| Les deux révisions précédentesRévision précédente | |
| informatique:ai_lm:model_bench [26/05/2026 10:14] – cyrille | informatique:ai_lm:model_bench [26/05/2026 10:15] (Version actuelle) – cyrille |
|---|
| |
| <code> | <code> |
| | 0.14.412.387 I srv init: init: chat template, thinking = 1 |
| | 0.14.412.686 I srv llama_server: model loaded |
| | 0.14.412.689 I srv llama_server: server is listening on http://0.0.0.0:8012 |
| | 0.14.412.697 I srv update_slots: all slots are idle |
| | 0.53.838.855 I srv params_from_: Chat format: peg-native |
| | 0.53.859.921 I slot get_availabl: id 3 | task -1 | selected slot by LRU, t_last = -1 |
| | 0.53.859.923 I srv get_availabl: updating prompt cache |
| | 0.53.859.929 I srv load: - looking for better prompt, base f_keep = -1.000, sim = 0.000 |
| | 0.53.859.934 I srv update: - cache state: 0 prompts, 0.000 MiB (limits: 8192.000 MiB, 131072 tokens, 8589934592 est) |
| | 0.53.859.934 I srv get_availabl: prompt cache update took 0.01 ms |
| | 0.53.860.696 I slot launch_slot_: id 3 | task 0 | processing task, is_child = 0 |
| | 0.53.962.888 I srv params_from_: Chat format: peg-native |
| | 0.55.442.476 I slot get_availabl: id 2 | task -1 | selected slot by LRU, t_last = -1 |
| | 0.55.442.478 I srv get_availabl: updating prompt cache |
| | 0.55.442.482 I srv load: - looking for better prompt, base f_keep = -1.000, sim = 0.000 |
| | 0.55.442.484 I srv update: - cache state: 0 prompts, 0.000 MiB (limits: 8192.000 MiB, 131072 tokens, 8589934592 est) |
| | 0.55.442.485 I srv get_availabl: prompt cache update took 0.01 ms |
| | 0.55.443.928 I slot launch_slot_: id 2 | task 2 | processing task, is_child = 0 |
| | 1.00.811.354 I slot print_timing: id 2 | task 2 | prompt processing, n_tokens = 2048, progress = 0.30, t = 5.37 s / 381.56 tokens per second |
| | 1.05.921.432 I slot print_timing: id 2 | task 2 | prompt processing, n_tokens = 4096, progress = 0.61, t = 10.48 s / 390.93 tokens per second |
| | 1.11.031.597 I slot print_timing: id 2 | task 2 | prompt processing, n_tokens = 6144, progress = 0.91, t = 15.59 s / 394.16 tokens per second |
| | 1.11.031.682 I slot print_timing: id 3 | task 0 | prompt processing, n_tokens = 371, progress = 0.42, t = 17.17 s / 21.61 tokens per second |
| | 1.12.311.375 I slot print_timing: id 2 | task 2 | prompt processing, n_tokens = 6248, progress = 0.92, t = 16.87 s / 370.42 tokens per second |
| | 1.12.311.469 I slot print_timing: id 3 | task 0 | prompt processing, n_tokens = 582, progress = 0.66, t = 18.45 s / 31.54 tokens per second |
| | 1.12.317.858 I slot create_check: id 3 | task 0 | created context checkpoint 1 of 32 (pos_min = 244, pos_max = 581, n_tokens = 582, size = 7.926 MiB) |
| | 1.13.691.441 I slot print_timing: id 2 | task 2 | prompt processing, n_tokens = 6459, progress = 0.95, t = 18.25 s / 353.97 tokens per second |
| | 1.13.698.938 I slot create_check: id 2 | task 2 | created context checkpoint 1 of 32 (pos_min = 6074, pos_max = 6458, n_tokens = 6459, size = 9.028 MiB) |
| | 1.13.698.943 I slot print_timing: id 3 | task 0 | prompt processing, n_tokens = 883, progress = 1.00, t = 19.84 s / 44.51 tokens per second |
| | 1.13.711.424 I slot create_check: id 3 | task 0 | created context checkpoint 2 of 32 (pos_min = 244, pos_max = 882, n_tokens = 883, size = 14.984 MiB) |
| | 1.14.989.097 I slot print_timing: id 2 | task 2 | prompt processing, n_tokens = 6760, progress = 1.00, t = 19.55 s / 345.87 tokens per second |
| | 1.14.999.395 I slot create_check: id 2 | task 2 | created context checkpoint 2 of 32 (pos_min = 6248, pos_max = 6759, n_tokens = 6760, size = 12.006 MiB) |
| | 1.17.275.512 I slot print_timing: id 2 | task 2 | prompt eval time = 19650.35 ms / 6764 tokens ( 2.91 ms per token, 344.22 tokens per second) |
| | 1.17.275.514 I slot print_timing: id 2 | task 2 | eval time = 2181.20 ms / 49 tokens ( 44.51 ms per token, 22.46 tokens per second) |
| | 1.17.275.515 I slot print_timing: id 2 | task 2 | total time = 21831.56 ms / 6813 tokens |
| | 1.17.275.518 I slot print_timing: id 2 | task 2 | graphs reused = 47 |
| | 1.17.322.530 I slot release: id 2 | task 2 | stop processing: n_tokens = 6812, truncated = 0 |
| | 1.18.577.818 I slot print_timing: id 3 | task 0 | n_decoded = 100, tg = 27.86 t/s |
| | 1.18.833.520 I slot print_timing: id 3 | task 0 | prompt eval time = 21128.34 ms / 887 tokens ( 23.82 ms per token, 41.98 tokens per second) |
| | 1.18.833.522 I slot print_timing: id 3 | task 0 | eval time = 3844.46 ms / 111 tokens ( 34.63 ms per token, 28.87 tokens per second) |
| | 1.18.833.522 I slot print_timing: id 3 | task 0 | total time = 24972.80 ms / 998 tokens |
| | 1.18.833.523 I slot print_timing: id 3 | task 0 | graphs reused = 107 |
| | 1.18.844.486 I slot release: id 3 | task 0 | stop processing: n_tokens = 997, truncated = 0 |
| | 1.18.844.505 I srv update_slots: all slots are idle |
| </code> | </code> |
| |
