Wan2GP: Abort trap: 6 python wgp.py --multiple-images --advanced

App: Wan2GP (wan.git)
Repo: https://github.com/pinokiofactory/wan.git
Generated: 2026-08-08T15:29:19.077Z
Pinokio: 8.0.40
Platform: darwin arm64
Node: v22.21.1

Summary

System

{
  "pinokio": {
    "version": "8.0.40",
    "node": "v22.21.1",
    "platform": "darwin",
    "arch": "arm64"
  },
  "hardware": {
    "gpu": "apple",
    "gpu_model": "apple m4 max",
    "ram_gb": 128,
    "vram_gb": 0
  },
  "os": {
    "platform": "darwin",
    "distro": "macOS",
    "release": "26.5.2",
    "codename": "Tahoe",
    "kernel": "25.5.0",
    "arch": "arm64",
    "build": "25F84",
    "uefi": true
  },
  "system": {
    "manufacturer": "Apple Inc.",
    "model": "Mac16,5",
    "version": "MacBook Pro (16-inch, M4 Pro, 2024)",
    "virtual": false
  },
  "cpu": {
    "manufacturer": "Apple",
    "brand": "M4 Max",
    "vendor": "Apple",
    "family": "399882554",
    "stepping": "5",
    "speed": 2.4,
    "speedMin": 2.4,
    "speedMax": 2.4,
    "cores": 16,
    "physicalCores": 16,
    "processors": 1,
    "performanceCores": 12,
    "efficiencyCores": 4,
    "virtualization": true,
    "cache": {
      "l1d": 65536,
      "l1i": 131072,
      "l2": 4194304
    }
  },
  "memory": {
    "total": 137438953472,
    "free": 2093219840,
    "used": 135345733632,
    "active": 65908654080,
    "available": 71530299392,
    "buffers": 0,
    "cached": 0,
    "slab": 0,
    "buffcache": 69437079552,
    "swaptotal": 0,
    "swapused": 0,
    "swapfree": 0
  },
  "gpus": [
    {
      "model": "apple m4 max"
    }
  ],
  "graphics": {
    "controllers": [
      {
        "vendor": "Apple",
        "model": "Apple M4 Max",
        "bus": "Built-In",
        "vramDynamic": true,
        "cores": "40"
      }
    ],
    "displays": [
      {
        "model": "Color LCD",
        "main": true,
        "builtin": true,
        "connection": "Internal",
        "currentResX": 1728,
        "currentResY": 1117,
        "resolutionX": 3456,
        "resolutionY": 2234,
        "currentRefreshRate": 120
      },
      {
        "model": "LG ULTRAGEAR",
        "main": false,
        "builtin": false,
        "currentResX": 2560,
        "currentResY": 1440,
        "resolutionX": 2560,
        "resolutionY": 1440,
        "currentRefreshRate": 100
      },
      {
        "model": "DELL P2419HC",
        "main": false,
        "builtin": false,
        "currentResX": 1920,
        "currentResY": 1080,
        "resolutionX": 1920,
        "resolutionY": 1080,
        "currentRefreshRate": 60
      }
    ]
  }
}

Logs

logs/api/start.js/1786202436480

Source: api / start.js
Lines: 38 total, last 38 included

[api shell.run]
<<PINOKIO_SHELL>>eval "$(conda shell.bash hook)" ; conda deactivate ; conda deactivate ; conda deactivate ; conda activate base ; source /Users/chufal/pinokio/api/wan.git/app/venv/bin/activate /Users/chufal/pinokio/api/wan.git/app/venv && python wgp.py --multiple-images --advanced 
[MPS Patch] Detected: Apple M4 Max, 128GB RAM
[MPS Patch] Device capability: (11, 0), BF16: True
[MPS Patch] Applied successfully
[MPS Patch] BF16 supported: True
[MPS Patch] Available system RAM: 128GB
[MPS Patch] Detected: Apple M4 Max, 128GB RAM
[MPS Patch] Device capability: (11, 0), BF16: True
[MPS Patch] Applied successfully
[MPS Patch] BF16 supported: True
[MPS Patch] Available system RAM: 128GB
/Users/chufal/pinokio/api/wan.git/app/shared/mps/device_patch.py:193: UserWarning: In MPS autocast, but the target dtype is not supported. Disabling autocast.
MPS Autocast only supports dtypes of torch.bfloat16, torch.float16 currently.
  return _orig_autocast(device_type, *args, **kwargs)
[GGUF][llama.cpp CUDA] kernels unavailable, using fallback
objc[37120]: Class AVFFrameReceiver is implemented in both /Users/chufal/pinokio/api/wan.git/app/venv/lib/python3.10/site-packages/cv2/.dylibs/libavdevice.61.3.100.dylib (0x152e943a8) and /Users/chufal/pinokio/api/wan.git/app/venv/lib/python3.10/site-packages/av/.dylibs/libavdevice.62.3.101.dylib (0x151abc3a8). This may cause spurious casting failures and mysterious crashes. One of the duplicates must be removed or renamed.
objc[37120]: Class AVFAudioReceiver is implemented in both /Users/chufal/pinokio/api/wan.git/app/venv/lib/python3.10/site-packages/cv2/.dylibs/libavdevice.61.3.100.dylib (0x152e943f8) and /Users/chufal/pinokio/api/wan.git/app/venv/lib/python3.10/site-packages/av/.dylibs/libavdevice.62.3.101.dylib (0x151abc3f8). This may cause spurious casting failures and mysterious crashes. One of the duplicates must be removed or renamed.
Loaded plugin: Motion Designer (from motion_designer)
* Running on local URL:  http://127.0.0.1:42003
* To create a public link, set `share=True` in `launch()`.
Loading Model 'ckpts/ltx-2.3-22b-dev_diffusion_model_quanto_int8.safetensors' ...
Loading Text Encoder 'ckpts/gemma-3-12b-it-qat-q4_0-unquantized/gemma-3-12b-it-qat-q4_0-unquantized_quanto_bf16_int8.safetensors' ...
************ Memory Management for the GPU Poor (mmgp 3.7.12) by DeepBeepMeep ************
Hooked to model 'transformer' (X0Model)
Hooked to model 'text_encoder' (Gemma3ForCausalLM)
Hooked to model 'text_embedding_projection' (GemmaFeaturesExtractorProjLinear)
Hooked to model 'text_embeddings_connector' (GemmaTextEmbeddingsConnectorModel)
Hooked to model 'vae' (VideoDecoder)
Hooked to model 'video_encoder' (VideoEncoder)
Hooked to model 'audio_encoder' (AudioEncoder)
Hooked to model 'audio_decoder' (AudioDecoder)
Hooked to model 'vocoder' (VocoderWithBWE)
Hooked to model 'spatial_upsampler' (LatentUpsampler)
Lora 'loras/ltx2/ltx-2.3-22b-distilled-lora-384.safetensors' was loaded in model 'models.ltx2.ltx2'
 12%|████████████████████▌                                                                                                                                               | 1/8 [00:34<03:58, 34.05s/steps]-[_MTLCommandBuffer addScheduledHandler:]:807: failed assertion `Scheduled handler provided after commit call'
Abort trap: 6              python wgp.py --multiple-images --advanced
(venv) (base) <<PINOKIO_SHELL>>