runtime error

Exit code: 1. Reason: 02<00:12, 190MB/s]  model-00004-of-00004.safetensors: 29%|██▉ | 797M/2.70G [00:03<00:06, 311MB/s] model-00004-of-00004.safetensors: 46%|████▌ | 1.25G/2.70G [00:04<00:03, 367MB/s] model-00004-of-00004.safetensors: 63%|██████▎ | 1.70G/2.70G [00:05<00:02, 396MB/s] model-00004-of-00004.safetensors: 83%|████████▎ | 2.25G/2.70G [00:06<00:01, 447MB/s] model-00004-of-00004.safetensors: 100%|██████████| 2.70G/2.70G [00:06<00:00, 409MB/s] Traceback (most recent call last): File "/app/app.py", line 134, in <module> model_v = Qwen3VLForConditionalGeneration.from_pretrained( File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 277, in _wrapper return func(*args, **kwargs) File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 4971, in from_pretrained model = cls(config, *model_args, **model_kwargs) File "/usr/local/lib/python3.10/site-packages/transformers/models/qwen3_vl/modeling_qwen3_vl.py", line 1279, in __init__ super().__init__(config) File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 2076, in __init__ self.config._attn_implementation_internal = self._check_and_adjust_attn_implementation( File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 2686, in _check_and_adjust_attn_implementation applicable_attn_implementation = self.get_correct_attn_implementation( File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 2714, in get_correct_attn_implementation self._flash_attn_2_can_dispatch(is_init_check) File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 2432, in _flash_attn_2_can_dispatch raise ValueError( ValueError: FlashAttention2 has been toggled on, but it cannot be used due to the following error: Flash Attention 2 is not available on CPU. Please make sure torch can access a CUDA device.

Container logs: