le prompt “hello”.

0.15.581.681 I srv          init: init: chat template, thinking = 1
0.15.581.967 I srv  llama_server: model loaded
0.15.581.973 I srv  llama_server: server is listening on http://0.0.0.0:8012
0.15.581.981 I srv  update_slots: all slots are idle
0.27.297.594 I srv  params_from_: Chat format: peg-gemma4
0.27.300.952 I slot get_availabl: id  3 | task -1 | selected slot by LRU, t_last = -1
0.27.300.957 I srv  get_availabl: updating prompt cache
0.27.300.966 I srv          load:  - looking for better prompt, base f_keep = -1.000, sim = 0.000
0.27.300.971 I srv        update:  - cache state: 0 prompts, 0.000 MiB (limits: 8192.000 MiB, 262144 tokens, 8589934592 est)
0.27.300.972 I srv  get_availabl: prompt cache update took 0.01 ms
0.27.301.028 I slot launch_slot_: id  3 | task 0 | processing task, is_child = 0
0.27.406.740 I srv  params_from_: Chat format: peg-gemma4
0.31.470.682 I slot get_availabl: id  2 | task -1 | selected slot by LRU, t_last = -1
0.31.470.685 I srv  get_availabl: updating prompt cache
0.31.470.689 I srv          load:  - looking for better prompt, base f_keep = -1.000, sim = 0.000
0.31.470.692 I srv        update:  - cache state: 0 prompts, 0.000 MiB (limits: 8192.000 MiB, 262144 tokens, 8589934592 est)
0.31.470.692 I srv  get_availabl: prompt cache update took 0.01 ms
0.31.480.325 I slot launch_slot_: id  2 | task 2 | processing task, is_child = 0
0.48.111.290 I slot print_timing: id  2 | task 2 | prompt processing, n_tokens =   2048, progress = 0.27, t =  16.63 s / 123.14 tokens per second
1.04.164.694 I slot print_timing: id  2 | task 2 | prompt processing, n_tokens =   4096, progress = 0.54, t =  32.68 s / 125.32 tokens per second
1.20.627.773 I slot print_timing: id  2 | task 2 | prompt processing, n_tokens =   6144, progress = 0.81, t =  49.15 s / 125.01 tokens per second
1.20.627.950 I slot print_timing: id  3 | task 0 | prompt processing, n_tokens =    346, progress = 0.40, t =  53.33 s / 6.49 tokens per second
1.31.552.764 I slot print_timing: id  2 | task 2 | prompt processing, n_tokens =   7034, progress = 0.93, t =  60.07 s / 117.09 tokens per second
1.31.552.931 I slot print_timing: id  3 | task 0 | prompt processing, n_tokens =    546, progress = 0.63, t =  64.25 s / 8.50 tokens per second
1.31.639.619 I slot create_check: id  3 | task 0 | created context checkpoint 1 of 32 (pos_min = 0, pos_max = 545, n_tokens = 546, size = 106.647 MiB)
1.35.810.635 I slot print_timing: id  2 | task 2 | prompt processing, n_tokens =   7234, progress = 0.96, t =  64.33 s / 112.45 tokens per second
1.36.313.785 I slot create_check: id  2 | task 2 | created context checkpoint 1 of 32 (pos_min = 3484, pos_max = 7233, n_tokens = 7234, size = 732.465 MiB)
1.36.313.791 I slot print_timing: id  3 | task 0 | prompt processing, n_tokens =    858, progress = 1.00, t =  69.01 s / 12.43 tokens per second
1.36.432.948 I slot create_check: id  3 | task 0 | created context checkpoint 2 of 32 (pos_min = 0, pos_max = 857, n_tokens = 858, size = 167.589 MiB)
1.40.181.720 I slot print_timing: id  2 | task 2 | prompt processing, n_tokens =   7546, progress = 1.00, t =  68.70 s / 109.84 tokens per second
1.40.690.306 I slot create_check: id  2 | task 2 | created context checkpoint 2 of 32 (pos_min = 3800, pos_max = 7545, n_tokens = 7546, size = 731.684 MiB)
1.40.889.823 I reasoning-budget: activated, budget=2147483647 tokens
1.49.385.767 I reasoning-budget: deactivated (natural end)
1.49.386.539 I slot print_timing: id  3 | task 0 | n_decoded =    100, tg =  10.86 t/s
1.49.476.807 I slot print_timing: id  2 | task 2 | n_decoded =    100, tg =  11.56 t/s
1.50.323.353 I slot print_timing: id  2 | task 2 | prompt eval time =   69344.18 ms /  7550 tokens (    9.18 ms per token,   108.88 tokens per second)
1.50.323.360 I slot print_timing: id  2 | task 2 |        eval time =    9498.81 ms /   109 tokens (   87.15 ms per token,    11.48 tokens per second)
1.50.323.361 I slot print_timing: id  2 | task 2 |       total time =   78842.98 ms /  7659 tokens
1.50.323.367 I slot print_timing: id  2 | task 2 |    graphs reused =        107
1.50.324.599 I slot      release: id  2 | task 2 | stop processing: n_tokens = 7658, truncated = 0
1.52.425.033 I slot print_timing: id  3 | task 0 | n_decoded =    152, tg =  12.41 t/s
1.55.456.041 I slot print_timing: id  3 | task 0 | n_decoded =    216, tg =  14.14 t/s
1.58.479.230 I slot print_timing: id  3 | task 0 | n_decoded =    279, tg =  15.25 t/s
2.01.502.693 I slot print_timing: id  3 | task 0 | n_decoded =    344, tg =  16.13 t/s
2.04.511.987 I slot print_timing: id  3 | task 0 | n_decoded =    404, tg =  16.60 t/s
2.07.519.350 I slot print_timing: id  3 | task 0 | n_decoded =    464, tg =  16.97 t/s
2.10.526.448 I slot print_timing: id  3 | task 0 | n_decoded =    521, tg =  17.17 t/s
2.12.137.202 I slot print_timing: id  3 | task 0 | prompt eval time =   72880.63 ms /   862 tokens (   84.55 ms per token,    11.83 tokens per second)
2.12.137.205 I slot print_timing: id  3 | task 0 |        eval time =   31955.50 ms /   555 tokens (   57.58 ms per token,    17.37 tokens per second)
2.12.137.206 I slot print_timing: id  3 | task 0 |       total time =  104836.13 ms /  1417 tokens
2.12.137.207 I slot print_timing: id  3 | task 0 |    graphs reused =        549
2.12.137.341 I slot      release: id  3 | task 0 | stop processing: n_tokens = 1416, truncated = 0
2.12.137.354 I srv  update_slots: all slots are idle

~/Code/bronx/AI_Coding/llama.cpp-86/build/bin/llama-server –host 0.0.0.0 –port 8012 -m ~/Data/AI_Models/gpt-oss-20b-UD-Q4_K_XL.gguf –jinja –no-mmap -c 0