{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreib5k3jm2izfoucn3pygpvsf6z3bvfnx4zgmgm4zaafa4g5xnfapv4",
    "uri": "at://did:plc:pgryn3ephfd2xgft23qokfzt/app.bsky.feed.post/3mi2ay367qsf2"
  },
  "path": "/t/pro-space-gpu-not-detected-cant-initialize-nvml-error/174696#post_1",
  "publishedAt": "2026-03-27T10:31:43.000Z",
  "site": "https://discuss.huggingface.co",
  "tags": [
    "Gemma 2b Finetuned Quotes Generator - a Hugging Face Space by IArjunS"
  ],
  "textContent": "Hello,\n\nI am new user of hugging face hub with user name IArjunS, and trying to host and run inference from a fine tuned ML model , I am not able to launch the app\nbecause of unavailibility of GPU i think. Can someone look into this error and provide help\n\nSpace URL: Gemma 2b Finetuned Quotes Generator - a Hugging Face Space by IArjunS\nMy account type - (Pro subscription).\n\nUserWarning: Can’t initialize NVML\nLoading model ‘IArjunS/gemma-2b-finetuned-quotes’ on device: cpu…\nStopping Node.js server…\nMy app.py has the DEVICE = “cuda” if torch.cuda.is_available() else “cpu” logic, and in settings Free GPU seems to be running automatically but error log suggests otherwise.\nI think the GPU is not being properly exposed to my container.\n\nThank you\nArjun",
  "title": "Pro Space GPU not detected: 'Can't initialize NVML' error"
}