{"record":{"id":"bd9943fd6ea995ab","repo":"docling-project/docling","slug":"xpu-is-not-supported-by-this-model-supported-devi","errorCode":null,"errorMessage":"XPU is not supported by this model. Supported devices: {[d.value for d in supported_devices]}","messagePattern":"XPU is not supported by this model\\. Supported devices: (.+?)","errorType":"exception","errorClass":"AcceleratorDeviceNotAvailableError","httpStatus":null,"severity":"error","filePath":"docling/utils/accelerator_utils.py","lineNumber":112,"sourceCode":"        ):\n            raise AcceleratorDeviceNotAvailableError(\n                f\"MPS is not supported by this model. Supported devices: {[d.value for d in supported_devices]}\"\n            )\n\n        if has_mps:\n            device = \"mps\"\n        else:\n            raise AcceleratorDeviceNotAvailableError(\n                \"MPS is not available in the system. \"\n                \"Please ensure you are running on Apple Silicon with MPS support, or use --device auto/cpu.\"\n            )\n\n    elif accelerator_device == AcceleratorDevice.XPU.value:\n        if (\n            supported_devices is not None\n            and AcceleratorDevice.XPU not in supported_devices\n        ):\n            raise AcceleratorDeviceNotAvailableError(\n                f\"XPU is not supported by this model. Supported devices: {[d.value for d in supported_devices]}\"\n            )\n\n        if has_xpu:\n            device = \"xpu\"\n        else:\n            raise AcceleratorDeviceNotAvailableError(\n                \"XPU is not available in the system. \"\n                \"Please ensure PyTorch with Intel XPU support is installed, or use --device auto/cpu.\"\n            )\n\n    elif accelerator_device == AcceleratorDevice.CPU.value:\n        device = \"cpu\"\n\n    else:\n        raise AcceleratorDeviceNotAvailableError(\n            f\"Unknown device option '{accelerator_device}'. \"\n            f\"Valid options are: auto, cpu, cuda, mps, xpu, or cuda:N\"","sourceCodeStart":94,"sourceCodeEnd":130,"githubUrl":"https://github.com/docling-project/docling/blob/61d76f1ff3f8428065465889f7b4577da7df704c/docling/utils/accelerator_utils.py#L94-L130","documentation":"AcceleratorDeviceNotAvailableError raised by decide_device() when the user explicitly requests 'xpu' (Intel GPU) but the model's supported_devices list excludes AcceleratorDevice.XPU. It is the model-capability variant of the XPU checks: even on an Intel GPU machine, the specific model stage cannot use XPU.","triggerScenarios":"Setting accelerator_device='xpu' while a pipeline stage passes supported_devices without XPU to decide_device (common: many vision/table models were only validated on CUDA/CPU).","commonSituations":"Early adoption of Intel GPU (Arc/Data Center Max) acceleration with model stages not yet XPU-enabled; enabling XPU globally via CLI while one stage doesn't support it.","solutions":["Use accelerator_device='auto' — it removes unsupported devices per model instead of raising","Check the model's supported device list and request one it supports","Configure the device per pipeline stage","Upgrade docling/torch — XPU support coverage improves over releases"],"exampleFix":"# before\naccelerator_options.accelerator_device = \"xpu\"\n\n# after\naccelerator_options.accelerator_device = \"auto\"","handlingStrategy":"validation","validationCode":"supported = {d.value for d in model_supported_devices or []}\nif accelerator_options.accelerator_device == \"xpu\" and supported and \"xpu\" not in supported:\n    accelerator_options.accelerator_device = \"auto\"","typeGuard":"def xpu_supported(supported: set[str]) -> bool:\n    return \"xpu\" in supported","tryCatchPattern":"from docling.exceptions import AcceleratorDeviceNotAvailableError\n\ntry:\n    device = decide_device(\"xpu\", supported_devices)\nexcept AcceleratorDeviceNotAvailableError:\n    device = decide_device(\"auto\", supported_devices)","preventionTips":["Use 'auto' unless every stage in your pipeline is known XPU-capable","Verify the model's supported_devices before pinning XPU","Track release notes — XPU coverage per model is still expanding","Scope XPU config to Intel GPU nodes only"],"tags":["xpu","accelerator","configuration","intel-gpu"],"backgroundTag":null,"analyzedSha":"61d76f1ff3f8428065465889f7b4577da7df704c","analyzedAt":"2026-08-14T23:53:18.727Z","schemaVersion":2},"datasetVersion":"2026-08-15T22:17:37.221Z"}