289.820 I slot print_timing: id 3 | task 6841 | total time = 74637.69 ms / 2093 tokens 55.59.289.820 I slot print_timing: id 3 | task 6841 | graphs reused = 5356 55.59.289.821 I slot print_timing: id 3 | task 6841 | graph reallocs = 0 / 0 (same size) / (changed size) 55.59.289.953 I slot release: id 3 | task 6841 | stop processing: n_tokens = 2092, truncated = 0 55.59.289.980 I slot print_timing: id 0 | task 6846 | prompt processing, n_tokens = 1578, progress = 0.75, t = 27.19 s / 58.03 tokens per second 55.59.311.903 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.877 (> 0.100 thold), f_keep = 0.856 55.59.311.945 I slot launch_slot_: id 3 | task 6851 | processing task, is_child = 0 55.59.312.005 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 795.273 MiB) 56.01.539.148 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 798.024 MiB) 56.01.572.142 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1125, t_last = 90148105376 56.01.572.277 I slot launch_slot_: id 1 | task 6852 | processing task, is_child = 0 56.01.572.336 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1162, t_last = 90148105866 56.01.572.409 I slot launch_slot_: id 2 | task 6853 | processing task, is_child = 0 56.01.572.417 I slot print_timing: id 0 | task 6846 | prompt processing, n_tokens = 1761, progress = 0.84, t = 27.22 s / 64.70 tokens per second 56.16.142.945 I slot print_timing: id 0 | task 6846 | prompt processing, n_tokens = 2090, progress = 1.00, t = 44.05 s / 47.45 tokens per second 56.17.309.323 I slot print_timing: id 1 | task 6852 | prompt processing, n_tokens = 372, progress = 0.18, t = 14.57 s / 25.54 tokens per second 56.17.313.916 I slot print_timing: id 2 | task 6853 | prompt processing, n_tokens = 372, progress = 0.18, t = 14.57 s / 25.54 tokens per second 56.17.318.616 I slot print_timing: id 3 | task 6851 | prompt processing, n_tokens = 276, progress = 1.00, t = 14.57 s / 18.95 tokens per second 56.23.656.086 I slot print_timing: id 1 | task 6852 | prompt processing, n_tokens = 640, progress = 0.31, t = 22.08 s / 28.99 tokens per second 56.23.656.113 I slot print_timing: id 2 | task 6853 | prompt processing, n_tokens = 640, progress = 0.30, t = 22.08 s / 28.99 tokens per second 56.45.205.752 I slot print_timing: id 0 | task 6846 | prompt eval time = 51561.93 ms / 2094 tokens ( 24.62 ms per token, 40.61 tokens per second) 56.45.205.758 I slot print_timing: id 0 | task 6846 | eval time = 21549.91 ms / 2 tokens (21549.91 ms per token, 0.05 tokens per second) 56.45.205.758 I slot print_timing: id 0 | task 6846 | total time = 73111.84 ms / 2096 tokens 56.45.205.759 I slot print_timing: id 0 | task 6846 | graphs reused = 5356 56.45.205.759 I slot print_timing: id 0 | task 6846 | graph reallocs = 0 / 0 (same size) / (changed size) 56.45.205.862 I slot release: id 0 | task 6846 | stop processing: n_tokens = 2095, truncated = 0 56.45.206.099 I slot print_timing: id 3 | task 6851 | prompt eval time = 22079.06 ms / 280 tokens ( 78.85 ms per token, 12.68 tokens per second) 56.45.206.101 I slot print_timing: id 3 | task 6851 | eval time = 21550.03 ms / 2 tokens (21550.03 ms per token, 0.05 tokens per second) 56.45.206.102 I slot print_timing: id 3 | task 6851 | total time = 43629.09 ms / 282 tokens 56.45.206.102 I slot print_timing: id 3 | task 6851 | graphs reused = 5356 56.45.206.103 I slot print_timing: id 3 | task 6851 | graph reallocs = 0 / 0 (same size) / (changed size) 56.45.206.162 I slot release: id 3 | task 6851 | stop processing: n_tokens = 2042, truncated = 0 56.45.206.174 I slot print_timing: id 1 | task 6852 | prompt processing, n_tokens = 1541, progress = 0.75, t = 43.63 s / 35.32 tokens per second 56.45.213.612 I slot print_timing: id 2 | task 6853 | prompt processing, n_tokens = 1589, progress = 0.75, t = 43.63 s / 36.42 tokens per second 56.49.283.672 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.868 (> 0.100 thold), f_keep = 0.854 56.49.283.738 I slot launch_slot_: id 0 | task 6858 | processing task, is_child = 0 56.49.283.833 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 794.398 MiB) 56.50.067.051 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.840 (> 0.100 thold), f_keep = 0.877 56.50.067.126 I slot launch_slot_: id 3 | task 6859 | processing task, is_child = 0 56.50.074.746 I slot print_timing: id 1 | task 6852 | prompt processing, n_tokens = 1761, progress = 0.86, t = 47.71 s / 36.91 tokens per second 56.50.079.184 I slot print_timing: id 2 | task 6853 | prompt processing, n_tokens = 1761, progress = 0.84, t = 47.71 s / 36.91 tokens per second 57.04.968.724 I slot print_timing: id 0 | task 6858 | prompt processing, n_tokens = 296, progress = 1.00, t = 14.90 s / 19.86 tokens per second 57.05.408.274 I slot print_timing: id 1 | task 6852 | prompt processing, n_tokens = 2053, progress = 1.00, t = 63.39 s / 32.39 tokens per second 57.05.413.251 I slot print_timing: id 2 | task 6853 | prompt processing, n_tokens = 2101, progress = 1.00, t = 63.39 s / 33.14 tokens per second 57.05.417.861 I slot print_timing: id 3 | task 6859 | prompt processing, n_tokens = 365, progress = 1.00, t = 14.89 s / 24.52 tokens per second 57.05.983.352 I slot print_timing: id 0 | task 6858 | prompt eval time = 15707.30 ms / 300 tokens ( 52.36 ms per token, 19.10 tokens per second) 57.05.983.357 I slot print_timing: id 0 | task 6858 | eval time = 208.91 ms / 2 tokens ( 208.91 ms per token, 4.79 tokens per second) 57.05.983.357 I slot print_timing: id 0 | task 6858 | total time = 15916.21 ms / 302 tokens 57.05.983.358 I slot print_timing: id 0 | task 6858 | graphs reused = 5357 57.05.983.358 I slot print_timing: id 0 | task 6858 | graph reallocs = 0 / 0 (same size) / (changed size) 57.05.983.434 I slot release: id 0 | task 6858 | stop processing: n_tokens = 2062, truncated = 0 57.05.983.586 I slot print_timing: id 1 | task 6852 | prompt eval time = 64197.76 ms / 2057 tokens ( 31.21 ms per token, 32.04 tokens per second) 57.05.983.589 I slot print_timing: id 1 | task 6852 | eval time = 208.98 ms / 2 tokens ( 208.98 ms per token, 4.79 tokens per second) 57.05.983.590 I slot print_timing: id 1 | task 6852 | total time = 64406.73 ms / 2059 tokens 57.05.983.590 I slot print_timing: id 1 | task 6852 | graphs reused = 5357 57.05.983.590 I slot print_timing: id 1 | task 6852 | graph reallocs = 0 / 0 (same size) / (changed size) 57.05.983.642 I slot release: id 1 | task 6852 | stop processing: n_tokens = 2058, truncated = 0 57.05.983.810 I slot print_timing: id 2 | task 6853 | prompt eval time = 64197.85 ms / 2105 tokens ( 30.50 ms per token, 32.79 tokens per second) 57.05.983.812 I slot print_timing: id 2 | task 6853 | eval time = 209.02 ms / 2 tokens ( 209.02 ms per token, 4.78 tokens per second) 57.05.983.813 I slot print_timing: id 2 | task 6853 | total time = 64406.87 ms / 2107 tokens 57.05.983.813 I slot print_timing: id 2 | task 6853 | graphs reused = 5357 57.05.983.813 I slot print_timing: id 2 | task 6853 | graph reallocs = 0 / 0 (same size) / (changed size) 57.05.983.865 I slot release: id 2 | task 6853 | stop processing: n_tokens = 2106, truncated = 0 57.05.984.043 I slot print_timing: id 3 | task 6859 | prompt eval time = 15691.55 ms / 369 tokens ( 42.52 ms per token, 23.52 tokens per second) 57.05.984.047 I slot print_timing: id 3 | task 6859 | eval time = 208.87 ms / 2 tokens ( 208.87 ms per token, 4.79 tokens per second) 57.05.984.047 I slot print_timing: id 3 | task 6859 | total time = 15900.42 ms / 371 tokens 57.05.984.047 I slot print_timing: id 3 | task 6859 | graphs reused = 5357 57.05.984.048 I slot print_timing: id 3 | task 6859 | graph reallocs = 0 / 0 (same size) / (changed size) 57.05.984.104 I slot release: id 3 | task 6859 | stop processing: n_tokens = 2131, truncated = 0 57.05.995.278 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.870 57.05.995.317 I slot launch_slot_: id 1 | task 6863 | processing task, is_child = 0 57.05.995.410 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 794.023 MiB) 57.05.995.414 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 795.398 MiB) 57.06.034.351 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 794.898 