runtime error

Exit code: 1. Reason: ase. print("Available backends:", torchaudio.list_audio_backends()) /app/inference_webui.py:98: UserWarning: torio.utils.ffmpeg_utils.get_audio_decoders has been deprecated. This deprecation is part of a large refactoring effort to transition TorchAudio into a maintenance phase. Please see https://github.com/pytorch/audio/issues/3902 for more information. It will be removed from the 2.9 release. print("FFmpeg Decoders:", ffmpeg_utils.get_audio_decoders()) Available backends: ['soundfile'] FFmpeg can't be loaded [nltk_data] Downloading package averaged_perceptron_tagger_eng to [nltk_data] /root/nltk_data... [nltk_data] Unzipping taggers/averaged_perceptron_tagger_eng.zip. /app/utils.py:258: SyntaxWarning: invalid escape sequence '\d' name_key = lambda _f: int(re.compile("._(\d+)\.pth").match(_f).group(1)) [INFO] CUDA is not available, skipping nvrtc setup. Loading weights: 0%| | 0/396 [00:00<?, ?it/s] Loading weights: 100%|██████████| 396/396 [00:00<00:00, 34142.09it/s] Loading weights: 0%| | 0/211 [00:00<?, ?it/s] Loading weights: 100%|██████████| 211/211 [00:00<00:00, 18696.88it/s] <All keys matched successfully> Loading Text2Semantic Weights from pretrained_models/s1v3.ckpt with Flash Attn Implement Traceback (most recent call last): File "/app/inference_webui.py", line 315, in <module> change_gpt_weights("pretrained_models/s1v3.ckpt") File "/app/inference_webui.py", line 308, in change_gpt_weights t2s_model = CUDAGraphRunner( ^^^^^^^^^^^^^^^^ File "/app/AR/models/t2s_model_flash_attn.py", line 227, in __init__ self.input_pos = torch.tensor([10]).int().cuda() ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.12/site-packages/torch/cuda/__init__.py", line 412, 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: