two workers got created automatically after first install, main gpu is 5070ti, two others gpus are 3080 with 10gb vram. Flash yellow then red.

[fengwoodson]

Please kindly help, thanks a lot. The error log is attached as following:

==================================================
=== ComfyUI Worker Session Started ===
Worker: Worker 1
Port: 8189
CUDA Device: 1
Started: 2025-10-19 20:46:42
Command: D:\AI\ComfyUI_Mie_V6.01\python_embeded\python.exe D:\AI\ComfyUI_Mie_V6.01\ComfyUI\main.py --port 8189 --enable-cors-header
Note: Worker will stop when master shuts down

[Worker Monitor] Monitoring master PID: 10644
Adding extra search path checkpoints F:\ComfyUI_Models\models\checkpoints
Adding extra search path gligen F:\ComfyUI_Models\models\gligen
Adding extra search path configs F:\ComfyUI_Models\models\configs
Adding extra search path loras F:\ComfyUI_Models\models\loras
Adding extra search path vae F:\ComfyUI_Models\models\vae
Adding extra search path clip F:\ComfyUI_Models\models\clip
Adding extra search path text_encoders F:\ComfyUI_Models\models\text_encoders
Adding extra search path diffusion_models F:\ComfyUI_Models\models\diffusion_models
Adding extra search path diffusion_models F:\ComfyUI_Models\models\unet
Adding extra search path clip_vision F:\ComfyUI_Models\models\clip_vision
Adding extra search path style_models F:\ComfyUI_Models\models\style_models
Adding extra search path embeddings F:\ComfyUI_Models\models\embeddings
Adding extra search path diffusers F:\ComfyUI_Models\models\diffusers
Adding extra search path vae_approx F:\ComfyUI_Models\models\vae_approx
Adding extra search path controlnet F:\ComfyUI_Models\models\controlnet
Adding extra search path controlnet F:\ComfyUI_Models\models\t2i_adapter
Adding extra search path upscale_models F:\ComfyUI_Models\models\upscale_models
Adding extra search path hypernetworks F:\ComfyUI_Models\models\hypernetworks
Adding extra search path photomaker F:\ComfyUI_Models\models\photomaker
Adding extra search path classifiers F:\ComfyUI_Models\models\classifiers
Starting up lumi_batcher_service...
Registering lumi_batcher_service module...
Successfully registered module: lumi_batcher_service
lumi_batcher_service started successfully.
[START] Security scan
[DONE] Security scan

ComfyUI-Manager: installing dependencies done.

** ComfyUI startup time: 2025-10-19 20:46:44.387
** Platform: Windows
** Python version: 3.12.10 (tags/v3.12.10:0cc8128, Apr 8 2025, 12:21:36) [MSC v.1943 64 bit (AMD64)]
** Python executable: D:\AI\ComfyUI_Mie_V6.01\python_embeded\python.exe
** ComfyUI Path: D:\AI\ComfyUI_Mie_V6.01\ComfyUI
** ComfyUI Base Folder Path: D:\AI\ComfyUI_Mie_V6.01\ComfyUI
** User directory: D:\AI\ComfyUI_Mie_V6.01\ComfyUI\user
** ComfyUI-Manager config path: D:\AI\ComfyUI_Mie_V6.01\ComfyUI\user\default\ComfyUI-Manager\config.ini
** Log path: D:\AI\ComfyUI_Mie_V6.01\ComfyUI\user\comfyui.log
[ComfyUI-Manager] WARN: Unsafe - SSL verification bypass option is Enabled. (see D:\AI\ComfyUI_Mie_V6.01\ComfyUI\user\default\ComfyUI-Manager\config.ini)

Prestartup times for custom nodes:
0.0 seconds: D:\AI\ComfyUI_Mie_V6.01\ComfyUI\custom_nodes\rgthree-comfy
0.0 seconds: D:\AI\ComfyUI_Mie_V6.01\ComfyUI\custom_nodes\comfyui-lumi-batcher
3.4 seconds: D:\AI\ComfyUI_Mie_V6.01\ComfyUI\custom_nodes\ComfyUI-Manager

Checkpoint files will always be loaded safely.
Traceback (most recent call last):
File "D:\AI\ComfyUI_Mie_V6.01\ComfyUI\main.py", line 138, in
import execution
File "D:\AI\ComfyUI_Mie_V6.01\ComfyUI\execution.py", line 15, in
import comfy.model_management
File "D:\AI\ComfyUI_Mie_V6.01\ComfyUI\comfy\model_management.py", line 221, in
total_vram = get_total_memory(get_torch_device()) / (1024 * 1024)
^^^^^^^^^^^^^^^^^^
File "D:\AI\ComfyUI_Mie_V6.01\ComfyUI\comfy\model_management.py", line 172, in get_torch_device
return torch.device(torch.cuda.current_device())
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\lifen\AppData\Roaming\Python\Python312\site-packages\torch\cuda_init_.py", line 940, in current_device
lazy_init()
File "C:\Users\lifen\AppData\Roaming\Python\Python312\site-packages\torch\cuda_init.py", line 310, in _lazy_init
raise AssertionError("Torch not compiled with CUDA enabled")
AssertionError: Torch not compiled with CUDA enabled
[Distributed] Started worker PID: 6364
[Distributed] Monitoring master PID: 10644
[Distributed] Worker process exited with code: 1