MiB) 57.06.379.743 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 807.903 MiB) 57.07.566.704 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.803 (> 0.100 thold), f_keep = 0.850 57.07.566.812 I slot launch_slot_: id 2 | task 6864 | processing task, is_child = 0 57.07.567.030 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.887 (> 0.100 thold), f_keep = 0.840 57.07.567.058 I slot launch_slot_: id 3 | task 6865 | processing task, is_child = 0 57.07.567.145 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.836 (> 0.100 thold), f_keep = 0.868 57.07.567.171 I slot launch_slot_: id 0 | task 6866 | processing task, is_child = 0 57.20.663.256 I slot print_timing: id 0 | task 6866 | prompt processing, n_tokens = 376, progress = 1.00, t = 13.10 s / 28.71 tokens per second 57.23.266.169 I slot print_timing: id 1 | task 6863 | prompt processing, n_tokens = 206, progress = 1.00, t = 13.05 s / 15.79 tokens per second 57.23.279.930 I slot print_timing: id 2 | task 6864 | prompt processing, n_tokens = 463, progress = 1.00, t = 12.99 s / 35.63 tokens per second 57.23.294.437 I slot print_timing: id 3 | task 6865 | prompt processing, n_tokens = 254, progress = 1.00, t = 12.96 s / 19.60 tokens per second 57.23.870.779 I slot print_timing: id 0 | task 6866 | prompt eval time = 16093.72 ms / 380 tokens ( 42.35 ms per token, 23.61 tokens per second) 57.23.870.783 I slot print_timing: id 0 | task 6866 | eval time = 209.88 ms / 2 tokens ( 209.88 ms per token, 4.76 tokens per second) 57.23.870.784 I slot print_timing: id 0 | task 6866 | total time = 16303.60 ms / 382 tokens 57.23.870.784 I slot print_timing: id 0 | task 6866 | graphs reused = 5357 57.23.870.784 I slot print_timing: id 0 | task 6866 | graph reallocs = 0 / 0 (same size) / (changed size) 57.23.870.970 I slot release: id 0 | task 6866 | stop processing: n_tokens = 2142, truncated = 0 57.23.871.244 I slot print_timing: id 1 | task 6863 | prompt eval time = 16046.84 ms / 210 tokens ( 76.41 ms per token, 13.09 tokens per second) 57.23.871.247 I slot print_timing: id 1 | task 6863 | eval time = 210.01 ms / 2 tokens ( 210.01 ms per token, 4.76 tokens per second) 57.23.871.248 I slot print_timing: id 1 | task 6863 | total time = 16256.85 ms / 212 tokens 57.23.871.248 I slot print_timing: id 1 | task 6863 | graphs reused = 5357 57.23.871.248 I slot print_timing: id 1 | task 6863 | graph reallocs = 0 / 0 (same size) / (changed size) 57.23.871.303 I slot release: id 1 | task 6863 | stop processing: n_tokens = 1972, truncated = 0 57.23.871.501 I slot print_timing: id 2 | task 6864 | prompt eval time = 15991.35 ms / 467 tokens ( 34.24 ms per token, 29.20 tokens per second) 57.23.871.503 I slot print_timing: id 2 | task 6864 | eval time = 209.86 ms / 2 tokens ( 209.86 ms per token, 4.77 tokens per second) 57.23.871.504 I slot print_timing: id 2 | task 6864 | total time = 16201.20 ms / 469 tokens 57.23.871.505 I slot print_timing: id 2 | task 6864 | graphs reused = 5357 57.23.871.505 I slot print_timing: id 2 | task 6864 | graph reallocs = 0 / 0 (same size) / (changed size) 57.23.871.590 I slot release: id 2 | task 6864 | stop processing: n_tokens = 2229, truncated = 0 57.23.871.871 I slot print_timing: id 3 | task 6865 | prompt eval time = 15958.17 ms / 258 tokens ( 61.85 ms per token, 16.17 tokens per second) 57.23.871.873 I slot print_timing: id 3 | task 6865 | eval time = 209.58 ms / 2 tokens ( 209.58 ms per token, 4.77 tokens per second) 57.23.871.874 I slot print_timing: id 3 | task 6865 | total time = 16167.74 ms / 260 tokens 57.23.871.874 I slot print_timing: id 3 | task 6865 | graphs reused = 5357 57.23.871.874 I slot print_timing: id 3 | task 6865 | graph reallocs = 0 / 0 (same size) / (changed size) 57.23.871.960 I slot release: id 3 | task 6865 | stop processing: n_tokens = 2020, truncated = 0 57.23.884.892 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.835 57.23.884.928 I slot launch_slot_: id 0 | task 6870 | processing task, is_child = 0 57.23.885.019 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 810.091 MiB) 57.24.045.860 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 809.028 MiB) 57.24.254.027 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 813.467 MiB) 57.24.348.894 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.907 57.24.348.968 I slot launch_slot_: id 1 | task 6871 | processing task, is_child = 0 57.24.349.158 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.867 (> 0.100 thold), f_keep = 0.803 57.24.349.193 I slot launch_slot_: id 2 | task 6872 | processing task, is_child = 0 57.24.349.279 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.850 (> 0.100 thold), f_keep = 0.886 57.24.349.301 I slot launch_slot_: id 3 | task 6873 | processing task, is_child = 0 57.36.931.639 I slot print_timing: id 0 | task 6870 | prompt processing, n_tokens = 208, progress = 1.00, t = 12.58 s / 16.53 tokens per second 57.37.709.920 I slot print_timing: id 1 | task 6871 | prompt processing, n_tokens = 249, progress = 1.00, t = 12.57 s / 19.81 tokens per second 57.37.714.543 I slot print_timing: id 2 | task 6872 | prompt processing, n_tokens = 300, progress = 1.00, t = 12.56 s / 23.88 tokens per second 57.37.719.176 I slot print_timing: id 3 | task 6873 | prompt processing, n_tokens = 341, progress = 1.00, t = 12.55 s / 27.16 tokens per second 57.38.284.730 I slot print_timing: id 0 | task 6870 | prompt eval time = 13726.34 ms / 212 tokens ( 64.75 ms per token, 15.44 tokens per second) 57.38.284.732 I slot print_timing: id 0 | task 6870 | eval time = 209.08 ms / 2 tokens ( 209.08 ms per token, 4.78 tokens per second) 57.38.284.732 I slot print_timing: id 0 | task 6870 | total time = 13935.42 ms / 214 tokens 57.38.284.733 I slot print_timing: id 0 | task 6870 | graphs reused = 5357 57.38.284.733 I slot print_timing: id 0 | task 6870 | graph reallocs = 0 / 0 (same size) / (changed size) 57.38.284.831 I slot release: id 0 | task 6870 | stop processing: n_tokens = 1974, truncated = 0 57.38.284.988 I slot print_timing: id 1 | task 6871 | prompt eval time = 13712.60 ms / 253 tokens ( 54.20 ms per token, 18.45 tokens per second) 57.38.284.993 I slot print_timing: id 1 | task 6871 | eval time = 209.17 ms / 2 tokens ( 209.17 ms per token, 4.78 tokens per second) 57.38.284.994 I slot print_timing: id 1 | task 6871 | total time = 13921.77 ms / 255 tokens 57.38.284.994 I slot print_timing: id 1 | task 6871 | graphs reused = 5357 57.38.284.995 I slot print_timing: id 1 | task 6871 | graph reallocs = 0 / 0 (same size) / (changed size) 57.38.285.053 I slot release: id 1 | task 6871 | stop processing: n_tokens = 2015, truncated = 0 57.38.285.235 I slot print_timing: id 2 | task 6872 | prompt eval time = 13705.06 ms / 304 tokens ( 45.08 ms per token, 22.18 tokens per second) 57.38.285.240 I slot print_timing: id 2 | task 6872 | eval time = 209.25 ms / 2 tokens ( 209.25 ms per token, 4.78 tokens per second) 57.38.285.240 I slot print_timing: id 2 | task 6872 | total time = 13914.31 ms / 306 tokens 57.38.285.241 I slot print_timing: id 2 | task 6872 | graphs reused = 5357 57.38.285.241 I slot print_timing: id 2 | task 6872 | graph reallocs = 0 / 0 (same size) / (changed size) 57.38.285.299 I slot release: id 2 | task 6872 | stop processing: n_tokens = 2066, truncated = 0 57.38.285.466 I slot print_timing: id 3 | task 6873 | prompt eval time = 13697.57 ms / 345 tokens ( 39.70 ms per token, 25.19 tokens per second) 57.38.285.467 I slot print_timing: id 3 | task 6873 | eval time = 209.32 ms / 2 tokens ( 209.32 ms per token, 4.78 tokens per second) 57.38.285.468 I slot print_timing: id 3 | task 6873 | total time = 13906.89 ms / 347 tokens 57.38.285.468 I slot print_timing: id 3 | task 6873 | graphs reused = 5357 57.38.285.468 I slot print_timing: id 3 | task 6873 | graph reallocs = 0 / 0 (same size) / (changed size) 57.38.285.520 I slot release: id 3 | task 6873 | stop processing: n_tokens = 2107, truncated = 0 57.38.296.876 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.847 (> 0.100 thold), f_keep = 0.866 57.38.296.902 I slot launch_slot_: id 2 | task 6877 | processing task, is_child = 0 57.38.296.997 