=== 2026-09-19T01:21:02Z pod i425oxd4f0v7ry | datacenter EUR-IS-1 | fase fase2-27b
Sat Sep 19 01:21:02 2026       
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 595.91.07              Driver Version: 595.91.07      CUDA Version: 13.2     |
+-----------------------------------------+------------------------+----------------------+
| GPU  Name                 Persistence-M | Bus-Id          Disp.A | Volatile Uncorr. ECC |
| Fan  Temp   Perf          Pwr:Usage/Cap |           Memory-Usage | GPU-Util  Compute M. |
|                                         |                        |               MIG M. |
|=========================================+========================+======================|
|   0  NVIDIA RTX PRO 6000 Blac...    On  |   00000000:77:00.0 Off |                    0 |
| N/A   30C    P8             35W /  600W |       0MiB /  97887MiB |      0%      Default |
|                                         |                        |             Disabled |
+-----------------------------------------+------------------------+----------------------+

+-----------------------------------------------------------------------------------------+
| Processes:                                                                              |
|  GPU   GI   CI              PID   Type   Process name                        GPU Memory |
|        ID   ID                                                               Usage      |
|=========================================================================================|
|  No running processes found                                                             |
+-----------------------------------------------------------------------------------------+

=== 2026-09-19T01:21:02Z sshd (so chave, sem senha)
sshd no ar, 1 chave(s) autorizada(s)
256 SHA256:[impressao-digital] root@00596eb50312 (ED25519)

=== 2026-09-19T01:21:03Z modelo
Qwen/Qwen3.8-27B-FP8 017b9c7af6b5689d5dd426a76e0bc077eb5ca20a
29G	/workspace/prisma/modelos/Qwen3.8-27B-FP8
vllm 0.29.0 | torch 2.13.0+cu130 | cuda 13.0
vllm serve /workspace/prisma/modelos/Qwen3.8-27B-FP8 --host 127.0.0.1 --port 8000 --served-model-name qwen3.8-27b --tensor-parallel-size 1 --max-model-len 65536 --gpu-memory-utilization 0.92 --enable-auto-tool-choice --tool-call-parser qwen3_xml --reasoning-parser qwen3 --enable-log-requests --enable-log-outputs
VLLM_USE_FLASHINFER_SAMPLER=0 TORCH_CUDA_ARCH_LIST=12.0 VLLM_CACHE_ROOT=/workspace/prisma/cache/vllm

=== 2026-09-19T01:30:42Z vLLM respondeu depois de 510 s

=== 2026-09-19T01:43:12Z fechando