0.00.168.650 I cmn  common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg)
0.00.168.874 W srv  llama_server: -----------------
0.00.168.875 W srv  llama_server: CORS is set to allow all origins ('*') and no API key is set
0.00.168.875 W srv  llama_server: this can be a security risk (cross-origin attacks)
0.00.168.875 W srv  llama_server: more info: https://github.com/ggml-org/llama.cpp/pull/25655
0.00.168.875 W srv  llama_server: -----------------
0.00.170.229 I srv    load_model: loading model '<REDACTED_PATH>'
0.01.032.618 W llama_model_loader: tensor overrides to CPU are used with mmap enabled - consider using --load-mode none for better performance
1.31.212.230 I cmn          init: llama threadpool init, n_threads = 24
1.34.564.926 I srv    load_model: initializing, n_slots = 1, n_ctx_slot = 131072, kv_unified = 'false'
1.34.590.473 W srv          init: chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve)
1.34.590.523 I srv  llama_server: model loaded
1.34.590.526 I srv  llama_server: listening on http://127.0.0.1:8137
1.36.504.936 I slot get_availabl: id  0 | task -1 | selected slot by LRU, t_last = -1
1.36.505.031 I slot launch_slot_: id  0 | task 0 | processing task, is_child = 0
1.41.212.637 I slot print_timing: id  0 | task 0 | prompt processing, n_tokens =      9, progress = 0.28, t =   4.71 s / 1.91 tokens per second
1.52.424.835 I slot print_timing: id  0 | task 0 | prompt processing, n_tokens =     28, progress = 0.88, t =  15.92 s / 1.76 tokens per second
2.14.062.222 I slot print_timing: id  0 | task 0 | prompt eval time =   17132.80 ms /    32 tokens (  535.40 ms per token,     1.87 tokens per second)
2.14.062.226 I slot print_timing: id  0 | task 0 |        eval time =   20424.35 ms /    71 tokens (  291.78 ms per token,     3.43 tokens per second)
2.14.062.226 I slot print_timing: id  0 | task 0 |       total time =   37557.15 ms /   103 tokens
2.14.062.231 I slot print_timing: id  0 | task 0 |    graphs reused =          0
2.14.062.474 I slot      release: id  0 | task 0 | stop processing: n_tokens = 102, truncated = 0
2.14.076.118 I slot get_availabl: id  0 | task -1 | selected slot by LRU, t_last = 139295704053
2.14.113.631 I slot launch_slot_: id  0 | task 74 | processing task, is_child = 0
2.26.925.912 I slot print_timing: id  0 | task 74 | prompt processing, n_tokens =     56, progress = 0.77, t =  12.81 s / 4.37 tokens per second
2.28.594.983 I slot print_timing: id  0 | task 74 | prompt processing, n_tokens =     69, progress = 0.95, t =  14.48 s / 4.76 tokens per second
2.32.522.868 I slot print_timing: id  0 | task 74 | prompt eval time =   14993.52 ms /    73 tokens (  205.39 ms per token,     4.87 tokens per second)
2.32.522.873 I slot print_timing: id  0 | task 74 |        eval time =    3414.75 ms /    18 tokens (  200.87 ms per token,     4.98 tokens per second)
2.32.522.895 I slot print_timing: id  0 | task 74 |       total time =   18408.27 ms /    91 tokens
2.32.522.898 I slot print_timing: id  0 | task 74 |    graphs reused =          0
2.32.524.314 I slot      release: id  0 | task 74 | stop processing: n_tokens = 90, truncated = 0
2.32.547.460 I slot get_availabl: id  0 | task -1 | selected slot by LRU, t_last = 139314165892
2.32.614.436 I slot launch_slot_: id  0 | task 95 | processing task, is_child = 0
3.56.189.597 I slot print_timing: id  0 | task 95 | prompt processing, n_tokens =   1434, progress = 0.74, t =  83.57 s / 17.16 tokens per second
4.08.969.640 I slot print_timing: id  0 | task 95 | prompt processing, n_tokens =   1946, progress = 1.00, t =  96.36 s / 20.20 tokens per second
4.12.259.951 I slot print_timing: id  0 | task 95 | prompt eval time =   97278.22 ms /  1950 tokens (   49.89 ms per token,    20.05 tokens per second)
4.12.259.955 I slot print_timing: id  0 | task 95 |        eval time =    2367.23 ms /    12 tokens (  215.20 ms per token,     4.65 tokens per second)
4.12.259.955 I slot print_timing: id  0 | task 95 |       total time =   99645.45 ms /  1962 tokens
4.12.259.956 I slot print_timing: id  0 | task 95 |    graphs reused =          0
4.12.261.623 I slot      release: id  0 | task 95 | stop processing: n_tokens = 1961, truncated = 0
4.12.308.375 I srv    operator(): operator(): cleaning up before exit...