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 818.469 MiB) 57.38.395.464 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 820.783 MiB) 57.38.493.564 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 875.803 MiB) 57.38.560.709 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.850 57.38.560.769 I slot launch_slot_: id 3 | task 6878 | processing task, is_child = 0 57.38.560.941 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.866 (> 0.100 thold), f_keep = 0.906 57.38.560.968 I slot launch_slot_: id 0 | task 6879 | processing task, is_child = 0 57.38.561.052 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.826 (> 0.100 thold), f_keep = 0.888 57.38.561.071 I slot launch_slot_: id 1 | task 6880 | processing task, is_child = 0 57.52.947.760 I slot print_timing: id 0 | task 6879 | prompt processing, n_tokens = 300, progress = 1.00, t = 14.39 s / 20.85 tokens per second 57.53.736.281 I slot print_timing: id 1 | task 6880 | prompt processing, n_tokens = 401, progress = 1.00, t = 14.38 s / 27.89 tokens per second 57.53.741.451 I slot print_timing: id 2 | task 6877 | prompt processing, n_tokens = 349, progress = 1.00, t = 14.37 s / 24.28 tokens per second 57.53.746.580 I slot print_timing: id 3 | task 6878 | prompt processing, n_tokens = 206, progress = 1.00, t = 14.36 s / 14.34 tokens per second 57.54.312.379 I slot print_timing: id 0 | task 6879 | prompt eval time = 15542.44 ms / 304 tokens ( 51.13 ms per token, 19.56 tokens per second) 57.54.312.382 I slot print_timing: id 0 | task 6879 | eval time = 208.85 ms / 2 tokens ( 208.85 ms per token, 4.79 tokens per second) 57.54.312.382 I slot print_timing: id 0 | task 6879 | total time = 15751.30 ms / 306 tokens 57.54.312.383 I slot print_timing: id 0 | task 6879 | graphs reused = 5357 57.54.312.383 I slot print_timing: id 0 | task 6879 | graph reallocs = 0 / 0 (same size) / (changed size) 57.54.312.475 I slot release: id 0 | task 6879 | stop processing: n_tokens = 2066, truncated = 0 57.54.312.634 I slot print_timing: id 1 | task 6880 | prompt eval time = 15535.01 ms / 405 tokens ( 38.36 ms per token, 26.07 tokens per second) 57.54.312.638 I slot print_timing: id 1 | task 6880 | eval time = 208.95 ms / 2 tokens ( 208.95 ms per token, 4.79 tokens per second) 57.54.312.638 I slot print_timing: id 1 | task 6880 | total time = 15743.96 ms / 407 tokens 57.54.312.639 I slot print_timing: id 1 | task 6880 | graphs reused = 5357 57.54.312.639 I slot print_timing: id 1 | task 6880 | graph reallocs = 0 / 0 (same size) / (changed size) 57.54.312.724 I slot release: id 1 | task 6880 | stop processing: n_tokens = 2167, truncated = 0 57.54.312.882 I slot print_timing: id 2 | task 6877 | prompt eval time = 15527.62 ms / 353 tokens ( 43.99 ms per token, 22.73 tokens per second) 57.54.312.884 I slot print_timing: id 2 | task 6877 | eval time = 209.04 ms / 2 tokens ( 209.04 ms per token, 4.78 tokens per second) 57.54.312.885 I slot print_timing: id 2 | task 6877 | total time = 15736.66 ms / 355 tokens 57.54.312.885 I slot print_timing: id 2 | task 6877 | graphs reused = 5357 57.54.312.885 I slot print_timing: id 2 | task 6877 | graph reallocs = 0 / 0 (same size) / (changed size) 57.54.312.936 I slot release: id 2 | task 6877 | stop processing: n_tokens = 2115, truncated = 0 57.54.313.102 I slot print_timing: id 3 | task 6878 | prompt eval time = 15520.17 ms / 210 tokens ( 73.91 ms per token, 13.53 tokens per second) 57.54.313.104 I slot print_timing: id 3 | task 6878 | eval time = 209.09 ms / 2 tokens ( 209.09 ms per token, 4.78 tokens per second) 57.54.313.104 I slot print_timing: id 3 | task 6878 | total time = 15729.27 ms / 212 tokens 57.54.313.104 I slot print_timing: id 3 | task 6878 | graphs reused = 5357 57.54.313.105 I slot print_timing: id 3 | task 6878 | graph reallocs = 0 / 0 (same size) / (changed size) 57.54.313.147 I slot release: id 3 | task 6878 | stop processing: n_tokens = 1972, truncated = 0 57.54.324.984 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.896 (> 0.100 thold), f_keep = 0.866 57.54.325.009 I slot launch_slot_: id 0 | task 6884 | processing task, is_child = 0 57.54.325.111 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 877.053 MiB) 57.54.433.070 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 879.804 MiB) 57.54.568.375 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 881.367 MiB) 57.54.643.068 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.880 (> 0.100 thold), f_keep = 0.826 57.54.643.123 I slot launch_slot_: id 1 | task 6885 | processing task, is_child = 0 57.54.643.301 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.846 57.54.643.322 I slot launch_slot_: id 2 | task 6886 | processing task, is_child = 0 57.54.643.408 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.823 (> 0.100 thold), f_keep = 0.908 57.54.643.426 I slot launch_slot_: id 3 | task 6887 | processing task, is_child = 0 58.06.610.706 I slot print_timing: id 0 | task 6884 | prompt processing, n_tokens = 232, progress = 1.00, t = 11.97 s / 19.39 tokens per second 58.08.481.398 I slot print_timing: id 1 | task 6885 | prompt processing, n_tokens = 268, progress = 1.00, t = 11.96 s / 22.41 tokens per second 58.08.486.966 I slot print_timing: id 2 | task 6886 | prompt processing, n_tokens = 260, progress = 1.00, t = 11.95 s / 21.75 tokens per second 58.08.492.274 I slot print_timing: id 3 | task 6887 | prompt processing, n_tokens = 409, progress = 1.00, t = 11.94 s / 34.24 tokens per second 58.09.058.740 I slot print_timing: id 0 | task 6884 | prompt eval time = 14206.35 ms / 236 tokens ( 60.20 ms per token, 16.61 tokens per second) 58.09.058.742 I slot print_timing: id 0 | task 6884 | eval time = 208.96 ms / 2 tokens ( 208.96 ms per token, 4.79 tokens per second) 58.09.058.743 I slot print_timing: id 0 | task 6884 | total time = 14415.30 ms / 238 tokens 58.09.058.743 I slot print_timing: id 0 | task 6884 | graphs reused = 5357 58.09.058.743 I slot print_timing: id 0 | task 6884 | graph reallocs = 0 / 0 (same size) / (changed size) 58.09.058.831 I slot release: id 0 | task 6884 | stop processing: n_tokens = 1998, truncated = 0 58.09.058.987 I slot print_timing: id 1 | task 6885 | prompt eval time = 14198.77 ms / 272 tokens ( 52.20 ms per token, 19.16 tokens per second) 58.09.058.989 I slot print_timing: id 1 | task 6885 | eval time = 209.04 ms / 2 tokens ( 209.04 ms per token, 4.78 tokens per second) 58.09.058.989 I slot print_timing: id 1 | task 6885 | total time = 14407.81 ms / 274 tokens 58.09.058.989 I slot print_timing: id 1 | task 6885 | graphs reused = 5357 58.09.058.990 I slot print_timing: id 1 | task 6885 | graph reallocs = 0 / 0 (same size) / (changed size) 58.09.059.036 I slot release: id 1 | task 6885 | stop processing: n_tokens = 2034, truncated = 0 58.09.059.206 I slot print_timing: id 2 | task 6886 | prompt eval time = 14191.36 ms / 264 tokens ( 53.76 ms per token, 18.60 tokens per second) 58.09.059.208 I slot print_timing: id 2 | task 6886 | eval time = 209.10 ms / 2 tokens ( 209.10 ms per token, 4.78 tokens per second) 58.09.059.209 I slot print_timing: id 2 | task 6886 | total time = 14400.46 ms / 266 tokens 58.09.059.209 I slot print_timing: id 2 | task 6886 | graphs reused = 5357 58.09.059.209 I slot print_timing: id 2 | task 6886 | graph reallocs = 0 / 0 (same size) / (changed size) 58.09.059.261 I slot release: id 2 | task 6886 | stop processing: n_tokens = 2026, truncated = 0 58.09.059.422 I slot print_timing: id 3 | task 6887 | prompt eval time = 14183.97 ms / 413 tokens ( 34.34 ms per token, 29.12 tokens per second) 58.09.059.426 I slot print_timing: id 3 | task 6887 | eval time = 209.15 ms / 2 tokens ( 209.15 ms per token, 4.78 tokens per second) 58.09.059.427 I slot print_timing: id 3 | task 6887 | total time = 14393.12 ms / 415 tokens 58.09.059.427 I slot print_timing: id 3 | task 6887 | graphs reused = 5357 58.09.059.428 I slot print_timing: id 3 | task 6887 | graph reallocs = 0 / 0 (same size) / (changed size) 58.09.059.485 I slot release: id 3 | task 6887 | stop processing: n_tokens = 2175, truncated = 0 58.09.070.616 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1998, t_last = 90277875505 