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

App: DramaBox (DramaBox-TTS-Pinokio.git)
Repo: https://github.com/PierrunoYT/DramaBox-TTS-Pinokio.git
Generated: 2026-08-28T03:01:51.987Z
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": "intel corporation",
    "gpu_model": "intel(r) graphics",
    "ram_gb": 16,
    "vram_gb": 2
  },
  "os": {
    "platform": "Windows",
    "distro": "Microsoft Windows 11 Home",
    "release": "10.0.26200",
    "codename": "25H2",
    "kernel": "10.0.26200",
    "arch": "x64",
    "build": "26200",
    "servicepack": "0.0",
    "uefi": true
  },
  "system": {
    "manufacturer": "Dell Inc.",
    "model": "Dell 24 All-in-One EC24250",
    "virtual": false
  },
  "cpu": {
    "manufacturer": "Intel",
    "brand": "Core™ 5 120U",
    "vendor": "GenuineIntel",
    "family": "6",
    "model": "186",
    "stepping": "3",
    "speed": 1.4,
    "speedMin": 1.4,
    "speedMax": 1.4,
    "cores": 12,
    "physicalCores": 10,
    "processors": 1,
    "performanceCores": 12,
    "efficiencyCores": 0,
    "virtualization": true,
    "cache": {
      "l1d": 360448,
      "l1i": 589824,
      "l2": 6815744,
      "l3": 12582912
    }
  },
  "memory": {
    "total": 16855994368,
    "free": 2097475584,
    "used": 14758518784,
    "active": 14758518784,
    "available": 2097475584,
    "buffers": 0,
    "cached": 0,
    "slab": 0,
    "buffcache": 0,
    "swaptotal": 9663676416,
    "swapused": 372244480,
    "swapfree": 9291431936
  },
  "gpus": [
    {
      "model": "intel(r) graphics"
    }
  ],
  "graphics": {
    "controllers": [
      {
        "vendor": "Intel Corporation",
        "model": "Intel(R) Graphics",
        "bus": "PCI",
        "vram": 2047.99609375,
        "vramDynamic": true
      }
    ],
    "displays": [
      {
        "model": "DELL AIO",
        "main": true,
        "builtin": false,
        "connection": "DP",
        "currentResX": 1920,
        "currentResY": 1080,
        "resolutionX": 1920,
        "resolutionY": 1080,
        "pixelDepth": 32,
        "currentRefreshRate": 60
      }
    ]
  }
}

Logs

logs/api/start.js/1787886078350

Source: api / start.js
Lines: 45 total, last 45 included

[api shell.run]
Microsoft Windows [Version 10.0.26200.9168]
(c) Microsoft Corporation. All rights reserved.

