CUDA error: operation not supported CUDA kernel errors

### Expected Behavior

CUDA error: operation not supported
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.

### Actual Behavior

CUDA error: operation not supported
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.

### Steps to Reproduce

CUDA error: operation not supported
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.

### Debug Logs

```powershell
CUDA error: operation not supported
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.
```

### Other

Queue size: 0
⚙️
×
Queue Prompt
Extra options
Queue FrontView QueueView History
Save
Load
Refresh
Clipspace
Clear
Load Default
Reset View
Manager
Share
text, watermark
beautiful sceneary nature glass bottle landscape, , purple galaxy bottle
KSampler
CUDA error: operation not supported
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.

# ComfyUI Error Report
## Error Details
- **Node Type:** KSampler
- **Exception Type:** RuntimeError
- **Exception Message:** CUDA error: operation not supported
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.

## Stack Trace
```
File "C:\1-ComfyU\ComfyUI_windows_portable\ComfyUI\execution.py", line 323, in execute
output_data, output_ui, has_subgraph = get_output_data(obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "C:\1-ComfyU\ComfyUI_windows_portable\ComfyUI\execution.py", line 198, in get_output_data
return_values = _map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "C:\1-ComfyU\ComfyUI_windows_portable\ComfyUI\execution.py", line 169, in _map_node_over_list
process_inputs(input_dict, i)

File "C:\1-ComfyU\ComfyUI_windows_portable\ComfyUI\execution.py", line 158, in process_inputs
results.append(getattr(obj, func)(**inputs))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "C:\1-ComfyU\ComfyUI_windows_portable\ComfyUI\nodes.py", line 1448, in sample
return common_ksampler(model, seed, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, denoise=denoise)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "C:\1-ComfyU\ComfyUI_windows_portable\ComfyUI\nodes.py", line 1415, in common_ksampler
samples = comfy.sample.sample(model, noise, steps, cfg, sampler_name, scheduler, positive, negative, latent_image,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "C:\1-ComfyU\ComfyUI_windows_portable\ComfyUI\comfy\sample.py", line 41, in sample
sampler = comfy.samplers.KSampler(model, steps=steps, device=model.load_device, sampler=sampler_name, scheduler=scheduler, denoise=denoise, model_options=model.model_options)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "C:\1-ComfyU\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 805, in __init__
self.set_steps(steps, denoise)

File "C:\1-ComfyU\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 826, in set_steps
self.sigmas = self.calculate_sigmas(steps).to(self.device)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

```
## System Information
- **ComfyUI Version:** v0.2.7-7-g75a818c
- **Arguments:** ComfyUI\main.py --windows-standalone-build
- **OS:** nt
- **Python Version:** 3.12.7 (tags/v3.12.7:0b05ead, Oct 1 2024, 03:06:41) [MSC v.1941 64 bit (AMD64)]
- **Embedded Python:** true
- **PyTorch Version:** 2.5.0+cu124
## Devices

- **Name:** cuda:0 NVIDIA GeForce 840M : cudaMallocAsync
- **Type:** cuda
- **VRAM Total:** 4294836224
- **VRAM Free:** 3587424256
- **Torch VRAM Total:** 0
- **Torch VRAM Free:** 0

