runtime error

Exit code: 1. Reason: pytorch_model.safetensors: 0%| | 0.00/5.60G [00:00<?, ?B/s] pytorch_model.safetensors: 1%|▏ | 77.1M/5.60G [00:10<12:16, 7.50MB/s] pytorch_model.safetensors: 19%|█▉ | 1.08G/5.60G [00:11<00:35, 127MB/s]  pytorch_model.safetensors: 37%|███▋ | 2.07G/5.60G [00:23<00:35, 98.5MB/s] pytorch_model.safetensors: 77%|███████▋ | 4.30G/5.60G [00:24<00:05, 258MB/s]  pytorch_model.safetensors: 100%|██████████| 5.60G/5.60G [00:24<00:00, 226MB/s] Traceback (most recent call last): File "/app/gradio_app.py", line 60, in <module> model = load_model_from_hf(dtype=MODEL_DTYPE, delete_blockwise_modules=True) File "/app/inference.py", line 38, in load_model_from_hf state = {k: v.to(device=device) for k, v in state.items()} ~~~~^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.13/site-packages/torch/cuda/__init__.py", line 424, in _lazy_init torch._C._cuda_init() ~~~~~~~~~~~~~~~~~~~^^ RuntimeError: Found no NVIDIA driver on your system. Please check that you have an NVIDIA GPU and installed a driver from http://www.nvidia.com/Download/index.aspx

Container logs: