Windows

Today, Windows developers can leverage PyTorch to run inference on the latest models across the breadth of GPUs in the Windows ecosystem, thanks to DirectML. We’ve updated Torch-DirectML to use DirectML 1.13 for acceleration and support PyTorch 2.2. PyTorch with DirectML simplifies the setup process, through a one-package install, making it easy to try out AI powered experiences and supporting your ability to scale AI to your customers across Windows. To see these updates in action, check out our Build session Bring AI experiences to all your Windows Devices. See here to learn how our hardware vendor partners are making this experience great: AMD: AMD is glad PyTorch with DirectML is enabling even more developers to run LLMs locally...

DirectML support for Phi 3 mini launched last month and we’ve since made several improvements, unlocking more models and even better performance! Developers can grab already quantized versions of Phi-3 mini (with variants for the 4k and 128k versions). They can now also get Phi 3 medium (4k and 128k) and Mistral v0.2. Stay tuned for additional pre-quantized models! We’ve also shipped a gradio interface to make easier to test these models with the new ONNX Runtime Generate() API. Learn more. Be sure to check out our Build sessions to learn more. See below for details. See here to learn what our hardware vendor partners have to say: AMD...

We are excited to announce the availability of the developer preview for WebNN, a web standard for cross-platform and hardware-accelerated neural network inference in the browser, using DirectML and ONNX Runtime Web. This preview enables web developers to leverage the power and performance of DirectML across GPUs with support coming soon for Intel’s® Core™ Ultra processors with Intel® AI Boost and the Copilot+ PC, powered by Qualcomm® Hexagon™ NPUs. WebNN is a game-changer for web development. It’s an emerging web standard that defines how to run machine learning models in the browser, using the hardware acceleration of your local device’s GPU or NPU. This way, you can enjoy web applications that use machine learning without any extra...

Hello Windows Insiders, today we are releasing Windows 11 Insider Preview Build 22635.3646 (KB5037858) to the Beta Channel. REMINDER: Windows Insiders in the Beta Channel will updates based on Windows 11, version 23H2 via an enablement package (Build 22635.xxxx). For Windows Insiders in the Beta Channel who want to be the first to get features gradually rolled out to you, you can turn ON the toggle (shown in the image below) to get the latest updates as they are available via Settings > Windows Update. Over time, we will increase the rollouts of features to everyone with the toggle turned on. Should you keep this toggle off, new features will gradually be rolled out to your device over time once they are ready. Turn on the toggle to...

Hello Windows Insiders! Today, we are making this year’s annual feature update Windows 11, version 24H2 (Build 26100.712) available in the Release Preview Channel for customers to preview ahead of general availability later this calendar year. Windows 11, version 24H2* includes a range of new features such as the HDR background support, energy saver, Sudo for Windows, Rust in the Windows kernel, support for Wi-Fi 7, voice clarity and more. It also includes many improvements across Windows. For example, we are introducing a scrollable view of the quick settings flyout from the taskbar, the ability to create 7-zip and TAR archives in File Explorer (in addition to ZIP), and improvements for connecting Bluetooth® Low Energy Audio devices...