C:\pinokio\api\DramaBox-TTS-Pinokio.git\app>conda_hook & conda deactivate & conda deactivate & conda deactivate & conda activate base & C:\pinokio\api\DramaBox-TTS-Pinokio.git\app\env\Scripts\activate C:\pinokio\api\DramaBox-TTS-Pinokio.git\app\env && python ../launch.py
2026-08-27 20:01:43,035 INFO Fetching DramaBox checkpoints from HuggingFace (cached after first run)...
2026-08-27 20:01:43,035 INFO Fetching transformer from ResembleAI/Dramabox/dramabox-dit-v1.safetensors...
2026-08-27 20:01:43,719 INFO   -> C:\pinokio\api\DramaBox-TTS-Pinokio.git\cache\HF_HOME\hub\models--ResembleAI--Dramabox\snapshots\404f967f653fa1170dc15a9d1ddd3fdb9a0a842d\dramabox-dit-v1.safetensors
2026-08-27 20:01:43,719 INFO Fetching audio_components from ResembleAI/Dramabox/dramabox-audio-components.safetensors...
2026-08-27 20:01:43,845 INFO   -> C:\pinokio\api\DramaBox-TTS-Pinokio.git\cache\HF_HOME\hub\models--ResembleAI--Dramabox\snapshots\404f967f653fa1170dc15a9d1ddd3fdb9a0a842d\dramabox-audio-components.safetensors
2026-08-27 20:01:43,845 INFO Fetching silence_latent from ResembleAI/Dramabox/assets/silence_latent_frame.pt...
2026-08-27 20:01:43,992 INFO   -> C:\pinokio\api\DramaBox-TTS-Pinokio.git\cache\HF_HOME\hub\models--ResembleAI--Dramabox\snapshots\404f967f653fa1170dc15a9d1ddd3fdb9a0a842d\assets\silence_latent_frame.pt
2026-08-27 20:01:43,992 INFO Fetching Gemma from unsloth/gemma-3-12b-it-bnb-4bit...
Fetching 16 files: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 16/16 [00:00<00:00, 1088.14it/s]
2026-08-27 20:01:44,160 INFO   -> C:\pinokio\api\DramaBox-TTS-Pinokio.git\cache\HF_HOME\hub\models--unsloth--gemma-3-12b-it-bnb-4bit\snapshots\826e729dbaeea4ecb143738eed2bcf3539ebf7bf
2026-08-27 20:01:44,160 INFO Loading DramaBox warm server (Gemma + DiT + VAE + Decoder)...
2026-08-27 20:01:44,161 INFO TTSServer loading on cuda...
2026-08-27 20:01:44,163 INFO Loading pre-quantized Gemma (bnb-4bit) — using checkpoint's own quantization_config
`torch_dtype` is deprecated! Use `dtype` instead!
Traceback (most recent call last):
  File "C:\pinokio\api\DramaBox-TTS-Pinokio.git\launch.py", line 22, in <module>
    import app as dramabox_app  # noqa: E402
  File "C:\pinokio\api\DramaBox-TTS-Pinokio.git\app\app.py", line 34, in <module>
    tts = TTSServer(
  File "C:\pinokio\api\DramaBox-TTS-Pinokio.git\app\src\inference_server.py", line 149, in __init__
    self._load_all()
  File "C:\pinokio\api\DramaBox-TTS-Pinokio.git\app\src\inference_server.py", line 155, in _load_all
    self._prompt_encoder = PromptEncoder(
  File "C:\pinokio\api\DramaBox-TTS-Pinokio.git\app\ltx2\ltx_pipelines\utils\blocks.py", line 361, in __init__
    self._warm_text_encoder = self._load_bnb_4bit_encoder(gemma_root)
  File "C:\pinokio\api\DramaBox-TTS-Pinokio.git\app\ltx2\ltx_pipelines\utils\blocks.py", line 481, in _load_bnb_4bit_encoder
    hf_model = Gemma3ForConditionalGeneration.from_pretrained(gemma_root, **from_kwargs)
  File "C:\pinokio\api\DramaBox-TTS-Pinokio.git\app\env\lib\site-packages\transformers\modeling_utils.py", line 277, in _wrapper
    return func(*args, **kwargs)
  File "C:\pinokio\api\DramaBox-TTS-Pinokio.git\app\env\lib\site-packages\transformers\modeling_utils.py", line 5048, in from_pretrained
    ) = cls._load_pretrained_model(
  File "C:\pinokio\api\DramaBox-TTS-Pinokio.git\app\env\lib\site-packages\transformers\modeling_utils.py", line 5432, in _load_pretrained_model
    caching_allocator_warmup(model, expanded_device_map, hf_quantizer)
  File "C:\pinokio\api\DramaBox-TTS-Pinokio.git\app\env\lib\site-packages\transformers\modeling_utils.py", line 6089, in caching_allocator_warmup
    index = device.index if device.index is not None else torch_accelerator_module.current_device()
  File "C:\pinokio\api\DramaBox-TTS-Pinokio.git\app\env\lib\site-packages\torch\cuda\__init__.py", line 1071, in current_device
    _lazy_init()
  File "C:\pinokio\api\DramaBox-TTS-Pinokio.git\app\env\lib\site-packages\torch\cuda\__init__.py", line 403, in _lazy_init
    raise AssertionError("Torch not compiled with CUDA enabled")
AssertionError: Torch not compiled with CUDA enabled