!!! Exception during processing !!! CUDA error: no kernel image is available for execution on the device

[Y007]

[ATTENTION] Using backend: sdpa (i cannot use flash_attn or xformers so i add "sdpa" in line 191 nodes.py to use sdpa)
...
...
Loading Shape Slat decoder model......
!!! Exception during processing !!! 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.

Exception raised from c10_cuda_check_implementation at C:\actions-runner_work\pytorch\pytorch\pytorch\c10\cuda\CUDAException.cpp:42 (most recent call first):
00007FF85EE8199400007FF85EE818F0 c10.dll!c10::Error::Error [ @ ]
00007FF85EE23BE800007FF85EE23BA0 c10.dll!c10::AcceleratorError::AcceleratorError [ @ ]
00007FF86405819200007FF864058050 c10_cuda.dll!c10::cuda::c10_cuda_check_implementation [ @ ]
00007FF86405E52500007FF864059380 c10_cuda.dll!c10::cuda::warn_or_error_on_sync [ @ ]
00007FF86405951900007FF864059380 c10_cuda.dll!c10::cuda::warn_or_error_on_sync [ @ ]
00007FF85EE43DA300007FF85EE43D40 c10.dll!c10::StorageImpl::StorageImpl [ @ ]
00007FFEAF1B32B100007FFEAF1B2B70 torch_cpu.dll!at::DynamicLibrary::sym [ @ ]
00007FFEAF1B55E400007FFEAF1B55B0 torch_cpu.dll!at::detail::empty_generic [ @ ]
00007FFE20901FB500007FFE20901ED0 torch_cuda.dll!at::detail::empty_cuda [ @ ]
00007FFE20901EAE00007FFE20901DF0 torch_cuda.dll!at::detail::empty_cuda [ @ ]
00007FFE20A33AA800007FFE20A33A40 torch_cuda.dll!at::native::empty_cuda [ @ ]
00007FFE22829BE100007FFE227CD080 torch_cuda.dll!at::cuda::where_outf [ @ ]
00007FFE2271B18E00007FFE226ABD00 torch_cuda.dll!at::cuda::bucketize_outf [ @ ]
00007FFEAFDF06D500007FFEAFD72630 torch_cpu.dll!at::_ops::xlogy__Tensor::redispatch [ @ ]
00007FFEAFEC4A9E00007FFEAFEC49C0 torch_cpu.dll!at::_ops::empty_memory_format::redispatch [ @ ]
00007FFEB012852100007FFEB01049E0 torch_cpu.dll!at::_ops::view_as_real::redispatch [ @ ]
00007FFEB012640E00007FFEB01049E0 torch_cpu.dll!at::_ops::view_as_real::redispatch [ @ ]
00007FFEAFE392EF00007FFEAFE390D0 torch_cpu.dll!at::_ops::empty_memory_format::call [ @ ]
00007FFEAF1C082200007FFEAF1C0700 torch_cpu.dll!onnx_torch::ModelProto::model_version [ @ ]
00007FFEAF73BEB900007FFEAF73BDA0 torch_cpu.dll!at::native::full [ @ ]
00007FFEB02464E400007FFEB0241850 torch_cpu.dll!at::compositeexplicitautograd::view_copy_symint_outf [ @ ]
00007FFEB021579D00007FFEB01CC3D0 torch_cpu.dll!at::compositeexplicitautograd::bucketize_outf [ @ ]
00007FFEB005111B00007FFEB00097E0 torch_cpu.dll!at::_ops::zeros_like_out::redispatch [ @ ]
00007FFEB00EB76D00007FFEB00EB690 torch_cpu.dll!at::_ops::full::redispatch [ @ ]
00007FFEB0128EE400007FFEB01049E0 torch_cpu.dll!at::_ops::view_as_real::redispatch [ @ ]
00007FFEB012586D00007FFEB01049E0 torch_cpu.dll!at::_ops::view_as_real::redispatch [ @ ]
00007FFEB008695800007FFEB0086740 torch_cpu.dll!at::_ops::full::call [ @ ]