## Logs
```
2024-11-08 19:01:52,519 - root - INFO - Total VRAM 4096 MB, total RAM 16292 MB
2024-11-08 19:01:52,519 - root - INFO - pytorch version: 2.5.0+cu124
2024-11-08 19:01:52,523 - root - INFO - Set vram state to: NORMAL_VRAM
2024-11-08 19:01:52,523 - root - INFO - Device: cuda:0 NVIDIA GeForce 840M : cudaMallocAsync
2024-11-08 19:01:55,092 - root - INFO - Using pytorch cross attention
2024-11-08 19:01:58,516 - root - INFO - [Prompt Server] web root: C:\1-ComfyU\ComfyUI_windows_portable\ComfyUI\web
2024-11-08 19:02:00,147 - root - INFO -
Import times for custom nodes:
2024-11-08 19:02:00,148 - root - INFO - 0.0 seconds: C:\1-ComfyU\ComfyUI_windows_portable\ComfyUI\custom_nodes\websocket_image_save.py
2024-11-08 19:02:00,150 - root - INFO - 0.5 seconds: C:\1-ComfyU\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Manager
2024-11-08 19:02:00,151 - root - INFO -
2024-11-08 19:02:00,153 - root - WARNING -
WARNING: this card most likely does not support cuda-malloc, if you get "CUDA error" please run ComfyUI with: --disable-cuda-malloc

2024-11-08 19:02:00,165 - root - INFO - Starting server

2024-11-08 19:02:00,166 - root - INFO - To see the GUI go to: http://127.0.0.1:8188
2024-11-08 19:02:19,986 - asyncio - ERROR - Exception in callback _ProactorBasePipeTransport._call_connection_lost(None)
handle:
Traceback (most recent call last):
File "asyncio\events.py", line 88, in _run
File "asyncio\proactor_events.py", line 165, in _call_connection_lost
ConnectionResetError: [WinError 10054] An existing connection was forcibly closed by the remote host
2024-11-08 19:03:01,453 - root - INFO - got prompt
2024-11-08 19:03:01,668 - root - INFO - model weight dtype torch.bfloat16, manual cast: torch.float32
2024-11-08 19:03:01,671 - root - INFO - model_type EPS
2024-11-08 19:03:11,285 - root - INFO - Using pytorch attention in VAE
2024-11-08 19:03:11,293 - root - INFO - Using pytorch attention in VAE
2024-11-08 19:03:11,838 - root - INFO - Requested to load SD1ClipModel
2024-11-08 19:03:11,838 - root - INFO - Loading 1 new model
2024-11-08 19:03:11,854 - root - INFO - loaded completely 0.0 235.84423828125 True
2024-11-08 19:03:13,556 - root - ERROR - !!! Exception during processing !!! CUDA error: operation not supported
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.

2024-11-08 19:03:13,562 - root - ERROR - Traceback (most recent call last):
File "C:\1-ComfyU\ComfyUI_windows_portable\ComfyUI\execution.py", line 323, in execute
output_data, output_ui, has_subgraph = get_output_data(obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\1-ComfyU\ComfyUI_windows_portable\ComfyUI\execution.py", line 198, in get_output_data
return_values = _map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\1-ComfyU\ComfyUI_windows_portable\ComfyUI\execution.py", line 169, in _map_node_over_list
process_inputs(input_dict, i)
File "C:\1-ComfyU\ComfyUI_windows_portable\ComfyUI\execution.py", line 158, in process_inputs
results.append(getattr(obj, func)(**inputs))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\1-ComfyU\ComfyUI_windows_portable\ComfyUI\nodes.py", line 1448, in sample
return common_ksampler(model, seed, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, denoise=denoise)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\1-ComfyU\ComfyUI_windows_portable\ComfyUI\nodes.py", line 1415, in common_ksampler
samples = comfy.sample.sample(model, noise, steps, cfg, sampler_name, scheduler, positive, negative, latent_image,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\1-ComfyU\ComfyUI_windows_portable\ComfyUI\comfy\sample.py", line 41, in sample
sampler = comfy.samplers.KSampler(model, steps=steps, device=model.load_device, sampler=sampler_name, scheduler=scheduler, denoise=denoise, model_options=model.model_options)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\1-ComfyU\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 805, in __init__
self.set_steps(steps, denoise)
File "C:\1-ComfyU\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 826, in set_steps
self.sigmas = self.calculate_sigmas(steps).to(self.device)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
RuntimeError: CUDA error: operation not supported
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.

2024-11-08 19:03:13,569 - root - INFO - Prompt executed in 12.11 seconds
2024-11-08 19:04:32,516 - root - INFO - got prompt
2024-11-08 19:04:32,562 - root - ERROR - !!! Exception during processing !!! CUDA error: operation not supported
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.

2024-11-08 19:04:32,566 - root - ERROR - Traceback (most recent call last):
File "C:\1-ComfyU\ComfyUI_windows_portable\ComfyUI\execution.py", line 323, in execute
output_data, output_ui, has_subgraph = get_output_data(obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\1-ComfyU\ComfyUI_windows_portable\ComfyUI\execution.py", line 198, in get_output_data
