When running to Triplane Gaussian Transformers(TGS), crashes and crashes occur without logs.

[WorkSync]

Hello everyone, I have tested the workflow——Triplane_Gaussian_Transformers_to_3DGS_and_3DMesh.json.What I found when I was testing (I had the model ready) was when I ran to the node——crashes and crashes occur without logs. At this point, the console displays the following information：

To see the GUI go to: http://127.0.0.1:8188 [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/model-list.json [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/extension-node-map.json [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/alter-list.json [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/github-stats.json [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/custom-node-list.json FETCH DATA from: C:\ZTData\Database\Code\Code_Py\clone_projects\ComfyUI_8190\custom_nodes\ComfyUI-Manager\extension-node-map.json [DONE] FETCH DATA from: C:\ZTData\Database\Code\Code_Py\clone_projects\ComfyUI_8190\custom_nodes\ComfyUI-Manager\extension-node-map.json [DONE] got prompt TriplaneGaussian.models.tokenizers.image TriplaneGaussian.models.pointclouds.simplepoint TriplaneGaussian.models.tokenizers.image TriplaneGaussian.models.networks TriplaneGaussian.models.tokenizers.point TriplaneGaussian.models.transformers TriplaneGaussian.models.networks TriplaneGaussian.models.snowflake.model_spdpp TriplaneGaussian.models.pointclouds.pointnet [Comfy3D] [Load_Triplane_Gaussian_Transformers] loaded model ckpt from C:\ZTData\Database\Code\Code_Py\clone_projects\ComfyUI_8190\custom_nodes\ComfyUI-3D-Pack\Checkpoints\TriplaneGaussian\model_lvis_rel.ckpt Warn!: C:\ZTData\Database\Code\Code_Py\clone_projects\ComfyUI_8190\custom_nodes\ComfyUI-3D-Pack\Gen_3D_Modules\TriplaneGaussian\data.py:91: UserWarning: Using torch.cross without specifying the dim arg is deprecated. Please either pass the dim explicitly or simply use torch.linalg.cross. The default value of dim will change to agree with that of linalg.cross in a future release. (Triggered internally at ..\aten\src\ATen\native\Cross.cpp:66.)
right: Float[Tensor, "B 3"] = F.normalize(torch.cross(lookat, up), dim=-1)

Warn!: C:\ZTData\Database\anaconda_env\comfyui_2\Lib\site-packages\diffusers\models\attention_processor.py:1584: UserWarning: 1Torch was not compiled with flash attention. (Triggered internally at ..\aten\src\ATen\native\transformers\cuda\sdp_utils.cpp:455.) hidden_states = F.scaled_dot_product_attention(

PS C:\ZTData\Database\Code\Code_Py\clone_projects\ComfyUI_8190>

I‘ve tested the original project of Triplane_Gaussian_Transformers,I found that when I was running this native project, there were crashes and crashes, and during the run, I noticed that the CPU was working but the GPU was not.As shown in the following figure：

But I am certain that CUDA is installed and there are no conflicts with its dependencies.(Actually, I tested the workflow——Tripo3D and successfully generated the 3D model.When it comes to Triplane_Gaussian_Transformers,it failed,which makes me sad.I've been stuck on this problem for a week.):

(C:\ZTData\Database\anaconda_env\comfyui_2) C:\ZTData\Database\Code\Code_Py\clone_projects\ComfyUI_8190>nvcc --version nvcc: NVIDIA (R) Cuda compiler driver Copyright (c) 2005-2023 NVIDIA Corporation Built on Mon_Apr__3_17:36:15_Pacific_Daylight_Time_2023 Cuda compilation tools, release 12.1, V12.1.105 Build cuda_12.1.r12.1/compiler.32688072_0

And the pip list:

(C:\ZTData\Database\anaconda_env\comfyui_2) C:\ZTData\Database\Code\Code_Py\clone_projects\ComfyUI_8190>pip list DEPRECATION: Loading egg at c:\ztdata\database\anaconda_env\comfyui_2\lib\site-packages\pointnet2_ops-3.0.0-py3.11-win-amd64.egg is deprecated. pip 24.3 will enforce this behaviour change. A possible replacement is to use pip for package installation.. Discussion can be found at https://github.com/pypa/pip/issues/12330Package Version