00007FFE92FDCD6F00007FFE92FD0AC0 cuda.cp312-win_amd64.pyd!PyInit_cuda [ @ ]
00007FFE92FE2F1900007FFE92FD0AC0 cuda.cp312-win_amd64.pyd!PyInit_cuda [ @ ]
00007FFE92FDAD3700007FFE92FD0AC0 cuda.cp312-win_amd64.pyd!PyInit_cuda [ @ ]
00007FFE92FDADB400007FFE92FD0AC0 cuda.cp312-win_amd64.pyd!PyInit_cuda [ @ ]
00007FFE92FCF9E900007FFE92FC6300 cuda.cp312-win_amd64.pyd!c10::ivalue::Object::operator= [ @ ]
00007FF839D479E400007FF839D473F4 python312.dll!PyThread_acquire_lock_timed [ @ ]
00007FF839D9201800007FF839D91990 python312.dll!PyObject_Vectorcall [ @ ]
00007FF839D919C500007FF839D91990 python312.dll!PyObject_Vectorcall [ @ ]
00007FF839D92EA500007FF839D92610 python312.dll!PyEval_EvalFrameDefault [ @ ]
00007FF839D9103C00007FF839D90EC0 python312.dll!PyFunction_Vectorcall [ @ ]
00007FF839DC281500007FF839DC26F0 python312.dll!PyObject_Call [ @ ]
00007FF839D193B700007FF839D1931C python312.dll!PyObject_Call [ @ ]
00007FF82570275F00007FF8256FD170 torch_python.dll!torch::autograd::registerFunctionPreHook [ @ ]
00007FF839D47A1600007FF839D473F4 python312.dll!PyThread_acquire_lock_timed [ @ ]
00007FF839DC27A600007FF839DC26F0 python312.dll!PyObject_Call [ @ ]
00007FF839D966EE00007FF839D92610 python312.dll!PyEval_EvalFrameDefault [ @ ]
00007FF839D9103C00007FF839D90EC0 python312.dll!PyFunction_Vectorcall [ @ ]
00007FF839D8BD8E00007FF839D8B9BC python312.dll!PyArg_CheckPositional [ @ ]
00007FF839DC281500007FF839DC26F0 python312.dll!PyObject_Call [ @ ]
00007FF839DC275F00007FF839DC26F0 python312.dll!PyObject_Call [ @ ]
00007FF839D966EE00007FF839D92610 python312.dll!PyEval_EvalFrameDefault [ @ ]
00007FF839D9103C00007FF839D90EC0 python312.dll!PyFunction_Vectorcall [ @ ]
00007FF839D8BD8E00007FF839D8B9BC python312.dll!PyArg_CheckPositional [ @ ]
00007FF839DC281500007FF839DC26F0 python312.dll!PyObject_Call [ @ ]
00007FF839DC275F00007FF839DC26F0 python312.dll!PyObject_Call [ @ ]
00007FF839D966EE00007FF839D92610 python312.dll!PyEval_EvalFrameDefault [ @ ]
00007FF839D9103C00007FF839D90EC0 python312.dll!PyFunction_Vectorcall [ @ ]
00007FF839DC3E8B00007FF839DC3E18 python312.dll!PyObject_FastCallDictTstate [ @ ]
00007FF839E6319B00007FF839E6311C python312.dll!PyObject_Call_Prepend [ @ ]
00007FF839E630C600007FF839E62DF0 python312.dll!PyDictProxy_New [ @ ]
00007FF839D9201800007FF839D91990 python312.dll!PyObject_Vectorcall [ @ ]
00007FF839D919C500007FF839D91990 python312.dll!PyObject_Vectorcall [ @ ]
00007FF839D92EA500007FF839D92610 python312.dll!PyEval_EvalFrameDefault [ @ ]
00007FF839D9103C00007FF839D90EC0 python312.dll!PyFunction_Vectorcall [ @ ]
00007FF839D8BD8E00007FF839D8B9BC python312.dll!PyArg_CheckPositional [ @ ]
00007FF839DC281500007FF839DC26F0 python312.dll!PyObject_Call [ @ ]
00007FF839DC275F00007FF839DC26F0 python312.dll!PyObject_Call [ @ ]