return_values = _map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\1-ComfyU\ComfyUI_windows_portable\ComfyUI\execution.py", line 169, in _map_node_over_list
process_inputs(input_dict, i)
File "C:\1-ComfyU\ComfyUI_windows_portable\ComfyUI\execution.py", line 158, in process_inputs
results.append(getattr(obj, func)(**inputs))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\1-ComfyU\ComfyUI_windows_portable\ComfyUI\nodes.py", line 1448, in sample
return common_ksampler(model, seed, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, denoise=denoise)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\1-ComfyU\ComfyUI_windows_portable\ComfyUI\nodes.py", line 1415, in common_ksampler
samples = comfy.sample.sample(model, noise, steps, cfg, sampler_name, scheduler, positive, negative, latent_image,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\1-ComfyU\ComfyUI_windows_portable\ComfyUI\comfy\sample.py", line 41, in sample
sampler = comfy.samplers.KSampler(model, steps=steps, device=model.load_device, sampler=sampler_name, scheduler=scheduler, denoise=denoise, model_options=model.model_options)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\1-ComfyU\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 805, in __init__
self.set_steps(steps, denoise)
File "C:\1-ComfyU\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 826, in set_steps
self.sigmas = self.calculate_sigmas(steps).to(self.device)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
RuntimeError: CUDA error: operation not supported
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.

2024-11-08 19:04:32,573 - root - INFO - Prompt executed in 0.05 seconds
```
## Attached Workflow
Please make sure that workflow does not contain any sensitive information such as API keys or passwords.
```
{"last_node_id":9,"last_link_id":9,"nodes":[{"id":7,"type":"CLIPTextEncode","pos":{"0":413,"1":389},"size":{"0":425.27801513671875,"1":180.6060791015625},"flags":{},"order":3,"mode":0,"inputs":[{"name":"clip","type":"CLIP","link":5}],"outputs":[{"name":"CONDITIONING","type":"CONDITIONING","links":[6],"slot_index":0}],"properties":{"Node name for S&R":"CLIPTextEncode"},"widgets_values":["text, watermark"]},{"id":5,"type":"EmptyLatentImage","pos":{"0":473,"1":609},"size":{"0":315,"1":106},"flags":{},"order":0,"mode":0,"inputs":[],"outputs":[{"name":"LATENT","type":"LATENT","links":[2],"slot_index":0}],"properties":{"Node name for S&R":"EmptyLatentImage"},"widgets_values":[512,512,1]},{"id":8,"type":"VAEDecode","pos":{"0":1209,"1":188},"size":{"0":210,"1":46},"flags":{},"order":5,"mode":0,"inputs":[{"name":"samples","type":"LATENT","link":7},{"name":"vae","type":"VAE","link":8}],"outputs":[{"name":"IMAGE","type":"IMAGE","links":[9],"slot_index":0}],"properties":{"Node name for S&R":"VAEDecode"},"widgets_values":[]},{"id":9,"type":"SaveImage","pos":{"0":1451,"1":189},"size":{"0":210,"1":58},"flags":{},"order":6,"mode":0,"inputs":[{"name":"images","type":"IMAGE","link":9}],"outputs":[],"properties":{},"widgets_values":["ComfyUI"]},{"id":4,"type":"CheckpointLoaderSimple","pos":{"0":26,"1":474},"size":{"0":315,"1":98},"flags":{},"order":1,"mode":0,"inputs":[],"outputs":[{"name":"MODEL","type":"MODEL","links":[1],"slot_index":0},{"name":"CLIP","type":"CLIP","links":[3,5],"slot_index":1},{"name":"VAE","type":"VAE","links":[8],"slot_index":2}],"properties":{"Node name for S&R":"CheckpointLoaderSimple"},"widgets_values":["dreamshaper_8.safetensors"]},{"id":6,"type":"CLIPTextEncode","pos":{"0":415,"1":186},"size":{"0":422.84503173828125,"1":164.31304931640625},"flags":{},"order":2,"mode":0,"inputs":[{"name":"clip","type":"CLIP","link":3}],"outputs":[{"name":"CONDITIONING","type":"CONDITIONING","links":[4],"slot_index":0}],"properties":{"Node name for S&R":"CLIPTextEncode"},"widgets_values":["beautiful sceneary nature glass bottle landscape, , purple galaxy bottle"]},{"id":3,"type":"KSampler","pos":{"0":863,"1":186},"size":{"0":315,"1":262},"flags":{},"order":4,"mode":0,"inputs":[{"name":"model","type":"MODEL","link":1},{"name":"positive","type":"CONDITIONING","link":4},{"name":"negative","type":"CONDITIONING","link":6},{"name":"latent_image","type":"LATENT","link":2}],"outputs":[{"name":"LATENT","type":"LATENT","links":[7],"slot_index":0}],"properties":{"Node name for S&R":"KSampler"},"widgets_values":[477202173605177,"randomize",20,8,"euler","normal",1]}],"links":[[1,4,0,3,0,"MODEL"],[2,5,0,3,3,"LATENT"],[3,4,1,6,0,"CLIP"],[4,6,0,3,1,"CONDITIONING"],[5,4,1,7,0,"CLIP"],[6,7,0,3,2,"CONDITIONING"],[7,3,0,8,0,"LATENT"],[8,4,2,8,1,"VAE"],[9,8,0,9,0,"IMAGE"]],"groups":[],"config":{},"extra":{"ds":{"scale":1,"offset":[0,0]}},"version":0.4}
```

## Additional Context
(Please add any additional context or steps to reproduce the error here)