runtime error

Exit code: 1. Reason: k_fixed.pkl: 38%|███▊ | 1.68G/4.44G [00:09<00:11, 247MB/s] last_250k_fixed.pkl: 50%|█████ | 2.23G/4.44G [00:10<00:06, 319MB/s] last_250k_fixed.pkl: 71%|███████▏ | 3.16G/4.44G [00:11<00:02, 483MB/s] last_250k_fixed.pkl: 88%|████████▊ | 3.90G/4.44G [00:12<00:00, 550MB/s] last_250k_fixed.pkl: 100%|██████████| 4.44G/4.44G [00:12<00:00, 343MB/s] Loading tokenizer Loading speech tokenizer Traceback (most recent call last): File "/home/user/app/app.py", line 35, in <module> inpainter = PlayDiffusion(device=device) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.11/site-packages/playdiffusion/inference.py", line 47, in __init__ self.mm = PlayDiffusionModelManager(self.preset, self.device) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.11/site-packages/playdiffusion/models/model_manager.py", line 17, in __init__ self.load_tokenizers( File "/usr/local/lib/python3.11/site-packages/playdiffusion/models/model_manager.py", line 53, in load_tokenizers speech_tokenizer = SpeechTokenizer( ^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.11/site-packages/playdiffusion/models/speech_tokenizer/speech_tokenizer.py", line 126, in __init__ self.cuda_stream = torch.cuda.Stream() ^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.11/site-packages/torch/cuda/streams.py", line 34, in __new__ return super().__new__(cls, priority=priority, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ RuntimeError: CUDA error: CUDA driver version is insufficient for CUDA runtime version CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1 Device-side assertions were explicitly omitted for this error check; the error probably arose while initializing the DSA handlers.

Container logs: