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

App: Wan2GP - AMD (wan2gp-amd.git)
Repo: https://github.com/6Morpheus6/wan2gp-amd.git
Generated: 2026-08-09T12:47:29.189Z
Pinokio: 8.0.40
Platform: win32 x64
Node: v22.21.1

Summary

im posting this cuz i need help with this i wana make it work but idk how tbh i tried many things but nothing works if somebody can help me THX!! Wan2GP - AMD: raise AssertionError("Torch not compiled with CUDA enabled")

System

{
  "pinokio": {
    "version": "8.0.40",
    "node": "v22.21.1",
    "platform": "win32",
    "arch": "x64"
  },
  "hardware": {
    "gpu": "amd",
    "gpu_model": "amd radeon rx 7600 xt",
    "ram_gb": 16,
    "vram_gb": 16
  },
  "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": "Gigabyte Technology Co., Ltd.",
    "model": "B550M AORUS ELITE",
    "version": "-CF",
    "virtual": false
  },
  "cpu": {
    "manufacturer": "AMD",
    "brand": "Ryzen 7 5800X 8-Core Processor",
    "vendor": "AuthenticAMD",
    "family": "25",
    "model": "33",
    "stepping": "2",
    "revision": "8450",
    "speed": 3.8,
    "speedMin": 3.8,
    "speedMax": 3.8,
    "cores": 16,
    "physicalCores": 8,
    "processors": 1,
    "performanceCores": 16,
    "efficiencyCores": 0,
    "virtualization": true,
    "cache": {
      "l1d": 256,
      "l1i": 256,
      "l2": 4194304,
      "l3": 33554432
    }
  },
  "memory": {
    "total": 17098874880,
    "free": 8847458304,
    "used": 8251416576,
    "active": 8251416576,
    "available": 8847458304,
    "buffers": 0,
    "cached": 0,
    "slab": 0,
    "buffcache": 0,
    "swaptotal": 3548381184,
    "swapused": 67108864,
    "swapfree": 3481272320
  },
  "gpus": [
    {
      "model": "amd radeon rx 7600 xt"
    }
  ],
  "graphics": {
    "controllers": [
      {
        "vendor": "Advanced Micro Devices, Inc.",
        "model": "AMD Radeon RX 7600 XT",
        "bus": "PCI",
        "vram": 16368,
        "vramDynamic": true
      }
    ],
    "displays": [
      {
        "model": "Oyssy G40B",
        "main": true,
        "builtin": false,
        "connection": "DP",
        "currentResX": 1920,
        "currentResY": 1080,
        "resolutionX": 1920,
        "resolutionY": 1080,
        "pixelDepth": 32,
        "currentRefreshRate": 240
      },
      {
        "model": "VX8",
        "main": false,
        "builtin": false,
        "connection": "HDMI",
        "currentResX": 1920,
        "currentResY": 1080,
        "resolutionX": 1920,
        "resolutionY": 1080,
        "pixelDepth": 32,
        "currentRefreshRate": 240
      }
    ]
  }
}

Logs

logs/api/start.js/1786279629008

Source: api / start.js
Lines: 23 total, last 23 included

[api shell.run]
Microsoft Windows [Version 10.0.26200.8875]
(c) Microsoft Corporation. All rights reserved.

C:\pinokio\api\wan2gp-amd.git\app>conda_hook & conda deactivate & conda deactivate & conda deactivate & conda activate base & C:\pinokio\api\wan2gp-amd.git\app\env\Scripts\activate C:\pinokio\api\wan2gp-amd.git\app\env && python wgp.py
C:\pinokio\api\wan2gp-amd.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\wan2gp-amd.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\wan2gp-amd.git\app\wgp.py", line 69, in <module>
    from shared.attention import ATTENTION_MODE_AVAILABILITY, get_attention_modes, get_supported_attention_modes, get_default_attention_mode, get_override_attention_modes, get_supported_override_attention_modes
  File "C:\pinokio\api\wan2gp-amd.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\wan2gp-amd.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\wan2gp-amd.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\wan2gp-amd.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

(env) (base) C:\pinokio\api\wan2gp-amd.git\app>

logs/api/start.js/1786279646176

Source: api / start.js
Lines: 19 total, last 19 included

[memory]
{"ts":1786279646176,"step":1,"input":{"id":"c19bb6ad-8396-4bca-8eb7-6a18fd40f293"},"args":{},"global":{},"local":{},"port":42003}

[api local.set]


===================================================

[api local.set]
# local variables

[api local.set]
{
  "url": "{{input.event[0]}}"
}
[api local.set]

===================================================