Traceback (most recent call last):
File "C:\KnG\ComfyUI-Easy-Install\ComfyUI-Easy-Install\ComfyUI\execution.py", line 518, in execute
output_data, output_ui, has_subgraph, has_pending_tasks = await get_output_data(prompt_id, unique_id, obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\KnG\ComfyUI-Easy-Install\ComfyUI-Easy-Install\ComfyUI\execution.py", line 329, in get_output_data
return_values = await _async_map_node_over_list(prompt_id, unique_id, obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\KnG\ComfyUI-Easy-Install\ComfyUI-Easy-Install\ComfyUI\execution.py", line 303, in _async_map_node_over_list
await process_inputs(input_dict, i)
File "C:\KnG\ComfyUI-Easy-Install\ComfyUI-Easy-Install\ComfyUI\execution.py", line 291, in process_inputs
result = f(**inputs)
^^^^^^^^^^^
File "C:\KnG\ComfyUI-Easy-Install\ComfyUI-Easy-Install\ComfyUI\custom_nodes\ComfyUI-Trellis2\nodes.py", line 838, in process
mesh = pipeline.run(image=image_in, seed=seed, pipeline_type=pipeline_type, sparse_structure_sampler_params = sparse_structure_sampler_params, shape_slat_sampler_params = shape_slat_sampler_params, tex_slat_sampler_params = tex_slat_sampler_params, max_num_tokens = max_num_tokens, sparse_structure_resolution = sparse_structure_resolution, max_views = max_views, generate_texture_slat=generate_texture_slat, pbar=pbar)[0]
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\KnG\ComfyUI-Easy-Install\ComfyUI-Easy-Install\python_embeded\Lib\site-packages\torch\utils_contextlib.py", line 120, in decorate_context
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "C:\KnG\ComfyUI-Easy-Install\ComfyUI-Easy-Install\ComfyUI\custom_nodes\ComfyUI-Trellis2\trellis2\pipelines\trellis2_image_to_3d.py", line 1113, in run
out_mesh = self.decode_latent(shape_slat, tex_slat, res)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\KnG\ComfyUI-Easy-Install\ComfyUI-Easy-Install\python_embeded\Lib\site-packages\torch\utils_contextlib.py", line 120, in decorate_context
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "C:\KnG\ComfyUI-Easy-Install\ComfyUI-Easy-Install\ComfyUI\custom_nodes\ComfyUI-Trellis2\trellis2\pipelines\trellis2_image_to_3d.py", line 794, in decode_latent
meshes, subs = self.decode_shape_slat(shape_slat, resolution)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\KnG\ComfyUI-Easy-Install\ComfyUI-Easy-Install\ComfyUI\custom_nodes\ComfyUI-Trellis2\trellis2\pipelines\trellis2_image_to_3d.py", line 683, in decode_shape_slat
ret = self.models['shape_slat_decoder'](slat, return_subs=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\KnG\ComfyUI-Easy-Install\ComfyUI-Easy-Install\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1773, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\KnG\ComfyUI-Easy-Install\ComfyUI-Easy-Install\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1784, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\KnG\ComfyUI-Easy-Install\ComfyUI-Easy-Install\ComfyUI\custom_nodes\ComfyUI-Trellis2\trellis2\models\sc_vaes\fdg_vae.py", line 85, in forward
