<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" version="2.0">
  <channel>
    <title>topic Seeking Technical Assistance: Intel Ultra 9 NPU Integration with PyTorch on Windows 11 in Mobile and Desktop Processors</title>
    <link>https://community.intel.com/t5/Mobile-and-Desktop-Processors/Seeking-Technical-Assistance-Intel-Ultra-9-NPU-Integration-with/m-p/1736217#M87675</link>
    <description>I am writing to request assistance with a persistent and blocking issue regarding the use of the Intel Ultra 9 NPU (AI Boost) for accelerating PyTorch model training on a Windows 11 system. My core, non-negotiable requirements are: Primary OS must be Windows (not WSL or Linux). Models must be developed and trained using native PyTorch. The installed Intel AI Boost NPU hardware must be utilized. The problem I face is that while the NPU is correctly recognized by Windows Device Manager and the task manager, I cannot make it work through the expected software paths: intel-extension-for-pytorch is not an option as it explicitly does not support Windows. OpenVINO Toolkit encounters a critical failure. When attempting to compile and run a Transformer model (exported from PyTorch via ONNX), the process crashes with errors pointing to core.cpp and plugin.cpp, indicating a likely low-level driver or runtime incompatibility. The system may become unstable or the process terminates unexpectedly. My attempt to enable the NPU within WSL2 also failed, as the /dev/intel_npu* device node was not present, suggesting the driver does not correctly pass through. I have ensured the latest Intel NPU driver is installed. The core contradiction I am stuck with is the lack of a supported, stable software bridge between PyTorch on Windows and the NPU hardware. Could you please advise: Is there a confirmed, stable software stack (specific driver + framework versions) for this use case? Are there any known workarounds or configuration changes for the OpenVINO runtime crashes on Windows 11? Is the newly open-sourced Intel NPU Acceleration Library intended to address this exact gap, and what is its current readiness for production PyTorch workloads? Any guidance or insight into resolving this "Windows + PyTorch + NPU" trilemma would be greatly appreciated. Thank you for your time and support. Sincerely, A Developer</description>
    <pubDate>Sat, 07 Feb 2026 09:49:42 GMT</pubDate>
    <dc:creator>YUANZHU</dc:creator>
    <dc:date>2026-02-07T09:49:42Z</dc:date>
    <item>
      <title>Seeking Technical Assistance: Intel Ultra 9 NPU Integration with PyTorch on Windows 11</title>
      <link>https://community.intel.com/t5/Mobile-and-Desktop-Processors/Seeking-Technical-Assistance-Intel-Ultra-9-NPU-Integration-with/m-p/1736217#M87675</link>
      <description>I am writing to request assistance with a persistent and blocking issue regarding the use of the Intel Ultra 9 NPU (AI Boost) for accelerating PyTorch model training on a Windows 11 system. My core, non-negotiable requirements are: Primary OS must be Windows (not WSL or Linux). Models must be developed and trained using native PyTorch. The installed Intel AI Boost NPU hardware must be utilized. The problem I face is that while the NPU is correctly recognized by Windows Device Manager and the task manager, I cannot make it work through the expected software paths: intel-extension-for-pytorch is not an option as it explicitly does not support Windows. OpenVINO Toolkit encounters a critical failure. When attempting to compile and run a Transformer model (exported from PyTorch via ONNX), the process crashes with errors pointing to core.cpp and plugin.cpp, indicating a likely low-level driver or runtime incompatibility. The system may become unstable or the process terminates unexpectedly. My attempt to enable the NPU within WSL2 also failed, as the /dev/intel_npu* device node was not present, suggesting the driver does not correctly pass through. I have ensured the latest Intel NPU driver is installed. The core contradiction I am stuck with is the lack of a supported, stable software bridge between PyTorch on Windows and the NPU hardware. Could you please advise: Is there a confirmed, stable software stack (specific driver + framework versions) for this use case? Are there any known workarounds or configuration changes for the OpenVINO runtime crashes on Windows 11? Is the newly open-sourced Intel NPU Acceleration Library intended to address this exact gap, and what is its current readiness for production PyTorch workloads? Any guidance or insight into resolving this "Windows + PyTorch + NPU" trilemma would be greatly appreciated. Thank you for your time and support. Sincerely, A Developer</description>
      <pubDate>Sat, 07 Feb 2026 09:49:42 GMT</pubDate>
      <guid>https://community.intel.com/t5/Mobile-and-Desktop-Processors/Seeking-Technical-Assistance-Intel-Ultra-9-NPU-Integration-with/m-p/1736217#M87675</guid>
      <dc:creator>YUANZHU</dc:creator>
      <dc:date>2026-02-07T09:49:42Z</dc:date>
    </item>
    <item>
      <title>Re:Seeking Technical Assistance: Intel Ultra 9 NPU Integration with PyTorch on Windows 11</title>
      <link>https://community.intel.com/t5/Mobile-and-Desktop-Processors/Seeking-Technical-Assistance-Intel-Ultra-9-NPU-Integration-with/m-p/1736341#M87689</link>
      <description>&lt;P&gt;Hello YUANZHU,&lt;/P&gt;&lt;P&gt;&lt;BR /&gt;&lt;/P&gt;&lt;P&gt;Thank you for raising this concern via the Intel Community.&lt;/P&gt;&lt;P&gt;&lt;BR /&gt;&lt;/P&gt;&lt;P&gt;To properly investigate the issue, I would like to gather some information first so I can provide you with the appropriate steps to help resolve it. Kindly provide the details below:&lt;/P&gt;&lt;UL&gt;&lt;LI&gt;Are you using a laptop or a desktop system?&lt;/LI&gt;&lt;LI&gt;What is the exact model of your Intel® Core™ Ultra 9 processor?&lt;/LI&gt;&lt;LI&gt;Does the crashing occur only when using any OpenVINO™ applications?&lt;/LI&gt;&lt;LI&gt;Are all system drivers, BIOS, and software fully up to date?&lt;/LI&gt;&lt;/UL&gt;&lt;P&gt;&lt;BR /&gt;&lt;/P&gt;&lt;P&gt;Once the information is provided, it will greatly help with our investigation.&lt;/P&gt;&lt;P&gt;&lt;BR /&gt;&lt;/P&gt;&lt;P&gt;Thank you, and I look forward to your response.&lt;/P&gt;&lt;P&gt;&lt;BR /&gt;&lt;/P&gt;&lt;P&gt;Regards,&lt;/P&gt;&lt;P&gt;&lt;BR /&gt;&lt;/P&gt;&lt;P&gt;John M.&lt;/P&gt;&lt;P&gt;Intel Customer Support Technician&lt;/P&gt;&lt;BR /&gt;</description>
      <pubDate>Mon, 09 Feb 2026 04:09:09 GMT</pubDate>
      <guid>https://community.intel.com/t5/Mobile-and-Desktop-Processors/Seeking-Technical-Assistance-Intel-Ultra-9-NPU-Integration-with/m-p/1736341#M87689</guid>
      <dc:creator>JohnM_Intel</dc:creator>
      <dc:date>2026-02-09T04:09:09Z</dc:date>
    </item>
    <item>
      <title>Re:Seeking Technical Assistance: Intel Ultra 9 NPU Integration with PyTorch on Windows 11</title>
      <link>https://community.intel.com/t5/Mobile-and-Desktop-Processors/Seeking-Technical-Assistance-Intel-Ultra-9-NPU-Integration-with/m-p/1736769#M87723</link>
      <description>&lt;P&gt;Hello YUANZHU,&lt;/P&gt;&lt;P&gt;&lt;BR /&gt;&lt;/P&gt;&lt;P&gt;I hope you had the opportunity to review the information I posted. At your earliest convenience, please let me know so we can determine the best course of action to resolve this matter efficiently.&lt;/P&gt;&lt;P&gt;&lt;BR /&gt;&lt;/P&gt;&lt;P&gt;Regards,&lt;/P&gt;&lt;P&gt;&lt;BR /&gt;&lt;/P&gt;&lt;P&gt;John M.&lt;/P&gt;&lt;P&gt;Intel Customer Support Technician&lt;/P&gt;&lt;P&gt;&lt;BR /&gt;&lt;/P&gt;&lt;BR /&gt;</description>
      <pubDate>Thu, 12 Feb 2026 03:33:37 GMT</pubDate>
      <guid>https://community.intel.com/t5/Mobile-and-Desktop-Processors/Seeking-Technical-Assistance-Intel-Ultra-9-NPU-Integration-with/m-p/1736769#M87723</guid>
      <dc:creator>JohnM_Intel</dc:creator>
      <dc:date>2026-02-12T03:33:37Z</dc:date>
    </item>
    <item>
      <title>Re: Re:Seeking Technical Assistance: Intel Ultra 9 NPU Integration with PyTorch on Windows 11</title>
      <link>https://community.intel.com/t5/Mobile-and-Desktop-Processors/Seeking-Technical-Assistance-Intel-Ultra-9-NPU-Integration-with/m-p/1736773#M87726</link>
      <description>&lt;P class=""&gt;&lt;SPAN&gt;Dear John M.,&lt;/SPAN&gt;&lt;/P&gt;&lt;P class=""&gt;&lt;SPAN&gt;Thank you for your response.&lt;/SPAN&gt;&lt;/P&gt;&lt;P class=""&gt;&lt;SPAN&gt;Please find my answers below:&lt;/SPAN&gt;&lt;/P&gt;&lt;P class=""&gt;&lt;STRONG&gt;&lt;SPAN&gt;1. Are you using a laptop or a desktop system?&lt;/SPAN&gt;&lt;/STRONG&gt;&lt;BR /&gt;&lt;SPAN&gt;I am using a&amp;nbsp;&lt;/SPAN&gt;&lt;STRONG&gt;&lt;SPAN&gt;laptop&lt;/SPAN&gt;&lt;/STRONG&gt;&lt;SPAN&gt;.&lt;/SPAN&gt;&lt;/P&gt;&lt;P class=""&gt;&lt;STRONG&gt;&lt;SPAN&gt;2. What is the exact model of your Intel® Core™ Ultra 9 processor?&lt;/SPAN&gt;&lt;/STRONG&gt;&lt;BR /&gt;&lt;STRONG&gt;Intel(R) Core(TM) Ultra 9 185H (2.50 GHz)&lt;/STRONG&gt;&lt;/P&gt;&lt;P class=""&gt;&lt;STRONG&gt;&lt;SPAN&gt;3. Does the crashing occur only when using any OpenVINO™ applications?&lt;/SPAN&gt;&lt;/STRONG&gt;&lt;BR /&gt;&lt;SPAN&gt;Yes, the crash occurs specifically when using OpenVINO to compile a model for the NPU device.&lt;/SPAN&gt;&lt;BR /&gt;&lt;SPAN&gt;The NPU is detected (&lt;/SPAN&gt;"NPU"&lt;SPAN&gt;&amp;nbsp;appears in&amp;nbsp;&lt;/SPAN&gt;ov.Core().available_devices&lt;SPAN&gt;), but calling&amp;nbsp;&lt;/SPAN&gt;core.compile_model(ov_model, "NPU")&lt;SPAN&gt;&amp;nbsp;fails with errors referencing&amp;nbsp;&lt;/SPAN&gt;core.cpp&lt;SPAN&gt;&amp;nbsp;and&amp;nbsp;&lt;/SPAN&gt;plugin.cpp&lt;SPAN&gt;.&lt;/SPAN&gt;&lt;BR /&gt;&lt;SPAN&gt;OpenVINO operations on CPU work normally.&lt;/SPAN&gt;&lt;/P&gt;&lt;P class=""&gt;&lt;STRONG&gt;&lt;SPAN&gt;4. Are all system drivers, BIOS, and software fully up to date?&lt;/SPAN&gt;&lt;/STRONG&gt;&lt;BR /&gt;&lt;SPAN&gt;All related software and drivers have been updated to the latest stable versions available through official channels at the time of testing.&lt;/SPAN&gt;&lt;/P&gt;&lt;HR /&gt;&lt;P class=""&gt;&lt;SPAN&gt;Please let me know if any additional information or logs are needed.&lt;/SPAN&gt;&lt;/P&gt;&lt;P class=""&gt;&lt;SPAN&gt;Thank you again for your assistance.&lt;/SPAN&gt;&lt;/P&gt;&lt;P class=""&gt;&lt;SPAN&gt;Best regards,&lt;/SPAN&gt;&lt;BR /&gt;&lt;SPAN&gt;YUANZHU&lt;/SPAN&gt;&lt;/P&gt;</description>
      <pubDate>Thu, 12 Feb 2026 04:20:29 GMT</pubDate>
      <guid>https://community.intel.com/t5/Mobile-and-Desktop-Processors/Seeking-Technical-Assistance-Intel-Ultra-9-NPU-Integration-with/m-p/1736773#M87726</guid>
      <dc:creator>YUANZHU</dc:creator>
      <dc:date>2026-02-12T04:20:29Z</dc:date>
    </item>
    <item>
      <title>Re:Seeking Technical Assistance: Intel Ultra 9 NPU Integration with PyTorch on Windows 11</title>
      <link>https://community.intel.com/t5/Mobile-and-Desktop-Processors/Seeking-Technical-Assistance-Intel-Ultra-9-NPU-Integration-with/m-p/1736937#M87735</link>
      <description>&lt;P&gt;Hello YUANZHU,&lt;/P&gt;&lt;P&gt;&lt;BR /&gt;&lt;/P&gt;&lt;P&gt;Thank you for this information.&lt;/P&gt;&lt;P&gt;&lt;BR /&gt;&lt;/P&gt;&lt;P&gt;I will do further research on this matter and post the response on this thread once it is available.&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;If you have questions, please let us know. Thank you.&lt;/P&gt;&lt;P&gt;&lt;BR /&gt;&lt;/P&gt;&lt;P&gt;Best regards,&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;Brenz L.&lt;/P&gt;&lt;P&gt;Intel Customer Support Technician&lt;/P&gt;&lt;BR /&gt;</description>
      <pubDate>Fri, 13 Feb 2026 03:13:15 GMT</pubDate>
      <guid>https://community.intel.com/t5/Mobile-and-Desktop-Processors/Seeking-Technical-Assistance-Intel-Ultra-9-NPU-Integration-with/m-p/1736937#M87735</guid>
      <dc:creator>BrenzL_Intel</dc:creator>
      <dc:date>2026-02-13T03:13:15Z</dc:date>
    </item>
    <item>
      <title>Re:Seeking Technical Assistance: Intel Ultra 9 NPU Integration with PyTorch on Windows 11</title>
      <link>https://community.intel.com/t5/Mobile-and-Desktop-Processors/Seeking-Technical-Assistance-Intel-Ultra-9-NPU-Integration-with/m-p/1737386#M87764</link>
      <description>&lt;P&gt;Hello YUANZHU,&lt;/P&gt;&lt;P&gt;&lt;BR /&gt;&lt;/P&gt;&lt;P&gt;Thank you for your continued cooperation with Intel.&lt;/P&gt;&lt;P&gt;&lt;BR /&gt;&lt;/P&gt;&lt;P&gt;Please install the correct NPU device driver by following the instructions provided in the &lt;A href="https://docs.openvino.ai/2023.2/openvino_docs_install_guides_configurations_for_intel_npu.html" rel="noopener noreferrer" target="_blank"&gt;NPU configuration guide&lt;/A&gt;.&lt;/P&gt;&lt;P&gt;&lt;BR /&gt;&lt;/P&gt;&lt;P&gt;After installing the proper driver, proceed to &lt;A href="https://docs.openvino.ai/2023.3/openvino_docs_install_guides_overview.html?VERSION=v_2023_3_0&amp;amp;OP_SYSTEM=WINDOWS&amp;amp;DISTRIBUTION=ARCHIVE#" rel="noopener noreferrer" target="_blank"&gt;Install the&amp;nbsp;distribution of OpenVINO™ toolkit via OpenVINO Archives&lt;/A&gt;.