58.09.070.716 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 871.426 MiB) 58.09.142.765 I slot launch_slot_: id 0 | task 6891 | processing task, is_child = 0 58.09.142.865 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 887.495 MiB) 58.09.210.991 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 874.427 MiB) 58.09.242.548 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 871.551 MiB) 58.09.268.045 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.899 (> 0.100 thold), f_keep = 0.884 58.09.268.105 I slot launch_slot_: id 2 | task 6892 | processing task, is_child = 0 58.09.268.281 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.880 58.09.268.303 I slot launch_slot_: id 1 | task 6893 | processing task, is_child = 0 58.09.268.397 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.823 58.09.268.417 I slot launch_slot_: id 3 | task 6894 | processing task, is_child = 0 58.20.011.121 I slot print_timing: id 0 | task 6891 | prompt processing, n_tokens = 363, progress = 0.25, t = 10.74 s / 33.79 tokens per second 58.20.778.598 I slot print_timing: id 1 | task 6893 | prompt processing, n_tokens = 145, progress = 1.00, t = 10.74 s / 13.50 tokens per second 58.20.784.048 I slot print_timing: id 2 | task 6892 | prompt processing, n_tokens = 226, progress = 1.00, t = 10.73 s / 21.05 tokens per second 58.20.789.186 I slot print_timing: id 3 | task 6894 | prompt processing, n_tokens = 192, progress = 1.00, t = 10.73 s / 17.90 tokens per second 58.23.697.978 I slot print_timing: id 0 | task 6891 | prompt processing, n_tokens = 575, progress = 0.39, t = 14.43 s / 39.85 tokens per second 58.28.163.758 I slot print_timing: id 1 | task 6893 | prompt eval time = 14428.94 ms / 149 tokens ( 96.84 ms per token, 10.33 tokens per second) 58.28.163.760 I slot print_timing: id 1 | task 6893 | eval time = 4466.23 ms / 2 tokens ( 4466.23 ms per token, 0.22 tokens per second) 58.28.163.761 I slot print_timing: id 1 | task 6893 | total time = 18895.17 ms / 151 tokens 58.28.163.762 I slot print_timing: id 1 | task 6893 | graphs reused = 5357 58.28.163.762 I slot print_timing: id 1 | task 6893 | graph reallocs = 0 / 0 (same size) / (changed size) 58.28.163.834 I slot release: id 1 | task 6893 | stop processing: n_tokens = 1911, truncated = 0 58.28.164.059 I slot print_timing: id 2 | task 6892 | prompt eval time = 14421.56 ms / 230 tokens ( 62.70 ms per token, 15.95 tokens per second) 58.28.164.062 I slot print_timing: id 2 | task 6892 | eval time = 4466.31 ms / 2 tokens ( 4466.31 ms per token, 0.22 tokens per second) 58.28.164.063 I slot print_timing: id 2 | task 6892 | total time = 18887.87 ms / 232 tokens 58.28.164.063 I slot print_timing: id 2 | task 6892 | graphs reused = 5357 58.28.164.063 I slot print_timing: id 2 | task 6892 | graph reallocs = 0 / 0 (same size) / (changed size) 58.28.164.122 I slot release: id 2 | task 6892 | stop processing: n_tokens = 1992, truncated = 0 58.28.164.352 I slot print_timing: id 3 | task 6894 | prompt eval time = 14414.22 ms / 196 tokens ( 73.54 ms per token, 13.60 tokens per second) 58.28.164.354 I slot print_timing: id 3 | task 6894 | eval time = 4466.38 ms / 2 tokens ( 4466.38 ms per token, 0.22 tokens per second) 58.28.164.356 I slot print_timing: id 3 | task 6894 | total time = 18880.60 ms / 198 tokens 58.28.164.356 I slot print_timing: id 3 | task 6894 | graphs reused = 5357 58.28.164.356 I slot print_timing: id 3 | task 6894 | graph reallocs = 0 / 0 (same size) / (changed size) 58.28.164.416 I slot release: id 3 | task 6894 | stop processing: n_tokens = 1958, truncated = 0 58.28.164.427 I slot print_timing: id 0 | task 6891 | prompt processing, n_tokens = 959, progress = 0.65, t = 18.90 s / 50.75 tokens per second 58.28.179.217 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1911, t_last = 90296980509 58.28.179.329 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 874.115 MiB) 58.31.827.631 I slot launch_slot_: id 1 | task 6899 | processing task, is_child = 0 58.31.827.733 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 879.867 MiB) 58.31.855.383 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 883.618 MiB) 58.31.883.074 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1992, t_last = 90296980796 58.31.883.231 I slot launch_slot_: id 2 | task 6900 | processing task, is_child = 0 58.31.883.317 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1958, t_last = 90296981091 58.31.883.426 I slot launch_slot_: id 3 | task 6901 | processing task, is_child = 0 58.31.883.433 I slot print_timing: id 0 | task 6891 | prompt processing, n_tokens = 1275, progress = 0.86, t = 18.91 s / 67.42 tokens per second 58.43.502.205 I slot print_timing: id 0 | task 6891 | prompt processing, n_tokens = 1471, progress = 1.00, t = 34.23 s / 42.97 tokens per second 58.46.067.224 I slot print_timing: id 1 | task 6899 | prompt processing, n_tokens = 261, progress = 0.26, t = 11.61 s / 22.47 tokens per second 58.46.071.659 I slot print_timing: id 2 | task 6900 | prompt processing, n_tokens = 363, progress = 0.23, t = 11.61 s / 31.25 tokens per second 58.46.083.964 I slot print_timing: id 3 | task 6901 | prompt processing, n_tokens = 363, progress = 0.22, t = 11.61 s / 31.26 tokens per second 58.53.001.284 I slot print_timing: id 1 | task 6899 | prompt processing, n_tokens = 409, progress = 0.41, t = 21.07 s / 19.41 tokens per second 58.53.001.299 I slot print_timing: id 2 | task 6900 | prompt processing, n_tokens = 575, progress = 0.37, t = 21.07 s / 27.29 tokens per second 58.53.001.312 I slot print_timing: id 3 | task 6901 | prompt processing, n_tokens = 575, progress = 0.34, t = 21.07 s / 27.29 tokens per second 59.06.303.084 I slot print_timing: id 0 | task 6891 | prompt eval time = 43732.84 ms / 1475 tokens ( 29.65 ms per token, 33.73 tokens per second) 59.06.303.091 I slot print_timing: id 0 | task 6891 | eval time = 13301.81 ms / 2 tokens (13301.81 ms per token, 0.08 tokens per second) 59.06.303.091 I slot print_timing: id 0 | task 6891 | total time = 57034.65 ms / 1477 tokens 59.06.303.092 I slot print_timing: id 0 | task 6891 | graphs reused = 5357 59.06.303.092 I slot print_timing: id 0 | task 6891 | graph reallocs = 0 / 0 (same size) / (changed size) 59.06.303.191 I slot release: id 0 | task 6891 | stop processing: n_tokens = 1476, truncated = 0 59.06.303.208 I slot print_timing: id 1 | task 6899 | prompt processing, n_tokens = 483, progress = 0.48, t = 34.41 s / 14.03 tokens per second 59.06.308.537 I slot print_timing: id 2 | task 6900 | prompt processing, n_tokens = 1039, progress = 0.67, t = 34.41 s / 30.19 tokens per second 59.06.320.181 I slot print_timing: id 3 | task 6901 | prompt processing, n_tokens = 1161, progress = 0.69, t = 34.41 s / 33.74 tokens per second 59.13.265.397 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1476, t_last = 90335119866 59.13.265.479 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 880.367 MiB) 59.15.099.669 I slot launch_slot_: id 0 | task 6906 | processing task, is_child = 0 59.15.099.788 I slot print_timing: id 1 | task 6899 | prompt processing, n_tokens = 853, progress = 0.85, t = 41.38 s / 20.62 tokens per second 59.15.104.235 I slot print_timing: id 2 | task 6900 | prompt processing, n_tokens = 1275, progress = 0.82, t = 41.38 s / 30.81 tokens per second 59.15.108.642 I slot print_timing: id 3 | task 6901 | prompt processing, n_tokens = 1275, progress = 0.76, t = 41.38 s / 30.81 tokens per second 59.26.464.250 I slot print_timing: id 0 | task 6906 | prompt processing, n_tokens = 261, progress = 0.26, t = 11.36 s / 22.97 tokens per second 59.27.968.889 I slot print_timing: id 1 | task 6899 | prompt processing, n_tokens = 995, progress = 1.00, t = 54.58 s / 18.23 tokens per second 59.27.973.444 I slot print_timing: id 2 | task 6900 | prompt processing, n_tokens = 1551, progress = 1.00, t = 54.58 s / 28.42 tokens per second 59.27.986.547 I slot print_timing: id 3 | task 6901 | prompt processing, n_tokens = 1673, progress = 1.00, t = 54.58 s / 30.65 tokens per second 59.30.164.831 I slot print_timing: id 0 | task 6906 | prompt processing, n_tokens = 409, progress = 0.41, t = 15.06 s / 27.15 