runtime error

Exit code: 1. Reason: y '/root/.config/Ultralytics' is not writable, using '/tmp/Ultralytics'. Set YOLO_CONFIG_DIR to override. WARNING ⚠️ torchvision==0.24 is incompatible with torch==2.4. Run 'pip install torchvision==0.19' to fix torchvision or 'pip install -U torch torchvision' to update both. For a full compatibility table see https://github.com/pytorch/vision#installation Creating new Ultralytics Settings v0.0.6 file ✅ View Ultralytics Settings with 'yolo settings' or at '/tmp/Ultralytics/settings.json' Update Settings with 'yolo settings key=value', i.e. 'yolo settings runs_dir=path/to/dir'. For help see https://docs.ultralytics.com/quickstart/#ultralytics-settings. Warning, cannot find cuda-compiled version of RoPE2D, using a slow pytorch version instead Traceback (most recent call last): File "/app/app.py", line 68, in <module> from unish.utils.inference_utils import ( File "/app/unish/utils/inference_utils.py", line 19, in <module> from unish.pipeline import UniSHPipeline File "/app/unish/pipeline.py", line 6, in <module> from unish.pi3.models.pi3 import Pi3 File "/app/unish/pi3/models/pi3.py", line 13, in <module> from .layers.transformer_head import TransformerDecoder, LinearPts3d, ConvStack File "/app/unish/pi3/models/layers/transformer_head.py", line 6, in <module> from torch.utils.checkpoint import checkpoint File "/usr/local/lib/python3.10/site-packages/torch/utils/checkpoint.py", line 15, in <module> from torch.testing._internal.logging_tensor import capture_logs, LoggingTensorMode File "/usr/local/lib/python3.10/site-packages/torch/testing/_internal/logging_tensor.py", line 10, in <module> from torch.utils._dtype_abbrs import dtype_abbrs as _dtype_abbrs File "/usr/local/lib/python3.10/site-packages/torch/utils/_dtype_abbrs.py", line 14, in <module> torch.float8_e8m0fnu: "f8e8m0fnu", File "/usr/local/lib/python3.10/site-packages/torch/__init__.py", line 2216, in __getattr__ futures as futures, AttributeError: module 'torch' has no attribute 'float8_e8m0fnu'

Container logs: