replicate cog Model setup failed

[xrunda]

$ sudo cog predict -i source_image=https://project-resource.oss-cn-beijing.aliyuncs.com/baby.png -i driven_audio=https://project-resource.oss-cn-beijing.aliyuncs.com/baby.wav
Building Docker image from environment in cog.yaml...

Starting Docker image cog-sadtalker-base and running setup()...
docker: Error response from daemon: failed to create shim task: OCI runtime create failed: runc create failed: unable to start container process: error during container init: error running hook #0: error running hook: exit status 1, stdout: , stderr: Auto-detected mode as 'legacy'
nvidia-container-cli: initialization error: load library failed: libnvidia-ml.so.1: cannot open shared object file: no such file or directory: unknown.
Missing device driver, re-trying without GPU
Error response from daemon: page not found
using safetensor as default
Traceback (most recent call last):
File "/root/.pyenv/versions/3.8.18/lib/python3.8/site-packages/cog/server/worker.py", line 185, in _setup
run_setup(self._predictor)
File "/root/.pyenv/versions/3.8.18/lib/python3.8/site-packages/cog/predictor.py", line 66, in run_setup
predictor.setup()
File "predict.py", line 25, in setup
self.preprocess_model = CropAndExtract(sadtalker_paths, device
File "/src/src/utils/preprocess.py", line 49, in init
self.propress = Preprocesser(device)
File "/src/src/utils/croper.py", line 21, in init
self.predictor = KeypointExtractor(device)
File "/src/src/face3d/extract_kp_videos_safe.py", line 45, in init
self.detector = init_alignment_model('awing_fan',device=device, model_rootpath=root_path)
File "/src/src/face3d/extract_kp_videos_safe.py", line 28, in init_alignment_model
model.load_state_dict(torch.load(model_path, map_location=device)['state_dict'], strict=True)
File "/root/.pyenv/versions/3.8.18/lib/python3.8/site-packages/torch/serialization.py", line 713, in load
return _legacy_load(opened_file, map_location, pickle_module, **pickle_load_args)
File "/root/.pyenv/versions/3.8.18/lib/python3.8/site-packages/torch/serialization.py", line 930, in _legacy_load
result = unpickler.load()
File "/root/.pyenv/versions/3.8.18/lib/python3.8/site-packages/torch/serialization.py", line 876, in persistent_load
wrap_storage=restore_location(obj, location),
File "/root/.pyenv/versions/3.8.18/lib/python3.8/site-packages/torch/serialization.py", line 970, in restore_location
return default_restore_location(storage, map_location)
File "/root/.pyenv/versions/3.8.18/lib/python3.8/site-packages/torch/serialization.py", line 175, in default_restore_location
result = fn(storage, location)
File "/root/.pyenv/versions/3.8.18/lib/python3.8/site-packages/torch/serialization.py", line 152, in _cuda_deserialize
device = validate_cuda_device(location)
File "/root/.pyenv/versions/3.8.18/lib/python3.8/site-packages/torch/serialization.py", line 136, in validate_cuda_device
raise RuntimeError('Attempting to deserialize object on a CUDA '
RuntimeError: Attempting to deserialize object on a CUDA device but torch.cuda.is_available() is False. If you are running on a CPU-only machine, please use torch.load with map_location=torch.device('cpu') to map your storages to the CPU.
ⅹ Model setup failed

=================================
cog.yaml

build:
gpu: true
cuda: "11.3"
python_version: "3.8"
system_packages:
- "ffmpeg"
- "libgl1-mesa-glx"
- "libglib2.0-0"
python_packages:
- "torch==1.12.1"
- "torchvision==0.13.1"
- "torchaudio==0.12.1"
- "joblib==1.1.0"
- "scikit-image==0.19.3"
- "basicsr==1.4.2"
- "facexlib==0.3.0"
- "resampy==0.3.1"
- "pydub==0.25.1"
- "scipy==1.10.1"
- "kornia==0.6.8"
- "face_alignment==1.3.5"
- "imageio==2.19.3"
- "imageio-ffmpeg==0.4.7"
- "librosa==0.9.2" #
- "tqdm==4.65.0"
- "yacs==0.1.8"
- "gfpgan==1.3.8"
- "dlib-bin==19.24.1"
- "av==10.0.0"
- "trimesh==3.9.20"
- "safetensors"
run:
- mkdir -p /root/.cache/torch/hub/checkpoints/ && wget --output-document "/root/.cache/torch/hub/checkpoints/s3fd-619a316812.pth" "https://www.adrianbulat.com/downloads/python-fan/s3fd-619a316812.pth"
- mkdir -p /root/.cache/torch/hub/checkpoints/ && wget --output-document "/root/.cache/torch/hub/checkpoints/2DFAN4-cd938726ad.zip" "https://www.adrianbulat.com/downloads/python-fan/2DFAN4-cd938726ad.zip"

predict: "predict.py:Predictor"

==============================
$ nvcc --version
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2023 NVIDIA Corporation
Built on Mon_Apr__3_17:16:06_PDT_2023
Cuda compilation tools, release 12.1, V12.1.105
Build cuda_12.1.r12.1/compiler.32688072_0

How do I fix this bug?

[idootop]

You may need to install NVIDIA Container Toolkit first.