tokens per second 59.31.130.921 I slot print_timing: id 1 | task 6899 | prompt eval time = 58276.53 ms / 999 tokens ( 58.33 ms per token, 17.14 tokens per second) 59.31.130.924 I slot print_timing: id 1 | task 6899 | eval time = 966.52 ms / 2 tokens ( 966.52 ms per token, 1.03 tokens per second) 59.31.130.925 I slot print_timing: id 1 | task 6899 | total time = 59243.04 ms / 1001 tokens 59.31.130.926 I slot print_timing: id 1 | task 6899 | graphs reused = 5357 59.31.130.926 I slot print_timing: id 1 | task 6899 | graph reallocs = 0 / 0 (same size) / (changed size) 59.31.130.987 I slot release: id 1 | task 6899 | stop processing: n_tokens = 1000, truncated = 0 59.31.131.139 I slot print_timing: id 2 | task 6900 | prompt eval time = 58276.60 ms / 1555 tokens ( 37.48 ms per token, 26.68 tokens per second) 59.31.131.142 I slot print_timing: id 2 | task 6900 | eval time = 966.53 ms / 2 tokens ( 966.53 ms per token, 1.03 tokens per second) 59.31.131.143 I slot print_timing: id 2 | task 6900 | total time = 59243.13 ms / 1557 tokens 59.31.131.143 I slot print_timing: id 2 | task 6900 | graphs reused = 5357 59.31.131.144 I slot print_timing: id 2 | task 6900 | graph reallocs = 0 / 0 (same size) / (changed size) 59.31.131.212 I slot release: id 2 | task 6900 | stop processing: n_tokens = 1556, truncated = 0 59.31.131.466 I slot print_timing: id 3 | task 6901 | prompt eval time = 58276.68 ms / 1677 tokens ( 34.75 ms per token, 28.78 tokens per second) 59.31.131.468 I slot print_timing: id 3 | task 6901 | eval time = 966.65 ms / 2 tokens ( 966.65 ms per token, 1.03 tokens per second) 59.31.131.469 I slot print_timing: id 3 | task 6901 | total time = 59243.32 ms / 1679 tokens 59.31.131.469 I slot print_timing: id 3 | task 6901 | graphs reused = 5357 59.31.131.469 I slot print_timing: id 3 | task 6901 | graph reallocs = 0 / 0 (same size) / (changed size) 59.31.131.522 I slot release: id 3 | task 6901 | stop processing: n_tokens = 1678, truncated = 0 59.31.131.531 I slot print_timing: id 0 | task 6906 | prompt processing, n_tokens = 473, progress = 0.48, t = 16.03 s / 29.51 tokens per second 59.31.143.719 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.882 59.31.143.757 I slot launch_slot_: id 1 | task 6911 | processing task, is_child = 0 59.31.143.833 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 871.426 MiB) 59.35.468.654 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 873.052 MiB) 59.35.496.368 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1556, t_last = 90359947886 59.35.496.507 I slot launch_slot_: id 2 | task 6912 | processing task, is_child = 0 59.35.496.580 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1678, t_last = 90359948196 59.35.496.672 I slot launch_slot_: id 3 | task 6913 | processing task, is_child = 0 59.35.496.679 I slot print_timing: id 0 | task 6906 | prompt processing, n_tokens = 853, progress = 0.86, t = 16.04 s / 53.17 tokens per second 59.41.173.894 I slot print_timing: id 0 | task 6906 | prompt processing, n_tokens = 985, progress = 1.00, t = 26.07 s / 37.78 tokens per second 59.44.459.355 I slot print_timing: id 1 | task 6911 | prompt processing, n_tokens = 120, progress = 1.00, t = 5.66 s / 21.19 tokens per second 59.44.463.872 I slot print_timing: id 2 | task 6912 | prompt processing, n_tokens = 261, progress = 0.27, t = 5.66 s / 46.15 tokens per second 59.44.468.315 I slot print_timing: id 3 | task 6913 | prompt processing, n_tokens = 261, progress = 0.27, t = 5.66 s / 46.15 tokens per second 59.48.063.253 I slot print_timing: id 2 | task 6912 | prompt processing, n_tokens = 409, progress = 0.43, t = 12.54 s / 32.60 tokens per second 59.48.063.264 I slot print_timing: id 3 | task 6913 | prompt processing, n_tokens = 409, progress = 0.42, t = 12.54 s / 32.60 tokens per second 59.49.841.765 I slot print_timing: id 0 | task 6906 | prompt eval time = 32963.36 ms / 989 tokens ( 33.33 ms per token, 30.00 tokens per second) 59.49.841.770 I slot print_timing: id 0 | task 6906 | eval time = 1778.72 ms / 2 tokens ( 1778.72 ms per token, 0.56 tokens per second) 59.49.841.771 I slot print_timing: id 0 | task 6906 | total time = 34742.08 ms / 991 tokens 59.49.841.771 I slot print_timing: id 0 | task 6906 | graphs reused = 5357 59.49.841.772 I slot print_timing: id 0 | task 6906 | graph reallocs = 0 / 0 (same size) / (changed size) 59.49.841.834 I slot release: id 0 | task 6906 | stop processing: n_tokens = 990, truncated = 0 59.49.842.071 I slot print_timing: id 1 | task 6911 | prompt eval time = 12552.87 ms / 124 tokens ( 101.23 ms per token, 9.88 tokens per second) 59.49.842.073 I slot print_timing: id 1 | task 6911 | eval time = 1778.83 ms / 2 tokens ( 1778.83 ms per token, 0.56 tokens per second) 59.49.842.074 I slot print_timing: id 1 | task 6911 | total time = 14331.70 ms / 126 tokens 59.49.842.074 I slot print_timing: id 1 | task 6911 | graphs reused = 5357 59.49.842.074 I slot print_timing: id 1 | task 6911 | graph reallocs = 0 / 0 (same size) / (changed size) 59.49.842.103 I slot release: id 1 | task 6911 | stop processing: n_tokens = 978, truncated = 0 59.49.842.110 I slot print_timing: id 2 | task 6912 | prompt processing, n_tokens = 444, progress = 0.46, t = 14.32 s / 31.00 tokens per second 59.49.849.714 I slot print_timing: id 3 | task 6913 | prompt processing, n_tokens = 467, progress = 0.48, t = 14.32 s / 32.60 tokens per second 59.58.837.510 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.890 59.58.837.592 I slot launch_slot_: id 0 | task 6918 | processing task, is_child = 0 59.58.837.652 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 875.303 MiB) 59.59.268.580 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.901 59.59.268.658 I slot launch_slot_: id 1 | task 6919 | processing task, is_child = 0 59.59.286.732 I slot print_timing: id 2 | task 6912 | prompt processing, n_tokens = 853, progress = 0.89, t = 23.32 s / 36.58 tokens per second 59.59.291.164 I slot print_timing: id 3 | task 6913 | prompt processing, n_tokens = 853, progress = 0.87, t = 23.32 s / 36.58 tokens per second 60.04.691.735 I slot print_timing: id 0 | task 6918 | prompt processing, n_tokens = 119, progress = 1.00, t = 5.42 s / 21.94 tokens per second 60.05.122.894 I slot print_timing: id 1 | task 6919 | prompt processing, n_tokens = 115, progress = 1.00, t = 5.41 s / 21.25 tokens per second 60.05.127.395 I slot print_timing: id 2 | task 6912 | prompt processing, n_tokens = 956, progress = 1.00, t = 29.17 s / 32.77 tokens per second 60.05.131.896 I slot print_timing: id 3 | task 6913 | prompt processing, n_tokens = 979, progress = 1.00, t = 29.17 s / 33.56 tokens per second 60.05.696.914 I slot print_timing: id 0 | task 6918 | prompt eval time = 6221.24 ms / 123 tokens ( 50.58 ms per token, 19.77 tokens per second) 60.05.696.919 I slot print_timing: id 0 | task 6918 | eval time = 207.00 ms / 2 tokens ( 207.00 ms per token, 4.83 tokens per second) 60.05.696.920 I slot print_timing: id 0 | task 6918 | total time = 6428.24 ms / 125 tokens 60.05.696.921 I slot print_timing: id 0 | task 6918 | graphs reused = 5357 60.05.696.921 I slot print_timing: id 0 | task 6918 | graph reallocs = 0 / 0 (same size) / (changed size) 60.05.696.967 I slot release: id 0 | task 6918 | stop processing: n_tokens = 977, truncated = 0 60.05.697.117 I slot print_timing: id 1 | task 6919 | prompt eval time = 6210.90 ms / 119 tokens ( 52.19 ms per token, 19.16 tokens per second) 60.05.697.121 I slot print_timing: id 1 | task 6919 | eval time = 207.06 ms / 2 tokens ( 207.06 ms per token, 4.83 tokens per second) 60.05.697.121 I slot print_timing: id 1 | task 6919 | total time = 6417.95 ms / 121 tokens 60.05.697.122 I slot print_timing: id 1 | task 6919 | graphs reused = 5357 60.05.697.122 I slot print_timing: id 1 | task 6919 | graph reallocs = 0 / 0 (same size) / (changed size) 60.05.697.146 I slot release: id 1 | task 6919 | stop processing: n_tokens = 973, truncated = 0 60.05.697.316 I slot print_timing: id 2 | task 6912 | prompt eval time = 29972.29 ms / 960 tokens ( 31.22 ms per token, 32.03 tokens per second) 60.05.697.317 I slot print_timing: id 2 | task 6912 | eval time = 207.09 ms / 2 tokens ( 207.09 ms per token, 4.83 tokens per second) 60.05.697.318 I slot print_timing: id 2 | task 6912 | total time = 30179.38 ms / 962 tokens 60.05.697.318 I slot print_timing: id 2 | task 6912 | graphs reused = 5357 60.05.697.318 I slot print_timing: id 2 | task 6912 | graph reallocs = 0 / 0 (same size) / (changed size) 60.05.697.349 I slot release: id 2 | task 6912 | stop processing: n_tokens = 961, truncated = 0 60.05.697.532 I slot print_timing: id 3 | task 6913 | prompt eval time = 29972.61 ms / 983 tokens ( 30.49 ms per token, 32.80 tokens per second) 60.05.697.533 I slot print_timing: id 3 | task 6913 | eval time = 206.88 ms / 2 tokens ( 206.88 ms per token, 4.83 tokens per second) 60.05.697.533 I slot print_timing: id 3 | task 6913 | total time = 30179.50 ms / 985 tokens 60.05.697.534 I slot print_timing: id 3 | task 6913 | graphs reused = 5357 60.05.697.534 I slot print_timing: id 3 | task 6913 | graph reallocs = 0 / 0 (same size) / (changed size) 60.05.697.555 I slot release: id 3 | task 6913 | stop processing: n_tokens = 984, truncated = 0 60.05.707.988 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 977, t_last = 90394513641 60.05.708.043 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 874.802 MiB) 60.05.727.252 I slot launch_slot_: id 0 | task 6923 | processing task, is_child = 0 60.05.727.303 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 884.118 MiB) 60.05.746.078 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 867.612 MiB) 60.05.764.823 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 872.677 MiB) 60.05.784.315 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 973, t_last = 90394513820 60.05.784.422 I slot launch_slot_: id 1 | task 6924 | processing task, is_child = 0 60.05.784.513 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 961, t_last = 90394514023 60.05.784.576 I slot launch_slot_: id 2 | task 6925 | processing task, is_child = 0 60.05.784.630 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 984, t_last = 90394514229 60.05.784.698 I slot launch_slot_: id 3 | task 6926 | processing task, is_child = 0 60.19.188.575 I slot print_timing: id 0 | task 6923 | prompt processing, n_tokens = 166, progress = 0.20, t = 13.40 s / 12.38 tokens per second 60.19.974.413 I slot print_timing: id 1 | task 6924 | prompt processing, n_tokens = 352, progress = 0.22, t = 13.40 s / 26.26 tokens per second 60.19.978.960 I slot print_timing: id 2 | task 6925 | prompt processing, n_tokens = 352, progress = 0.22, t = 13.40 s / 26.26 tokens per second 60.19.983.738 I slot print_timing: id 3 | task 6926 | prompt processing, n_tokens = 352, progress = 0.22, t = 13.40 s / 26.26 tokens per second 60.26.502.594 I slot print_timing: id 0 | task 6923 | prompt processing, n_tokens = 309, progress = 0.37, t = 20.72 s / 14.91 tokens per second 60.28.029.141 I slot print_timing: id 1 | task 6924 | prompt processing, n_tokens = 533, progress = 0.33, t = 20.72 s / 25.73 tokens per second 60.28.029.168 I slot print_timing: id 2 | task 6925 | prompt processing, n_tokens = 533, progress = 0.34, t = 20.72 s / 25.73 tokens per second 60.28.029.188 I slot print_timing: id 3 | task 6926 | prompt processing, n_tokens = 533, progress = 0.33, t = 20.72 s / 25.73 tokens per second 60.51.037.261 I slot print_timing: id 0 | task 6923 | prompt processing, n_tokens = 706, progress = 0.86, t = 45.25 s / 15.60 tokens per second 60.51.806.701 I slot print_timing: id 1 | task 6924 | prompt processing, n_tokens = 1113, progress = 0.68, t = 45.25 s / 24.60 tokens per second 60.51.811.508 I slot print_timing: id 2 | task 6925 | prompt processing, n_tokens = 1071, progress = 0.67, t = 45.25 s / 23.67 tokens per second 60.51.815.950 I slot print_timing: id 3 | task 6926 | prompt processing, n_tokens = 1066, progress = 0.66, t = 45.25 s / 23.56 tokens per second 61.00.300.043 I slot print_timing: id 0 | task 6923 | prompt processing, n_tokens = 821, progress = 1.00, t = 54.52 s / 15.06 tokens per second 61.01.074.064 I slot print_timing: id 1 | task 6924 | prompt processing, n_tokens = 1374, progress = 0.84, t = 54.52 s / 25.20 tokens per second 61.01.078.544 I slot print_timing: id 2 | task 6925 | prompt processing, n_tokens = 1374, progress = 0.87, t = 54.52 s / 25.20 tokens per second 61.01.082.979 I slot print_timing: id 3 | task 6926 | prompt processing, n_tokens = 1099, progress = 0.68, t = 54.52 s / 20.16 tokens per second 61.10.751.699 I slot print_timing: id 1 | task 6924 | prompt processing, n_tokens = 1625, progress = 1.00, t = 64.97 s / 25.01 tokens per second 61.10.759.137 I slot print_timing: id 2 | task 6925 | prompt processing, n_tokens = 1583, progress = 1.00, t = 64.97 s / 24.37 tokens per second 61.10.763.789 I slot print_timing: id 3 | task 6926 | prompt processing, n_tokens = 1374, progress = 0.85, t = 64.97 s / 21.15 tokens per second 61.14.196.123 I slot print_timing: id 0 | task 6923 | prompt eval time = 64966.98 ms / 825 tokens ( 78.75 ms per token, 12.70 tokens per second) 61.14.196.126 I slot print_timing: id 0 | task 6923 | eval time = 3444.43 ms / 2 tokens ( 3444.43 ms per token, 0.29 tokens per second) 61.14.196.127 I slot print_timing: id 0 | task 6923 | total time = 68411.41 ms / 827 tokens 61.14.196.127 I slot print_timing: id 0 | task 6923 | graphs reused = 5358 61.14.196.127 I slot print_timing: id 0 | task 6923 | graph reallocs = 0 / 0 (same size) / (changed size) 61.14.196.168 I slot release: id 0 | task 6923 | stop processing: n_tokens = 826, truncated = 0 61.14.196.674 I slot print_timing: id 3 | task 6926 | prompt processing, n_tokens = 1611, progress = 1.00, t = 68.41 s / 23.55 tokens per second 61.14.569.439 I slot print_timing: id 1 | task 6924 | prompt eval time = 68411.63 ms / 1629 tokens ( 42.00 ms per token, 23.81 tokens per second) 61.14.569.441 I slot print_timing: id 1 | task 6924 | eval time = 373.02 ms / 2 tokens ( 373.02 ms per token, 2.68 tokens per second) 61.14.569.442 I slot print_timing: id 1 | task 6924 | total time = 68784.65 ms / 1631 tokens 61.14.569.442 I slot print_timing: id 1 | task 6924 | graphs reused = 5358 61.14.569.443 I slot print_timing: id 1 | task 6924 | graph reallocs = 0 / 0 (same size) / (changed size) 61.14.569.521 I slot release: id 1 | task 6924 | stop processing: n_tokens = 1630, truncated = 0 61.14.569.675 I slot print_timing: id 2 | task 6925 | prompt eval time = 68411.80 ms / 1587 tokens ( 43.11 ms per token, 23.20 tokens per second) 61.14.569.677 I slot print_timing: id 2 | task 6925 | eval time = 373.01 ms / 2 tokens ( 373.01 ms per token, 2.68 tokens per second) 61.14.569.678 I slot print_timing: id 2 | task 6925 | total time = 68784.81 ms / 1589 tokens 61.14.569.678 I slot print_timing: id 2 | task 6925 | graphs reused = 5358 61.14.569.678 I slot print_timing: id 2 | task 6925 | graph reallocs = 0 / 0 (same size) / (changed size) 61.14.569.719 I slot release: id 2 | task 6925 | stop processing: n_tokens = 1588, truncated = 0 61.14.569.920 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.861 (> 0.100 thold), f_keep = 0.860 61.14.569.974 I slot launch_slot_: id 1 | task 6934 | processing task, is_child = 0 61.14.570.029 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 870.551 MiB) 61.14.594.707 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 840.415 MiB) 61.14.614.740 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 826, t_last = 90463012842 61.14.614.843 I slot launch_slot_: id 0 | task 6935 | processing task, is_child = 0 61.14.614.916 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.816 (> 0.100 thold), f_keep = 0.883 61.14.614.937 I slot launch_slot_: id 2 | task 6936 | processing task, is_child = 0 61.23.180.121 I slot print_timing: id 3 | task 6926 | prompt eval time = 68784.98 ms / 1615 tokens ( 42.59 ms per token, 23.48 tokens per second) 61.23.180.124 I slot print_timing: id 3 | task 6926 | eval time = 8610.20 ms / 2 tokens ( 8610.20 ms per token, 0.12 tokens per second) 61.23.180.124 I slot print_timing: id 3 | task 6926 | total time = 77395.18 ms / 1617 tokens 61.23.180.125 I slot print_timing: id 3 | task 6926 | graphs reused = 5358 61.23.180.125 I