&lt;/P&gt;&lt;P&gt;&lt;BR /&gt;&lt;/P&gt;&lt;P&gt;Once the installation has been completed, please source the environment variables from the OpenVINO installation, also available through the OpenVINO Archives.&lt;/P&gt;&lt;P&gt;&lt;BR /&gt;&lt;/P&gt;&lt;P&gt;If you need further assistance with any of these steps, please let us know.&lt;/P&gt;&lt;P&gt;&lt;BR /&gt;&lt;/P&gt;&lt;P&gt;Best regards,&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;Brenz L.&lt;/P&gt;&lt;P&gt;Intel Customer Support Technician&lt;/P&gt;&lt;BR /&gt;</description>
      <pubDate>Tue, 17 Feb 2026 03:27:31 GMT</pubDate>
      <guid>https://community.intel.com/t5/Mobile-and-Desktop-Processors/Seeking-Technical-Assistance-Intel-Ultra-9-NPU-Integration-with/m-p/1737386#M87764</guid>
      <dc:creator>BrenzL_Intel</dc:creator>
      <dc:date>2026-02-17T03:27:31Z</dc:date>
    </item>
    <item>
      <title>Re:Seeking Technical Assistance: Intel Ultra 9 NPU Integration with PyTorch on Windows 11</title>
      <link>https://community.intel.com/t5/Mobile-and-Desktop-Processors/Seeking-Technical-Assistance-Intel-Ultra-9-NPU-Integration-with/m-p/1738324#M87830</link>
      <description>&lt;P&gt;Hello YUANZHU,&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;Could you please confirm if you have reviewed the information I posted? Your feedback at your earliest convenience would be greatly appreciated so we can decide on the best way to proceed with resolving this matter.&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;Best regards,&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;Brenz L.&lt;/P&gt;&lt;P&gt;Intel Customer Support Technician&lt;/P&gt;&lt;BR /&gt;</description>
      <pubDate>Tue, 24 Feb 2026 04:44:44 GMT</pubDate>
      <guid>https://community.intel.com/t5/Mobile-and-Desktop-Processors/Seeking-Technical-Assistance-Intel-Ultra-9-NPU-Integration-with/m-p/1738324#M87830</guid>
      <dc:creator>BrenzL_Intel</dc:creator>
      <dc:date>2026-02-24T04:44:44Z</dc:date>
    </item>
    <item>
      <title>Re:Seeking Technical Assistance: Intel Ultra 9 NPU Integration with PyTorch on Windows 11</title>
      <link>https://community.intel.com/t5/Mobile-and-Desktop-Processors/Seeking-Technical-Assistance-Intel-Ultra-9-NPU-Integration-with/m-p/1738643#M87859</link>
      <description>&lt;P&gt;Hello YUANZHU,&lt;/P&gt;&lt;P&gt;&lt;BR /&gt;&lt;/P&gt;&lt;P&gt;Since I haven't received a response from you, I will be closing this inquiry. If you need further assistance, please submit a new question, as this thread will no longer be monitored.&lt;/P&gt;&lt;P&gt;&lt;BR /&gt;&lt;/P&gt;&lt;P&gt;Best regards,&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;Brenz L.&lt;/P&gt;&lt;P&gt;Intel Customer Support Technician&lt;/P&gt;&lt;BR /&gt;</description>
      <pubDate>Thu, 26 Feb 2026 03:52:04 GMT</pubDate>
      <guid>https://community.intel.com/t5/Mobile-and-Desktop-Processors/Seeking-Technical-Assistance-Intel-Ultra-9-NPU-Integration-with/m-p/1738643#M87859</guid>
      <dc:creator>BrenzL_Intel</dc:creator>
      <dc:date>2026-02-26T03:52:04Z</dc:date>
    </item>
  </channel>
</rss>

