Windows AI Platform
The Windows AI Platform enables the ML community to build and deploy AI powered experiences on the breadth of Windows devices. This developer blog provides in-depth looks at new and upcoming Windows AI features, customer success stories, and educational material to help developers get started.
Latest posts
DirectML: Accelerating AI on Windows, now with NPUs
We are thrilled to announce our collaboration with Intel®, one of our key partners, to bring the first Neural Processing Unit (NPU) powered by DirectML on Windows. AI is transforming the world, driving innovation, and creating value across industries. NPUs are critical components in enabling amazing AI experiences for developers and consumers alike. An NPU is a processor built for enabling machine learning (ML) workloads that are computationally intensive, do not require graphics interactions, and provide efficient power consumption. These new devices will revolutionize how AI transforms our day-to-day experie...
Boost Your Gen AI Experience with our DirectML extension for Automatic1111’s WebUI
Olive is a powerful open-source Microsoft tool to optimize ONNX models for DirectML. You may remember from this year’s Build that we showcased Olive support for Stable Diffusion, a cutting-edge Generative AI model that creates images from text. We didn’t want to stop there, since many users access Stable Diffusion through Automatic1111's webUI, a popular and versatile interface for Stable Diffusion. Luckily this webUI supports extensions, and today we're thrilled to reveal our DirectML extension! Specifically, our extension offers DirectML support for the compute-heavy uNet models in Stable Diffusion. Th...
Announcing preview support for Llama 2 in DirectML
At Inspire this year we talked about how developers will be able to run Llama 2 on Windows with DirectML and the ONNX Runtime and we've been hard at work to make this a reality. We now have a sample showing our progress with Llama 2 7B! See https://github.com/microsoft/Olive/tree/main/examples/directml/llama_v2 This sample relies on first doing an optimization pass on the model with Olive, a powerful optimization tool for ONNX models. Olive utilizes powerful graph fusion optimizations from the ONNX Runtime and a model architecture optimized for DirectML to speed up inference times by up to 10X! After ...
DirectML at Build 2023
DirectML shared some exciting announcements at Build this year! We demonstrated a few awesome demos and highlighted new capabilities during the Windows AI Breakout session, Deliver AI-powered experiences across cloud and edge, with Windows. We are also excited to announce the launch of our new product landing page! This new product page provides the information you need to bring performant, cross-hardware AI acceleration into your app. DirectML enables Adobe to scale to Intel’s first VPU to market We partnered with Adobe and Intel to showcase how DirectML makes it possible for developers to integrate machine...
Adobe Premiere Pro leverages DirectML on new AI Silicon
DirectML is ushering in a new wave of machine learning integration capabilities on emerging AI silicon. At the Windows AI Breakout BUILD session, we showcased how ONNX Runtime, powered by DirectML, enables Adobe’s Premiere Pro to leverage Intel’s next generation platform, Meteor Lake with integrated VPU. Adobe Premiere Pro with DirectML Adobe Premiere Pro leverages DirectML today to power many features with AI, such as Auto Reframe and Scene Edit Detection: DirectML with ONNX Runtime empowers Adobe to light up hardware acceleration for these features, with the same code path acro...
Optimize DirectML performance with Olive
Are you ready to revolutionize the way you optimize your AI models? Say hello to Olive (ONNX Live), the advanced model optimization tool that integrates seamlessly with DirectML for hardware acceleration across the breadth of the Windows ecosystem. With Olive, you can easily incorporate cutting-edge techniques like model compression, optimization, and compilation, all in one powerful tool. And the best part? You don't need to be an expert in optimizing models for underlying GPUs or NPUs - Olive does all the heavy lifting for you to get the best possible performance with DirectML! In our Stable Diffusion t...
DirectML ❤ Stable Diffusion
Text-to-image models are amazing tools that can transform natural language into stunning images. Stable Diffusion is particularly interesting. The base model can create images from text and since it’s open-source developers can customize it for their own needs and preferences. With some extra training, developers can fine-tune their model to generate images of any domain, subject, or style they want. We are demonstrating what can be done with Stable Diffusion models in two of our Build sessions: Shaping the future of work with AI and Deliver AI-powered experiences across cloud and edge, with Windows. We've ...
Transformer support for PyTorch with DirectML is here!
The latest release of PyTorch with DirectML is available today! This release brings support for training popular Transformer Models like GPT2, BERT, and Detection Transformers. To get started with training Transformer Models using PyTorch with DirectML, you can find a new sample on the DirectML GitHub. The sample covers training a PyTorch implementation of the Transformer Model in the popular paper "Attention is All You Need " (Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, Illia Polosukhin, arxiv, 2017). This release of PyTorch with DirectML also includ...
Real-Time Image Blurring & DirectX Resource Binding in the Windows ML Samples Gallery
Last November, we announced the release of the Windows ML Samples Gallery. The newest release of the gallery adds 4 new samples, 2 of which are discussed in detail below. Real-Time Background Image Blurring Linnea May Real-time machine learning inference is a hot topic in ML, with applications such as real-time object detection in autonomous cars or background image blurring of a video stream during a work call. This new sample demonstrates the best practices to follow with Windows Machine Learning (Windows ML) and Microsoft Media Foundation to run background image blurring during inference on a...