runtime error

Exit code: 1. Reason: 01(…): 100%|██████████| 3.10G/3.10G [00:02<00:00, 1.53GB/s] Traceback (most recent call last): File "/app/app.py", line 43, in <module> transformer=WanTransformer3DModel.from_pretrained( ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^ MODEL_ID, ^^^^^^^^^ ...<3 lines>... token=HF_TOKEN ^^^^^^^^^^^^^^ ), ^ File "/root/.pyenv/versions/3.13.11/lib/python3.13/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn return fn(*args, **kwargs) File "/root/.pyenv/versions/3.13.11/lib/python3.13/site-packages/diffusers/models/modeling_utils.py", line 1288, in from_pretrained ) = cls._load_pretrained_model( ~~~~~~~~~~~~~~~~~~~~~~~~~~^ model, ^^^^^^ ...<13 lines>... is_parallel_loading_enabled=is_parallel_loading_enabled, ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ) ^ File "/root/.pyenv/versions/3.13.11/lib/python3.13/site-packages/diffusers/models/modeling_utils.py", line 1537, in _load_pretrained_model _caching_allocator_warmup(model, expanded_device_map, dtype, hf_quantizer) ~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/root/.pyenv/versions/3.13.11/lib/python3.13/site-packages/diffusers/models/model_loading_utils.py", line 748, in _caching_allocator_warmup _ = torch.empty(byte_count // factor, dtype=dtype, device=device, requires_grad=False) torch.OutOfMemoryError: CUDA out of memory. Tried to allocate 26.62 GiB. GPU 0 has a total capacity of 22.03 GiB of which 21.84 GiB is free. Including non-PyTorch memory, this process has 186.00 MiB memory in use. Of the allocated memory 0 bytes is allocated by PyTorch, and 0 bytes is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables)

Container logs: