I did everthing of setup.md but got pytroch error

First I want to thank you for granting accses to this awesome hard worked model but sadly I got problem:
`
+-----------------------------------------------------------------------------------------+ | NVIDIA-SMI 580.105.08 Driver Version: 580.105.08 CUDA Version: 13.0 | +-----------------------------------------+------------------------+----------------------+ | GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC | | Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. | | | | MIG M. | |=========================================+========================+======================| | 0 NVIDIA GeForce RTX 5090 On | 00000000:01:00.0 On | N/A | | 0% 43C P0 63W / 600W | 1269MiB / 32607MiB | 4% Default | | | | N/A | +-----------------------------------------+------------------------+----------------------+`

`_init__:131 - Loading model weights... Traceback (most recent call last): File "/home/b_cansin/miniconda3/envs/sam3d-objects/lib/python3.11/site-packages/hydra/_internal/instantiate/_instantiate2.py", line 92, in _call_target return _target_(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^ File "/media/b_cansin/ai/ai/sam-3d-objects-main/sam3d_objects/model/backbone/tdfy_dit/models/mm_latent.py", line 17, in __init__ self.input_layer = nn.Linear(in_channels, model_channels) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/b_cansin/miniconda3/envs/sam3d-objects/lib/python3.11/site-packages/torch/nn/modules/linear.py", line 112, in __init__ self.reset_parameters() File "/home/b_cansin/miniconda3/envs/sam3d-objects/lib/python3.11/site-packages/torch/nn/modules/linear.py", line 118, in reset_parameters init.kaiming_uniform_(self.weight, a=math.sqrt(5)) File "/home/b_cansin/miniconda3/envs/sam3d-objects/lib/python3.11/site-packages/torch/nn/init.py", line 500, in kaiming_uniform_ return torch.overrides.handle_torch_function( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/b_cansin/miniconda3/envs/sam3d-objects/lib/python3.11/site-packages/torch/overrides.py", line 1717, in handle_torch_function result = mode.__torch_function__(public_api, types, args, kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/b_cansin/miniconda3/envs/sam3d-objects/lib/python3.11/site-packages/torch/utils/_device.py", line 106, in __torch_function__ return func(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^ File "/home/b_cansin/miniconda3/envs/sam3d-objects/lib/python3.11/site-packages/torch/nn/init.py", line 518, in kaiming_uniform_ return tensor.uniform_(-bound, bound, generator=generator) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ RuntimeError: CUDA error: no kernel image is available for execution on the device 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 Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions. The above exception was the direct cause of the following exception: Traceback (most recent call last): File "/home/b_cansin/miniconda3/envs/sam3d-objects/lib/python3.11/site-packages/hydra/_internal/instantiate/_instantiate2.py", line 92, in _call_target return _target_(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^ File "/media/b_cansin/ai/ai/sam-3d-objects-main/sam3d_objects/pipeline/inference_pipeline_pointmap.py", line 99, in __init__ super().__init__(*args, **kwargs) File "/media/b_cansin/ai/ai/sam-3d-objects-main/sam3d_objects/pipeline/inference_pipeline.py", line 133, in __init__ ss_generator = self.init_ss_generator( ^^^^^^^^^^^^^^^^^^^^^^^ File "/media/b_cansin/ai/ai/sam-3d-objects-main/sam3d_objects/pipeline/inference_pipeline.py", line 313, in init_ss_generator return self.instantiate_and_load_from_pretrained( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/media/b_cansin/ai/ai/sam-3d-objects-main/sam3d_objects/pipeline/inference_pipeline.py", line 269, in instantiate_and_load_from_pretrained model = instantiate(config) ^^^^^^^^^^^^^^^^^^^ File "/home/b_cansin/miniconda3/envs/sam3d-objects/lib/python3.11/site-packages/hydra/_internal/instantiate/_instantiate2.py", line 226, in instantiate return instantiate_node( ^^^^^^^^^^^^^^^^^ File "/home/b_cansin/miniconda3/envs/sam3d-objects/lib/python3.11/site-packages/hydra/_internal/instantiate/_instantiate2.py", line 342, in instantiate_node value = instantiate_node( ^^^^^^^^^^^^^^^^^ File "/home/b_cansin/miniconda3/envs/sam3d-objects/lib/python3.11/site-packages/hydra/_internal/instantiate/_instantiate2.py", line 342, in instantiate_node value = instantiate_node( ^^^^^^^^^^^^^^^^^ File "/home/b_cansin/miniconda3/envs/sam3d-objects/lib/python3.11/site-packages/hydra/_internal/instantiate/_instantiate2.py", line 342, in instantiate_node value = instantiate_node( ^^^^^^^^^^^^^^^^^ File "/home/b_cansin/miniconda3/envs/sam3d-objects/lib/python3.11/site-packages/hydra/_internal/instantiate/_instantiate2.py", line 366, in instantiate_node cfg[key] = instantiate_node( ^^^^^^^^^^^^^^^^^ File "/home/b_cansin/miniconda3/envs/sam3d-objects/lib/python3.11/site-packages/hydra/_internal/instantiate/_instantiate2.py", line 347, in instantiate_node return _call_target(_target_, partial, args, kwargs, full_key) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/b_cansin/miniconda3/envs/sam3d-objects/lib/python3.11/site-packages/hydra/_internal/instantiate/_instantiate2.py", line 97, in _call_target raise InstantiationException(msg) from e hydra.errors.InstantiationException: Error in call to target 'sam3d_objects.model.backbone.tdfy_dit.models.mm_latent.Latent': RuntimeError('CUDA error: no kernel image is available for execution on the device\nCUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.\nFor debugging consider passing CUDA_LAUNCH_BLOCKING=1\nCompile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.\n') full_key: module.generator.backbone.reverse_fn.backbone.latent_mapping.6drotation_normalized The above exception was the direct cause of the following exception: Traceback (most recent call last): File "/media/b_cansin/ai/ai/sam-3d-objects-main/demo.py", line 10, in inference = Inference(config_path, compile=False) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/media/b_cansin/ai/ai/sam-3d-objects-main/notebook/inference.py", line 92, in __init__ self._pipeline: InferencePipelinePointMap = instantiate(config) ^^^^^^^^^^^^^^^^^^^ File "/home/b_cansin/miniconda3/envs/sam3d-objects/lib/python3.11/site-packages/hydra/_internal/instantiate/_instantiate2.py", line 226, in instantiate return instantiate_node( ^^^^^^^^^^^^^^^^^ File "/home/b_cansin/miniconda3/envs/sam3d-objects/lib/python3.11/site-packages/hydra/_internal/instantiate/_instantiate2.py", line 347, in instantiate_node return _call_target(_target_, partial, args, kwargs, full_key) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/b_cansin/miniconda3/envs/sam3d-objects/lib/python3.11/site-packages/hydra/_internal/instantiate/_instantiate2.py", line 97, in _call_target raise InstantiationException(msg) from e hydra.errors.InstantiationException: Error in call to target 'sam3d_objects.pipeline.inference_pipeline_pointmap.InferencePipelinePointMap': InstantiationException("Error in call to target 'sam3d_objects.model.backbone.tdfy_dit.models.mm_latent.Latent':\nRuntimeError('CUDA error: no kernel image is available for execution on the device\\nCUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.\\nFor debugging consider passing CUDA_LAUNCH_BLOCKING=1\\nCompile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.\\n')\nfull_key: module.generator.backbone.reverse_fn.backbone.latent_mapping.6drotation_normalized")`

Than upgrade pytorch to pre cuda 13 with
`pip3 install --pre torch torchvision --index-url https://download.pytorch.org/whl/nightly/cu130`

than got

`s-main$ python demo.py /home/b_cansin/miniconda3/envs/sam3d-objects/lib/python3.11/site-packages/torch/cuda/__init__.py:65: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you. import pynvml # type: ignore[import] Traceback (most recent call last): File "/media/b_cansin/ai/ai/sam-3d-objects-main/demo.py", line 5, in from inference import Inference, load_image, load_single_mask File "/media/b_cansin/ai/ai/sam-3d-objects-main/notebook/inference.py", line 25, in from kaolin.visualize import IpyTurntableVisualizer File "/home/b_cansin/miniconda3/envs/sam3d-objects/lib/python3.11/site-packages/kaolin/__init__.py", line 1, in from . import io File "/home/b_cansin/miniconda3/envs/sam3d-objects/lib/python3.11/site-packages/kaolin/io/__init__.py", line 1, in from . import dataset File "/home/b_cansin/miniconda3/envs/sam3d-objects/lib/python3.11/site-packages/kaolin/io/dataset.py", line 31, in from ..utils.testing import contained_torch_equal File "/home/b_cansin/miniconda3/envs/sam3d-objects/lib/python3.11/site-packages/kaolin/utils/__init__.py", line 1, in from . import testing File "/home/b_cansin/miniconda3/envs/sam3d-objects/lib/python3.11/site-packages/kaolin/utils/testing.py", line 29, in import kaolin.ops.random as random File "/home/b_cansin/miniconda3/envs/sam3d-objects/lib/python3.11/site-packages/kaolin/ops/__init__.py", line 1, in from . import batch File "/home/b_cansin/miniconda3/envs/sam3d-objects/lib/python3.11/site-packages/kaolin/ops/batch.py", line 17, in from kaolin import _C ImportError: /home/b_cansin/miniconda3/envs/sam3d-objects/lib/python3.11/site-packages/kaolin/_C.so: undefined symbol: _ZN3c104cuda29c10_cuda_check_implementationEiPKcS2_ib (sam3d-objects) b_cansin@b-cansin-ubuntu-main:/media/b_cansin/ai/ai/sam-3d-objects-main$`

now I think I made even more worser than ever. Sad I really want to etremely give it try.

Can we get comfyui nodes? It would extremely easy to use with it.