decoded = super().forward(x, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\KnG\ComfyUI-Easy-Install\ComfyUI-Easy-Install\ComfyUI\custom_nodes\ComfyUI-Trellis2\trellis2\models\sc_vaes\sparse_unet_vae.py", line 610, in forward
h = block(h)
^^^^^^^^
File "C:\KnG\ComfyUI-Easy-Install\ComfyUI-Easy-Install\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1773, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\KnG\ComfyUI-Easy-Install\ComfyUI-Easy-Install\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1784, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\KnG\ComfyUI-Easy-Install\ComfyUI-Easy-Install\ComfyUI\custom_nodes\ComfyUI-Trellis2\trellis2\models\sc_vaes\sparse_unet_vae.py", line 373, in forward
return self._forward(x)
^^^^^^^^^^^^^^^^
File "C:\KnG\ComfyUI-Easy-Install\ComfyUI-Easy-Install\ComfyUI\custom_nodes\ComfyUI-Trellis2\trellis2\models\sc_vaes\sparse_unet_vae.py", line 360, in _forward
h = self.conv(x)
^^^^^^^^^^^^
File "C:\KnG\ComfyUI-Easy-Install\ComfyUI-Easy-Install\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1773, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\KnG\ComfyUI-Easy-Install\ComfyUI-Easy-Install\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1784, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\KnG\ComfyUI-Easy-Install\ComfyUI-Easy-Install\ComfyUI\custom_nodes\ComfyUI-Trellis2\trellis2\modules\sparse\conv\conv.py", line 19, in forward
return backends[config.CONV].sparse_conv3d_forward(self, x)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\KnG\ComfyUI-Easy-Install\ComfyUI-Easy-Install\ComfyUI\custom_nodes\ComfyUI-Trellis2\trellis2\modules\sparse\conv\conv_flex_gemm.py", line 46, in sparse_conv3d_forward
out, neighbor_cache = sparse_submanifold_conv3d(
^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\KnG\ComfyUI-Easy-Install\ComfyUI-Easy-Install\python_embeded\Lib\site-packages\flex_gemm\ops\spconv\submanifold_conv3d.py", line 372, in sparse_submanifold_conv3d
return SubMConv3dFunction.apply(feats, coords, shape, neighbor_cache, weight, bias, dilation)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\KnG\ComfyUI-Easy-Install\ComfyUI-Easy-Install\python_embeded\Lib\site-packages\torch\autograd\function.py", line 576, in apply
return super().apply(*args, **kwargs) # type: ignore[misc]
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\KnG\ComfyUI-Easy-Install\ComfyUI-Easy-Install\python_embeded\Lib\site-packages\flex_gemm\ops\spconv\submanifold_conv3d.py", line 318, in forward
neighbor_cache = SubMConv3dFunction._compute_neighbor_cache(coords, shape, (Kw, Kh, Kd), dilation)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\KnG\ComfyUI-Easy-Install\ComfyUI-Easy-Install\python_embeded\Lib\site-packages\flex_gemm\ops\spconv\submanifold_conv3d.py", line 52, in _compute_neighbor_cache
neighbor_map = kernels.cuda.hashmap_build_submanifold_conv_neighbour_map_cuda(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
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.

