新闻与深度文章
新闻报道 | ASA Workshop
ASA workshop at PLDI
While many aspects of “AI for Code / ML for code” research area has been explored, the success of static analysis in identifying various software bugs creates a unique opportunity to explore the area of AI for Code. Along with…
新闻报道 | Visual Studio Blog
Typing Less, Coding More: How we delivered IntelliCode whole line completions with a transformer model
Great code completions make you more productive while composing your code. Visual Studio 2022 now automatically completes C# code up to a whole line at a time, using a rich knowledge of your coding context. We have also released the IntelliCode Completions extension in Visual…
新闻报道 | Microsoft Open Source Blog
Journey to optimize large scale transformer model inference with ONNX Runtime
With its resource-efficient and high-performance nature, ONNX Runtime helped us meet the need of deploying a large-scale multi-layer generative transformer model for code, a.k.a., GPT-C, to empower IntelliCode with the whole line of code completion suggestions in Visual Studio and…
新闻报道 | Az Predictor
Az Predictor: AI powered interactive assistant
We built Az Predictor, an intelligent command completion module for Azure Powershell. Az Predictor helps our Azure developers find the cmdlet they are looking for efficiently, identify the required parameters quickly, and experience fewer errors. Az Predictor takes the context…
新闻报道 | Empowering Azure CLI developers with AI
Empowering Azure CLI developers with AI
When we redesigned the Azure CLI in 2016, our goal was to create a simple, easy to use, tool for managing Azure. Since then, Azure has grown tremendously from supporting multiple clouds in various locations across the globe, on/off premises…
新闻报道 | Visual Studio Blog
The making of Visual Studio IntelliCode’s first deep learning model: a research journey
Since the first IntelliCode code completion model was shipped in Visual Studio and Visual Studio Code in 2018, it has become an essential coding assistant for millions of developers around the world. In the past two years, we have been working tirelessly to enable IntelliCode for more programming languages and, in the meantime, researching ways to improve the model precision and coverage to deliver an even more satisfying user experience. One of our major research…