Wan2GP: raise AssertionError("Torch not compiled with CUDA enabled")

App: Wan2GP (wan.git)
Repo: https://github.com/pinokiofactory/wan.git
Generated: 2026-07-18T08:57:20.203Z
Pinokio: 8.0.31
Platform: win32 x64
Node: v22.21.1

Summary

System

{
  "pinokio": {
    "version": "8.0.31",
    "node": "v22.21.1",
    "platform": "win32",
    "arch": "x64"
  },
  "hardware": {
    "gpu": "intel corporation",
    "gpu_model": "intel(r) uhd graphics 620",
    "ram_gb": 16,
    "vram_gb": 1
  },
  "os": {
    "platform": "Windows",
    "distro": "Microsoft Windows 11 Pro",
    "release": "10.0.26200",
    "codename": "25H2",
    "kernel": "10.0.26200",
    "arch": "x64",
    "build": "26200",
    "servicepack": "0.0",
    "uefi": true
  },
  "system": {
    "manufacturer": "LENOVO",
    "model": "20LXS3LJ00",
    "version": "ThinkPad L580",
    "virtual": false
  },
  "cpu": {
    "manufacturer": "Intel",
    "brand": "Core™ i5-8250U",
    "vendor": "GenuineIntel",
    "family": "6",
    "model": "142",
    "stepping": "10",
    "speed": 1.6,
    "speedMin": 1.6,
    "speedMax": 1.8,
    "cores": 8,
    "physicalCores": 4,
    "processors": 1,
    "performanceCores": 8,
    "efficiencyCores": 0,
    "virtualization": false,
    "cache": {
      "l1d": 128,
      "l1i": 128,
      "l2": 1048576,
      "l3": 6291456
    }
  },
  "memory": {
    "total": 17026777088,
    "free": 5000179712,
    "used": 12026597376,
    "active": 12026597376,
    "available": 5000179712,
    "buffers": 0,
    "cached": 0,
    "slab": 0,
    "buffcache": 0,
    "swaptotal": 1073741824,
    "swapused": 97517568,
    "swapfree": 976224256
  },
  "gpus": [
    {
      "model": "intel(r) uhd graphics 620"
    }
  ],
  "graphics": {
    "controllers": [
      {
        "vendor": "Intel Corporation",
        "model": "Intel(R) UHD Graphics 620",
        "bus": "PCI",
        "vram": 1024,
        "vramDynamic": true
      }
    ],
    "displays": [
      {
        "model": "Wide viewing angle & High density FlexView Display 1920x1080",
        "main": true,
        "builtin": true,
        "connection": "INTERNAL",
        "currentResX": 1536,
        "currentResY": 864,
        "resolutionX": 1920,
        "resolutionY": 1080,
        "pixelDepth": 32,
        "currentRefreshRate": 60
      }
    ]
  }
}

Logs

logs/api/start.js/1784364724044

Source: api / start.js
Lines: 22 total, last 22 included

[api shell.run]
Microsoft Windows [Version 10.0.26200.8037]
(c) Microsoft Corporation. All rights reserved.

C:\pinokio\api\wan.git\app>conda_hook & conda deactivate & conda deactivate & conda deactivate & conda activate base & C:\pinokio\api\wan.git\app\env\Scripts\activate C:\pinokio\api\wan.git\app\env & bluefairy-activate.cmd && python wgp.py --multiple-images 
[OK] bluefairy active: uv/npm/bun protection enabled
C:\pinokio\api\wan.git\app\env\lib\site-packages\diffusers\models\transformers\transformer_kandinsky.py:168: UserWarning: CUDA is not available or torch_xla is imported. Disabling autocast.
  @torch.autocast(device_type="cuda", dtype=torch.float32)
C:\pinokio\api\wan.git\app\env\lib\site-packages\diffusers\models\transformers\transformer_kandinsky.py:272: UserWarning: CUDA is not available or torch_xla is imported. Disabling autocast.
  @torch.autocast(device_type="cuda", dtype=torch.float32)
Traceback (most recent call last):
  File "C:\pinokio\api\wan.git\app\wgp.py", line 69, in <module>
    from shared.attention import get_attention_modes, get_supported_attention_modes, get_default_attention_mode
  File "C:\pinokio\api\wan.git\app\shared\attention.py", line 14, in <module>
    major, minor = (0, 0) if _is_mps else torch.cuda.get_device_capability(None)
  File "C:\pinokio\api\wan.git\app\env\lib\site-packages\torch\cuda\__init__.py", line 720, in get_device_capability
    prop = get_device_properties(device)
  File "C:\pinokio\api\wan.git\app\env\lib\site-packages\torch\cuda\__init__.py", line 737, in get_device_properties
    _lazy_init()  # will define _get_device_properties
  File "C:\pinokio\api\wan.git\app\env\lib\site-packages\torch\cuda\__init__.py", line 522, in _lazy_init
    raise AssertionError("Torch not compiled with CUDA enabled")
AssertionError: Torch not compiled with CUDA enabled