slot print_timing: id 3 | task 6926 | graph reallocs = 0 / 0 (same size) / (changed size) 61.23.180.195 I slot release: id 3 | task 6926 | stop processing: n_tokens = 1616, truncated = 0 61.23.180.207 I slot print_timing: id 0 | task 6935 | prompt processing, n_tokens = 126, progress = 0.15, t = 8.57 s / 14.71 tokens per second 61.23.186.192 I slot print_timing: id 1 | task 6934 | prompt processing, n_tokens = 251, progress = 1.00, t = 8.56 s / 29.31 tokens per second 61.23.191.726 I slot print_timing: id 2 | task 6936 | prompt processing, n_tokens = 340, progress = 1.00, t = 8.56 s / 39.73 tokens per second 61.24.986.153 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1616, t_last = 90471996869 61.24.986.237 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 845.417 MiB) 61.25.010.339 I slot launch_slot_: id 3 | task 6939 | processing task, is_child = 0 61.25.010.351 I slot print_timing: id 0 | task 6935 | prompt processing, n_tokens = 245, progress = 0.29, t = 10.37 s / 23.62 tokens per second 61.27.811.108 I slot print_timing: id 1 | task 6934 | prompt eval time = 10370.95 ms / 255 tokens ( 40.67 ms per token, 24.59 tokens per second) 61.27.811.110 I slot print_timing: id 1 | task 6934 | eval time = 2825.12 ms / 2 tokens ( 2825.12 ms per token, 0.35 tokens per second) 61.27.811.111 I slot print_timing: id 1 | task 6934 | total time = 13196.07 ms / 257 tokens 61.27.811.111 I slot print_timing: id 1 | task 6934 | graphs reused = 5358 61.27.811.112 I slot print_timing: id 1 | task 6934 | graph reallocs = 0 / 0 (same size) / (changed size) 61.27.811.173 I slot release: id 1 | task 6934 | stop processing: n_tokens = 1630, truncated = 0 61.27.811.328 I slot print_timing: id 2 | task 6936 | prompt eval time = 10363.50 ms / 344 tokens ( 30.13 ms per token, 33.19 tokens per second) 61.27.811.331 I slot print_timing: id 2 | task 6936 | eval time = 2825.18 ms / 2 tokens ( 2825.18 ms per token, 0.35 tokens per second) 61.27.811.331 I slot print_timing: id 2 | task 6936 | total time = 13188.68 ms / 346 tokens 61.27.811.331 I slot print_timing: id 2 | task 6936 | graphs reused = 5358 61.27.811.332 I slot print_timing: id 2 | task 6936 | graph reallocs = 0 / 0 (same size) / (changed size) 61.27.811.411 I slot release: id 2 | task 6936 | stop processing: n_tokens = 1719, truncated = 0 61.27.811.422 I slot print_timing: id 0 | task 6935 | prompt processing, n_tokens = 322, progress = 0.38, t = 13.20 s / 24.40 tokens per second 61.32.509.682 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1630, t_last = 90476627848 61.32.509.782 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 853.044 MiB) 61.33.984.396 I slot launch_slot_: id 1 | task 6942 | processing task, is_child = 0 61.33.984.482 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 809.278 MiB) 61.34.007.946 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1719, t_last = 90476628086 61.34.008.074 I slot launch_slot_: id 2 | task 6943 | processing task, is_child = 0 61.34.008.083 I slot print_timing: id 0 | task 6935 | prompt processing, n_tokens = 725, progress = 0.87, t = 17.89 s / 40.51 tokens per second 61.34.012.709 I slot print_timing: id 3 | task 6939 | prompt processing, n_tokens = 245, progress = 0.28, t = 7.50 s / 32.67 tokens per second 61.39.019.998 I slot print_timing: id 0 | task 6935 | prompt processing, n_tokens = 834, progress = 1.00, t = 24.41 s / 34.17 tokens per second 61.40.177.184 I slot print_timing: id 1 | task 6942 | prompt processing, n_tokens = 149, progress = 0.18, t = 5.01 s / 29.76 tokens per second 61.40.181.619 I slot print_timing: id 2 | task 6943 | prompt processing, n_tokens = 149, progress = 0.17, t = 5.01 s / 29.76 tokens per second 61.40.186.068 I slot print_timing: id 3 | task 6939 | prompt processing, n_tokens = 349, progress = 0.40, t = 14.01 s / 24.91 tokens per second 61.47.728.760 I slot print_timing: id 1 | task 6942 | prompt processing, n_tokens = 277, progress = 0.33, t = 13.72 s / 20.20 tokens per second 61.47.728.773 I slot print_timing: id 2 | task 6943 | prompt processing, n_tokens = 277, progress = 0.32, t = 13.72 s / 20.20 tokens per second 61.47.728.780 I slot print_timing: id 3 | task 6939 | prompt processing, n_tokens = 725, progress = 0.84, t = 22.72 s / 31.91 tokens per second 61.51.687.985 I slot print_timing: id 0 | task 6935 | prompt eval time = 33113.79 ms / 838 tokens ( 39.52 ms per token, 25.31 tokens per second) 61.51.687.988 I slot print_timing: id 0 | task 6935 | eval time = 3959.23 ms / 2 tokens ( 3959.23 ms per token, 0.25 tokens per second) 61.51.687.989 I slot print_timing: id 0 | task 6935 | total time = 37073.02 ms / 840 tokens 61.51.687.989 I slot print_timing: id 0 | task 6935 | graphs reused = 5358 61.51.687.989 I slot print_timing: id 0 | task 6935 | graph reallocs = 0 / 0 (same size) / (changed size) 61.51.688.028 I slot release: id 0 | task 6935 | stop processing: n_tokens = 839, truncated = 0 61.51.688.040 I slot print_timing: id 1 | task 6942 | prompt processing, n_tokens = 326, progress = 0.39, t = 17.68 s / 18.44 tokens per second 61.51.693.598 I slot print_timing: id 2 | task 6943 | prompt processing, n_tokens = 343, progress = 0.40, t = 17.68 s / 19.41 tokens per second 61.51.698.325 I slot print_timing: id 3 | task 6939 | prompt processing, n_tokens = 861, progress = 1.00, t = 26.68 s / 32.27 tokens per second 62.01.012.463 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 839, t_last = 90500504702 62.01.012.518 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 809.216 MiB) 62.01.033.574 I slot launch_slot_: id 0 | task 6948 | processing task, is_child = 0 62.01.033.648 I slot print_timing: id 1 | task 6942 | prompt processing, n_tokens = 716, progress = 0.85, t = 27.00 s / 26.52 tokens per second 62.01.038.079 I slot print_timing: id 2 | task 6943 | prompt processing, n_tokens = 716, progress = 0.83, t = 27.00 s / 26.52 tokens per second 62.06.312.351 I slot print_timing: id 3 | task 6939 | prompt eval time = 36002.09 ms / 865 tokens ( 41.62 ms per token, 24.03 tokens per second) 62.06.312.354 I slot print_timing: id 3 | task 6939 | eval time = 5299.89 ms / 2 tokens ( 5299.89 ms per token, 0.19 tokens per second) 62.06.312.355 I slot print_timing: id 3 | task 6939 | total time = 41301.98 ms / 867 tokens 62.06.312.355 I slot print_timing: id 3 | task 6939 | graphs reused = 5358 62.06.312.355 I slot print_timing: id 3 | task 6939 | graph reallocs = 0 / 0 (same size) / (changed size) 62.06.312.395 I slot release: id 3 | task 6939 | stop processing: n_tokens = 866, truncated = 0 62.06.312.407 I slot print_timing: id 0 | task 6948 | prompt processing, n_tokens = 149, progress = 0.17, t = 5.28 s / 28.23 tokens per second 62.06.318.984 I slot print_timing: id 1 | task 6942 | prompt processing, n_tokens = 838, progress = 1.00, t = 32.30 s / 25.94 tokens per second 62.06.323.514 I slot print_timing: id 2 | task 6943 | prompt processing, n_tokens = 855, progress = 1.00, t = 32.30 s / 26.47 tokens per second 62.08.124.288 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 866, t_last = 90515129069 62.08.124.348 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 808.966 MiB) 62.08.144.954 I slot launch_slot_: id 3 | task 6951 | processing task, is_child = 0 62.08.144.964 I slot print_timing: id 0 | task 6948 | prompt processing, n_tokens = 277, progress = 0.31, t = 7.09 s / 39.07 tokens per second 62.10.956.532 I slot print_timing: id 1 | task 6942 | prompt eval time = 34111.63 ms / 842 tokens ( 40.51 ms per token, 24.68 tokens per second) 62.10.956.534 I slot print_timing: id 1 | task 6942 | eval time = 2832.41 ms / 2 tokens ( 2832.41 ms per token, 0.35 tokens per second) 62.10.956.535 I slot print_timing: id 1 | task 6942 | total time = 36944.05 ms / 844 tokens 62.10.956.535 I slot print_timing: id 1 | task 6942 | graphs reused = 5358 62.10.956.536 I slot print_timing: id 1 | task 6942 | graph reallocs = 0 / 0 (same size) / (changed size) 62.10.956.574 I slot release: id 1 | task 6942 | stop processing: n_tokens = 843, truncated = 0 62.10.956.737 I slot print_timing: id 2 | task 6943 | prompt eval time = 34111.68 ms / 859 tokens ( 39.71 