---

aiofiles 23.2.1 aiohttp 3.9.5 aiosignal 1.3.1 annotated-types 0.7.0 antlr4-python3-runtime 4.9.3 anyio 4.4.0 attrs 23.2.0 certifi 2024.7.4 cffi 1.16.0 charset-normalizer 3.3.2 click 8.1.7 cmake 3.30.1 colorama 0.4.6 coloredlogs 15.0.1 contourpy 1.2.1 cryptography 43.0.0 cycler 0.12.1 dataclasses-json 0.6.7 Deprecated 1.2.14 diff_gaussian_rasterization 0.0.0 diffusers 0.29.2 dnspython 2.6.1 einops 0.8.0 email_validator 2.2.0 executing 2.0.1 fastapi 0.111.1 fastapi-cli 0.0.4 ffmpy 0.3.2 filelock 3.15.4 flash_attn 2.6.1 flatbuffers 24.3.25 fonttools 4.53.1 frozenlist 1.4.1 fsspec 2024.6.1 ftfy 6.2.0 fvcore 0.1.5.post20221221 gitdb 4.0.11 GitPython 3.1.43 gradio 4.39.0 gradio_client 1.1.1 gradio_model3dgs 0.2.5 h11 0.14.0 httpcore 1.0.5 httptools 0.6.1 httpx 0.27.0 huggingface-hub 0.24.0 humanfriendly 10.0 idna 3.7 imageio 2.34.2 imageio-ffmpeg 0.5.1 importlib_metadata 8.0.0 importlib_resources 6.4.0 intel-openmp 2021.4.0 iopath 0.1.10 jaxtyping 0.2.33 Jinja2 3.1.4 jsonschema 4.23.0 jsonschema-specifications 2023.12.1 kiui 0.2.10 kiwisolver 1.4.5 kornia 0.7.3 kornia_rs 0.1.5 lazy_loader 0.4 lightning-utilities 0.11.5 llvmlite 0.43.0 markdown-it-py 3.0.0 MarkupSafe 2.1.5 marshmallow 3.21.3 matplotlib 3.9.1 matrix-client 0.4.0 mdurl 0.1.2 mkl 2021.4.0 mpmath 1.3.0 msvc_runtime 14.40.33807 multidict 6.0.5 mypy-extensions 1.0.0 nerfacc 0.5.3 networkx 3.3 ninja 1.11.1.1 numba 0.60.0 numpy 1.26.4 nvdiffrast 0.3.1 objprint 0.2.3 omegaconf 2.3.0 onnxruntime 1.18.1 open_clip_torch 2.26.1 opencv-python 4.10.0.84 opencv-python-headless 4.10.0.84 orjson 3.10.6 packaging 24.1 pandas 2.2.2 piexif 1.1.3 pillow 10.4.0 pip 24.0 platformdirs 4.2.2 plyfile 1.0.3 pointnet2_ops 3.0.0 pointnet2_ops 3.0.0 pooch 1.8.2 portalocker 2.10.1 protobuf 5.27.2 psutil 6.0.0 py-cpuinfo 9.0.0 pycparser 2.22 pydantic 2.8.2 pydantic_core 2.20.1 pydub 0.25.1 PyGithub 2.3.0 pygltflib 1.16.2 Pygments 2.18.0 pyhocon 0.3.61 PyJWT 2.8.0 PyMatting 1.1.12 PyMCubes 0.1.6 pymeshlab 2023.12.post1 PyNaCl 1.5.0 pyparsing 3.1.2 pyreadline3 3.4.1 python-dateutil 2.9.0.post0 python-dotenv 1.0.1 python-multipart 0.0.9 pytorch-lightning 2.3.3 pytorch-msssim 1.0.0 pytorch3d 0.7.7 pytz 2024.1 pywin32 306 PyYAML 6.0.1 referencing 0.35.1 regex 2024.5.15 rembg 2.0.57 requests 2.32.3 rich 13.7.1 rpds-py 0.19.0 ruff 0.5.4 safetensors 0.4.3 scikit-image 0.24.0 scipy 1.14.0 seaborn 0.13.2 segment-anything 1.0 semantic-version 2.10.0 sentencepiece 0.2.0 setuptools 69.5.1 shellingham 1.5.4 simple_knn 0.0.0 six 1.16.0 smmap 5.0.1 sniffio 1.3.1 soundfile 0.12.1 spandrel 0.3.4 starlette 0.37.2 sympy 1.13.1 tabulate 0.9.0 tbb 2021.13.0 termcolor 2.4.0 tifffile 2024.7.21 timm 1.0.7 tokenizers 0.19.1 tomlkit 0.12.0 torch 2.3.0+cu121 torch_scatter 2.1.2 torchaudio 2.3.0+cu121 torchmetrics 1.4.0.post0 torchsde 0.2.6 torchtyping 0.1.4 torchvision 0.18.0+cu121 tqdm 4.66.4 trampoline 0.1.2 transformers 4.42.4 trimesh 4.4.3 triton 2.1.0 typeguard 2.13.3 typer 0.12.3 typing_extensions 4.12.2 typing-inspect 0.9.0 tzdata 2024.1 ultralytics 8.2.64 ultralytics-thop 2.0.0 urllib3 2.2.2 uvicorn 0.30.3 varname 0.13.3 watchfiles 0.22.0 wcwidth 0.2.13 websockets 11.0.3 wheel 0.43.0 wrapt 1.16.0 xatlas 0.0.9 xformers 0.0.26.post1 yacs 0.1.8 yarl 1.9.4 zipp 3.19.2

I would appreciate it if someone could help me qaq.

[WorkSync]

My GPU models are as follows:

NVIDIA GeForce RTX 3060

My output code is:

import torch
print(torch.cuda.get_device_properties(0).name)

[atilladeniz]

same here

[Duodecimus]

Your torchscatter isn't installed with cuda. Mine looks like this in pip: torch_scatter==2.1.2+pt23cu121

[WorkSync]

Your torchscatter isn't installed with cuda. Mine looks like this in pip: torch_scatter==2.1.2+pt23cu121

Thank you for your reply, but my pip show that I have installed it and it does not match version 2.1.2+pt23cu121