0.00.139.517 I cmn  common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg)
0.00.251.982 I srv    load_model: loading model '<VAULT>/models/gguf/Mistral-Large-3/UD-IQ1_S/Mistral-Large-3-675B-Instruct-2512-UD-IQ1_S-00001-of-00004.gguf'
0.00.744.979 W llama_model_loader: tensor overrides to CPU are used with mmap enabled - consider using --no-mmap for better performance
4.04.906.271 W llama_context: setting new yarn_attn_factor = 1.0000 (mscale == 1.0, mscale_all_dim = 1.0)
4.06.456.616 I srv    load_model: initializing, n_slots = 1, n_ctx_slot = 32768, kv_unified = 'false'
4.06.465.102 I srv  llama_server: model loaded
4.06.465.109 I srv  llama_server: listening on http://<BRIDGE-IP>:8104
4.14.689.001 I slot get_availabl: id  0 | task -1 | selected slot by LRU, t_last = -1
4.14.689.020 I slot launch_slot_: id  0 | task 0 | processing task, is_child = 0
6.49.521.033 I slot print_timing: id  0 | task 0 | prompt eval time =  149099.07 ms /   547 tokens (  272.58 ms per token,     3.67 tokens per second)
6.49.521.036 I slot print_timing: id  0 | task 0 |        eval time =    5732.09 ms /    36 tokens (  159.22 ms per token,     6.28 tokens per second)
6.49.521.037 I slot print_timing: id  0 | task 0 |       total time =  154831.16 ms /   583 tokens
6.49.521.037 I slot print_timing: id  0 | task 0 |    graphs reused =          0
6.49.522.700 I slot      release: id  0 | task 0 | stop processing: n_tokens = 582, truncated = 0
7.20.391.675 I slot get_availabl: id  0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.941 (> 0.100 thold), f_keep = 0.924
7.20.392.608 I slot launch_slot_: id  0 | task 37 | processing task, is_child = 0
7.57.239.419 I slot print_timing: id  0 | task 37 | n_decoded =    100, tg =   5.35 t/s, tg_3s =   5.35 t/s
8.00.445.367 I slot print_timing: id  0 | task 37 | n_decoded =    120, tg =   5.48 t/s, tg_3s =   6.24 t/s
8.03.460.567 I slot print_timing: id  0 | task 37 | n_decoded =    139, tg =   5.58 t/s, tg_3s =   6.30 t/s
8.06.586.466 I slot print_timing: id  0 | task 37 | n_decoded =    159, tg =   5.67 t/s, tg_3s =   6.40 t/s
8.09.641.949 I slot print_timing: id  0 | task 37 | n_decoded =    179, tg =   5.76 t/s, tg_3s =   6.55 t/s
8.12.768.440 I slot print_timing: id  0 | task 37 | n_decoded =    199, tg =   5.82 t/s, tg_3s =   6.40 t/s
8.15.802.869 I slot print_timing: id  0 | task 37 | n_decoded =    219, tg =   5.88 t/s, tg_3s =   6.59 t/s
8.18.837.255 I slot print_timing: id  0 | task 37 | n_decoded =    239, tg =   5.93 t/s, tg_3s =   6.59 t/s
8.21.844.167 I slot print_timing: id  0 | task 37 | n_decoded =    259, tg =   5.98 t/s, tg_3s =   6.65 t/s
8.22.002.500 I slot print_timing: id  0 | task 37 | prompt eval time =   18164.93 ms /    34 tokens (  534.26 ms per token,     1.87 tokens per second)
8.22.002.503 I slot print_timing: id  0 | task 37 |        eval time =   43444.95 ms /   260 tokens (  167.10 ms per token,     5.98 tokens per second)
8.22.002.503 I slot print_timing: id  0 | task 37 |       total time =   61609.87 ms /   294 tokens
8.22.002.504 I slot print_timing: id  0 | task 37 |    graphs reused =          0
8.22.003.466 I slot      release: id  0 | task 37 | stop processing: n_tokens = 831, truncated = 0
8.48.135.289 I srv    operator(): operator(): cleaning up before exit...