Wan2GP: [GGUF][llama.cpp CUDA] kernels unavailable, using fallback

App: Wan2GP (wan.git)
Repo: https://github.com/pinokiofactory/wan.git
Generated: 2026-07-25T18:35:15.700Z
Pinokio: 8.0.40
Platform: win32 x64
Node: v22.21.1

Summary

System

{
  "pinokio": {
    "version": "8.0.40",
    "node": "v22.21.1",
    "platform": "win32",
    "arch": "x64"
  },
  "hardware": {
    "gpu": "nvidia",
    "gpu_model": "nvidia geforce gt 1030",
    "ram_gb": 8,
    "vram_gb": 2
  },
  "os": {
    "platform": "Windows",
    "distro": "Microsoft Windows 10 Home",
    "release": "10.0.19045",
    "codename": "22H2",
    "kernel": "10.0.19045",
    "arch": "x64",
    "build": "19045",
    "servicepack": "0.0",
    "uefi": true
  },
  "system": {
    "manufacturer": "Hewlett-Packard",
    "model": "HP Compaq Pro 6300 SFF",
    "virtual": false
  },
  "cpu": {
    "manufacturer": "Intel",
    "brand": "Core™ i5-3470",
    "vendor": "GenuineIntel",
    "family": "6",
    "model": "58",
    "stepping": "9",
    "revision": "14857",
    "speed": 3.2,
    "speedMin": 3.2,
    "speedMax": 3.2,
    "cores": 4,
    "physicalCores": 4,
    "processors": 1,
    "performanceCores": 4,
    "efficiencyCores": 0,
    "virtualization": false,
    "cache": {
      "l1d": 128,
      "l1i": 128,
      "l2": 1048576,
      "l3": 6291456
    }
  },
  "memory": {
    "total": 8457838592,
    "free": 3799425024,
    "used": 4658413568,
    "active": 4658413568,
    "available": 3799425024,
    "buffers": 0,
    "cached": 0,
    "slab": 0,
    "buffcache": 0,
    "swaptotal": 2856321024,
    "swapused": 117440512,
    "swapfree": 2738880512
  },
  "gpus": [
    {
      "model": "meta virtual monitor"
    },
    {
      "model": "intel(r) hd graphics"
    },
    {
      "model": "nvidia geforce gt 1030"
    }
  ],
  "graphics": {
    "controllers": [
      {
        "vendor": "Meta Inc.",
        "model": "Meta Virtual Monitor",
        "vram": 0,
        "vramDynamic": true
      },
      {
        "vendor": "Intel Corporation",
        "model": "Intel(R) HD Graphics",
        "bus": "PCI",
        "vram": 2112,
        "vramDynamic": true
      },
      {
        "vendor": "NVIDIA",
        "model": "NVIDIA GeForce GT 1030",
        "bus": "PCI",
        "vram": 2048,
        "vramDynamic": false,
        "driverVersion": "582.53"
      }
    ],
    "displays": [
      {
        "model": "10001589",
        "main": true,
        "builtin": false,
        "connection": "HDMI",
        "currentResX": 1280,
        "currentResY": 720,
        "resolutionX": 1920,
        "resolutionY": 1080,
        "pixelDepth": 32,
        "currentRefreshRate": 60
      }
    ]
  }
}

Logs

logs/api/start.js/1785003249091

Source: api / start.js
Lines: 12 total, last 12 included

[api shell.run]
Microsoft Windows [Version 10.0.19045.7417]
(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\activat
e C:\pinokio\api\wan.git\app\env && python wgp.py --multiple-images
[GGUF][llama.cpp CUDA] kernels unavailable, using fallback
Switching to FP16 models when possible as GPU architecture doesn't support optimed BF16 Kernels
Traceback (most recent call last):
  File "C:\pinokio\api\wan.git\app\wgp.py", line 3233, in <module>
    attention_mode = server_config["attention_mode"]
KeyError: 'attention_mode'