Exception raised from c10_cuda_check_implementation at C:\actions-runner_work\pytorch\pytorch\pytorch\c10\cuda\CUDAException.cpp:42 (most recent call first):
00007FF85EE8199400007FF85EE818F0 c10.dll!c10::Error::Error [ @ ]
00007FF85EE23BE800007FF85EE23BA0 c10.dll!c10::AcceleratorError::AcceleratorError [ @ ]
00007FF86405819200007FF864058050 c10_cuda.dll!c10::cuda::c10_cuda_check_implementation [ @ ]
00007FF86405E52500007FF864059380 c10_cuda.dll!c10::cuda::warn_or_error_on_sync [ @ ]
00007FF86405951900007FF864059380 c10_cuda.dll!c10::cuda::warn_or_error_on_sync [ @ ]
00007FF85EE43DA300007FF85EE43D40 c10.dll!c10::StorageImpl::StorageImpl [ @ ]
00007FFEAF1B32B100007FFEAF1B2B70 torch_cpu.dll!at::DynamicLibrary::sym [ @ ]
00007FFEAF1B55E400007FFEAF1B55B0 torch_cpu.dll!at::detail::empty_generic [ @ ]
00007FFE20901FB500007FFE20901ED0 torch_cuda.dll!at::detail::empty_cuda [ @ ]
00007FFE20901EAE00007FFE20901DF0 torch_cuda.dll!at::detail::empty_cuda [ @ ]
00007FFE20A33AA800007FFE20A33A40 torch_cuda.dll!at::native::empty_cuda [ @ ]
00007FFE22829BE100007FFE227CD080 torch_cuda.dll!at::cuda::where_outf [ @ ]
00007FFE2271B18E00007FFE226ABD00 torch_cuda.dll!at::cuda::bucketize_outf [ @ ]
00007FFEAFDF06D500007FFEAFD72630 torch_cpu.dll!at::_ops::xlogy__Tensor::redispatch [ @ ]
00007FFEAFEC4A9E00007FFEAFEC49C0 torch_cpu.dll!at::_ops::empty_memory_format::redispatch [ @ ]
00007FFEB012852100007FFEB01049E0 torch_cpu.dll!at::_ops::view_as_real::redispatch [ @ ]
00007FFEB012640E00007FFEB01049E0 torch_cpu.dll!at::_ops::view_as_real::redispatch [ @ ]
00007FFEAFE392EF00007FFEAFE390D0 torch_cpu.dll!at::_ops::empty_memory_format::call [ @ ]
00007FFEAF1C082200007FFEAF1C0700 torch_cpu.dll!onnx_torch::ModelProto::model_version [ @ ]
00007FFEAF73BEB900007FFEAF73BDA0 torch_cpu.dll!at::native::full [ @ ]
00007FFEB02464E400007FFEB0241850 torch_cpu.dll!at::compositeexplicitautograd::view_copy_symint_outf [ @ ]
00007FFEB021579D00007FFEB01CC3D0 torch_cpu.dll!at::compositeexplicitautograd::bucketize_outf [ @ ]
00007FFEB005111B00007FFEB00097E0 torch_cpu.dll!at::_ops::zeros_like_out::redispatch [ @ ]
00007FFEB00EB76D00007FFEB00EB690 torch_cpu.dll!at::_ops::full::redispatch [ @ ]
00007FFEB0128EE400007FFEB01049E0 torch_cpu.dll!at::_ops::view_as_real::redispatch [ @ ]
00007FFEB012586D00007FFEB01049E0 torch_cpu.dll!at::_ops::view_as_real::redispatch [ @ ]
00007FFEB008695800007FFEB0086740 torch_cpu.dll!at::_ops::full::call [ @ ]
00007FFE92FDCD6F00007FFE92FD0AC0 cuda.cp312-win_amd64.pyd!PyInit_cuda [ @ ]
00007FFE92FE2F1900007FFE92FD0AC0 cuda.cp312-win_amd64.pyd!PyInit_cuda [ @ ]
00007FFE92FDAD3700007FFE92FD0AC0 cuda.cp312-win_amd64.pyd!PyInit_cuda [ @ ]
00007FFE92FDADB400007FFE92FD0AC0 cuda.cp312-win_amd64.pyd!PyInit_cuda [ @ ]
00007FFE92FCF9E900007FFE92FC6300 cuda.cp312-win_amd64.pyd!c10::ivalue::Object::operator= [ @ ]
00007FF839D479E400007FF839D473F4 python312.dll!PyThread_acquire_lock_timed [ @ ]
00007FF839D9201800007FF839D91990 python312.dll!PyObject_Vectorcall [ @ ]
00007FF839D919C500007FF839D91990 python312.dll!PyObject_Vectorcall [ @ ]