ms per token, 25.18 tokens per second) 62.10.956.742 I slot print_timing: id 2 | task 6943 | eval time = 2832.45 ms / 2 tokens ( 2832.45 ms per token, 0.35 tokens per second) 62.10.956.743 I slot print_timing: id 2 | task 6943 | total time = 36944.14 ms / 861 tokens 62.10.956.743 I slot print_timing: id 2 | task 6943 | graphs reused = 5358 62.10.956.743 I slot print_timing: id 2 | task 6943 | graph reallocs = 0 / 0 (same size) / (changed size) 62.10.956.769 I slot release: id 2 | task 6943 | stop processing: n_tokens = 860, truncated = 0 62.10.956.777 I slot print_timing: id 0 | task 6948 | prompt processing, n_tokens = 370, progress = 0.42, t = 9.92 s / 37.29 tokens per second 62.14.960.657 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 843, t_last = 90519773248 62.14.960.715 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 808.216 MiB) 62.16.784.266 I slot launch_slot_: id 1 | task 6954 | processing task, is_child = 0 62.16.784.322 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 809.654 MiB) 62.16.802.761 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 860, t_last = 90519773443 62.16.802.862 I slot launch_slot_: id 2 | task 6955 | processing task, is_child = 0 62.16.802.870 I slot print_timing: id 0 | task 6948 | prompt processing, n_tokens = 716, progress = 0.81, t = 13.93 s / 51.41 tokens per second 62.16.807.417 I slot print_timing: id 3 | task 6951 | prompt processing, n_tokens = 260, progress = 0.33, t = 6.82 s / 38.15 tokens per second 62.21.898.507 I slot print_timing: id 0 | task 6948 | prompt processing, n_tokens = 882, progress = 1.00, t = 20.86 s / 42.27 tokens per second 62.22.176.607 I slot print_timing: id 1 | task 6954 | prompt processing, n_tokens = 113, progress = 0.16, t = 5.09 s / 22.20 tokens per second 62.22.181.425 I slot print_timing: id 2 | task 6955 | prompt processing, n_tokens = 125, progress = 0.17, t = 5.09 s / 24.55 tokens per second 62.22.185.841 I slot print_timing: id 3 | task 6951 | prompt processing, n_tokens = 264, progress = 0.34, t = 13.75 s / 19.20 tokens per second 62.28.740.529 I slot print_timing: id 1 | task 6954 | prompt processing, n_tokens = 175, progress = 0.25, t = 11.93 s / 14.67 tokens per second 62.28.745.812 I slot print_timing: id 2 | task 6955 | prompt processing, n_tokens = 233, progress = 0.31, t = 11.93 s / 19.53 tokens per second 62.28.750.549 I slot print_timing: id 3 | task 6951 | prompt processing, n_tokens = 628, progress = 0.81, t = 20.60 s / 30.49 tokens per second 62.39.875.697 I slot print_timing: id 0 | task 6948 | prompt eval time = 27706.93 ms / 886 tokens ( 31.27 ms per token, 31.98 tokens per second) 62.39.875.700 I slot print_timing: id 0 | task 6948 | eval time = 11135.18 ms / 2 tokens (11135.18 ms per token, 0.09 tokens per second) 62.39.875.700 I slot print_timing: id 0 | task 6948 | total time = 38842.11 ms / 888 tokens 62.39.875.701 I slot print_timing: id 0 | task 6948 | graphs reused = 5358 62.39.875.701 I slot print_timing: id 0 | task 6948 | graph reallocs = 0 / 0 (same size) / (changed size) 62.39.875.746 I slot release: id 0 | task 6948 | stop processing: n_tokens = 887, truncated = 0 62.39.875.760 I slot print_timing: id 1 | task 6954 | prompt processing, n_tokens = 571, progress = 0.83, t = 23.07 s / 24.75 tokens per second 62.39.880.902 I slot print_timing: id 2 | task 6955 | prompt processing, n_tokens = 628, progress = 0.84, t = 23.07 s / 27.22 tokens per second 62.39.886.118 I slot print_timing: id 3 | task 6951 | prompt processing, n_tokens = 776, progress = 0.99, t = 31.73 s / 24.46 tokens per second 62.42.854.595 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 887, t_last = 90548692420 62.42.854.651 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 799.775 MiB) 62.42.876.112 I slot launch_slot_: id 0 | task 6960 | processing task, is_child = 0 62.42.876.196 I slot print_timing: id 1 | task 6954 | prompt processing, n_tokens = 687, progress = 0.99, t = 26.05 s / 26.38 tokens per second 62.42.880.881 I slot print_timing: id 2 | task 6955 | prompt processing, n_tokens = 745, progress = 0.99, t = 26.05 s / 28.60 tokens per second 62.44.764.952 I slot print_timing: id 3 | task 6951 | prompt eval time = 34709.61 ms / 780 tokens ( 44.50 ms per token, 22.47 tokens per second) 62.44.764.955 I slot print_timing: id 3 | task 6951 | eval time = 1910.36 ms / 2 tokens ( 1910.36 ms per token, 0.52 tokens per second) 62.44.764.956 I slot print_timing: id 3 | task 6951 | total time = 36619.97 ms / 782 tokens 62.44.764.956 I slot print_timing: id 3 | task 6951 | graphs reused = 5358 62.44.764.957 I slot print_timing: id 3 | task 6951 | graph reallocs = 0 / 0 (same size) / (changed size) 62.44.765.006 I slot release: id 3 | task 6951 | stop processing: n_tokens = 781, truncated = 0 62.46.088.053 I slot print_timing: id 1 | task 6954 | prompt eval time = 27957.32 ms / 691 tokens ( 40.46 ms per token, 24.72 tokens per second) 62.46.088.056 I slot print_timing: id 1 | task 6954 | eval time = 1323.44 ms / 2 tokens ( 1323.44 ms per token, 0.76 tokens per second) 62.46.088.056 I slot print_timing: id 1 | task 6954 | total time = 29280.76 ms / 693 tokens 62.46.088.057 I slot print_timing: id 1 | task 6954 | graphs reused = 5358 62.46.088.057 I slot print_timing: id 1 | task 6954 | graph reallocs = 0 / 0 (same size) / (changed size) 62.46.088.109 I slot release: id 1 | task 6954 | stop processing: n_tokens = 692, truncated = 0 62.46.088.259 I slot print_timing: id 2 | task 6955 | prompt eval time = 27957.44 ms / 749 tokens ( 37.33 ms per token, 26.79 tokens per second) 62.46.088.261 I slot print_timing: id 2 | task 6955 | eval time = 1323.46 ms / 2 tokens ( 1323.46 ms per token, 0.76 tokens per second) 62.46.088.261 I slot print_timing: id 2 | task 6955 | total time = 29280.90 ms / 751 tokens 62.46.088.261 I slot print_timing: id 2 | task 6955 | graphs reused = 5358 62.46.088.262 I slot print_timing: id 2 | task 6955 | graph reallocs = 0 / 0 (same size) / (changed size) 62.46.088.291 I slot release: id 2 | task 6955 | stop processing: n_tokens = 750, truncated = 0 62.46.088.296 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.883 (> 0.100 thold), f_keep = 0.866 62.46.088.358 I slot launch_slot_: id 1 | task 6963 | processing task, is_child = 0 62.46.088.407 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 847.417 MiB) 62.46.142.545 I slot print_timing: id 0 | task 6960 | prompt processing, n_tokens = 196, progress = 0.28, t = 3.21 s / 61.03 tokens per second 62.48.735.694 I slot print_timing: id 0 | task 6960 | prompt processing, n_tokens = 571, progress = 0.80, t = 5.86 s / 97.45 tokens per second 62.54.031.404 I slot print_timing: id 0 | task 6960 | prompt processing, n_tokens = 708, progress = 0.99, t = 11.16 s / 63.47 tokens per second 62.54.321.675 I slot print_timing: id 1 | task 6963 | prompt eval time = 7875.40 ms / 107 tokens ( 73.60 ms per token, 13.59 tokens per second) 62.54.321.681 I slot print_timing: id 1 | task 6963 | eval time = 290.28 ms / 2 tokens ( 290.28 ms per token, 3.44 tokens per second) 62.54.321.681 I slot print_timing: id 1 | task 6963 | total time = 8165.69 ms / 109 tokens 62.54.321.682 I slot print_timing: id 1 | task 6963 | graphs reused = 5358 62.54.321.682 I slot print_timing: id 1 | task 6963 | graph reallocs = 0 / 0 (same size) / (changed size) 62.54.321.715 I slot release: id 1 | task 6963 | stop processing: n_tokens = 679, truncated = 0 62.54.422.724 I slot print_timing: id 0 | task 6960 | prompt eval time = 11445.42 ms / 712 tokens ( 16.08 ms per token, 62.21 tokens per second) 62.54.422.725 I slot print_timing: id 0 | task 6960 | eval time = 101.18 ms / 2 tokens ( 101.18 ms per token, 9.88 tokens per second) 62.54.422.726 I slot print_timing: id 0 | task 6960 | total time = 11546.59 ms / 714 tokens 62.54.422.726 I slot print_timing: id 0 | task 6960 | graphs reused = 5358 62.54.422.727 I slot print_timing: id 0 | task 6960 | graph reallocs = 0 / 0 (same size) / (changed size) 62.54.422.753 I slot release: id 0 | task 6960 | stop processing: n_tokens = 713, truncated = 0 62.57.318.553 I srv operator(): operator(): cleaning up before exit...