AssertionError: Torch not compiled with CUDA enabled

2025-06-19 02:45:48,301 - modelscope - INFO - No preprocessor key ('latent-text-to-video-synthesis', 'text-to-video-synthesis') found in PREPROCESSOR_MAP, skip building preprocessor. If the pipeline runs normally, please ignore this log.
Traceback (most recent call last):
  File "text-to-video.py", line 16, in
    output = pipeline({"text":prompt}, num_frames=48, fps=8)
  File "/usr/local/lib/python3.8/dist-packages/modelscope/pipelines/base.py", line 242, in __call__
    output = self._process_single(input, *args, **kwargs)
  File "/usr/local/lib/python3.8/dist-packages/modelscope/pipelines/base.py", line 270, in _process_single
    out = self.preprocess(input, **preprocess_params)
  File "/usr/local/lib/python3.8/dist-packages/modelscope/pipelines/multi_modal/text_to_video_synthesis_pipeline.py", line 52, in preprocess
    text_emb =