00007FF839D92EA500007FF839D92610 python312.dll!PyEval_EvalFrameDefault [ @ ]
00007FF839D9103C00007FF839D90EC0 python312.dll!PyFunction_Vectorcall [ @ ]
00007FF839DC281500007FF839DC26F0 python312.dll!PyObject_Call [ @ ]
00007FF839D193B700007FF839D1931C python312.dll!PyObject_Call [ @ ]
00007FF82570275F00007FF8256FD170 torch_python.dll!torch::autograd::registerFunctionPreHook [ @ ]
00007FF839D47A1600007FF839D473F4 python312.dll!PyThread_acquire_lock_timed [ @ ]
00007FF839DC27A600007FF839DC26F0 python312.dll!PyObject_Call [ @ ]
00007FF839D966EE00007FF839D92610 python312.dll!PyEval_EvalFrameDefault [ @ ]
00007FF839D9103C00007FF839D90EC0 python312.dll!PyFunction_Vectorcall [ @ ]
00007FF839D8BD8E00007FF839D8B9BC python312.dll!PyArg_CheckPositional [ @ ]
00007FF839DC281500007FF839DC26F0 python312.dll!PyObject_Call [ @ ]
00007FF839DC275F00007FF839DC26F0 python312.dll!PyObject_Call [ @ ]
00007FF839D966EE00007FF839D92610 python312.dll!PyEval_EvalFrameDefault [ @ ]
00007FF839D9103C00007FF839D90EC0 python312.dll!PyFunction_Vectorcall [ @ ]
00007FF839D8BD8E00007FF839D8B9BC python312.dll!PyArg_CheckPositional [ @ ]
00007FF839DC281500007FF839DC26F0 python312.dll!PyObject_Call [ @ ]
00007FF839DC275F00007FF839DC26F0 python312.dll!PyObject_Call [ @ ]
00007FF839D966EE00007FF839D92610 python312.dll!PyEval_EvalFrameDefault [ @ ]
00007FF839D9103C00007FF839D90EC0 python312.dll!PyFunction_Vectorcall [ @ ]
00007FF839DC3E8B00007FF839DC3E18 python312.dll!PyObject_FastCallDictTstate [ @ ]
00007FF839E6319B00007FF839E6311C python312.dll!PyObject_Call_Prepend [ @ ]
00007FF839E630C600007FF839E62DF0 python312.dll!PyDictProxy_New [ @ ]
00007FF839D9201800007FF839D91990 python312.dll!PyObject_Vectorcall [ @ ]
00007FF839D919C500007FF839D91990 python312.dll!PyObject_Vectorcall [ @ ]
00007FF839D92EA500007FF839D92610 python312.dll!PyEval_EvalFrameDefault [ @ ]
00007FF839D9103C00007FF839D90EC0 python312.dll!PyFunction_Vectorcall [ @ ]
00007FF839D8BD8E00007FF839D8B9BC python312.dll!PyArg_CheckPositional [ @ ]
00007FF839DC281500007FF839DC26F0 python312.dll!PyObject_Call [ @ ]
00007FF839DC275F00007FF839DC26F0 python312.dll!PyObject_Call [ @ ]

Windows + RTX 2000 series + Nvidia Studio Driver 591.44
Python 3.12.10
torch 2.8.0+cu128

[Y007]

Update: I restarted comfy and now it just stuck at:

Loading Shape Slat decoder model......

Error above seems to be gone

Is the stuck related to model not offloaded to cpu? can you add option to offload to cpu?

[visualbruno]

Hi.

I already had this kind of error "CUDA kernel errors ..." and it was because of the version of "Flash Attention" was not good.
At the same time, did you install the wheels for your version of Torch and Python ? So in the folder "wheels/Windows/Torch280/"

[Y007]

Hello. Actually i don't use flash-attention due to my GPU not supported and xformers always fail to install so i added SDPA option to the code.

Yes i have installed the wheel successfully including the newly updated wheels & code with tiled decoder feature. As of now in my case there is no above error no more but still stuck on Loading Shape Slat decoder model......