Intel Dev Tools

06/26/2025

Get the most out of your genAI models with the OpenVINO 2025.2 release.
With Intel® XMX Graphics optimizations, KV cache compression, and support for FP16-NF4 precision, you'll get more from your GPUs, CPUs, and NPUs.
Download now!
https://intel.ly/3G8IYOo

04/09/2025

Intel's Parallel Universe Magazine Issue 58 is now available! 🎉

Discover how Intel® oneAPI, Intel® Extension for Scikit-learn, Intel® Tiber™ AI Cloud, and Intel® GPUs are driving innovation.

📖 Read the full issue: https://intel.ly/42jnyFg

12/27/2024

Harness the power of Intel VTune Profiler to optimize your Data Parallel Python applications! This new recipe shows how to profile and improve performance for parallelized Python workloads, helping you unlock greater efficiency and scalability. Take your Python performance to the next level: https://intel.ly/4gq07PU

12/26/2024

Boost PyTorch Inductor performance with Intel optimizations! By leveraging Intel extensions for PyTorch, and Torch. Compile with Intel Compilers, developers can accelerate model training and inference, unlocking faster performance. Enhance your AI projects with these powerful performance improvements. https://intel.ly/3Zp4sMy

This article demonstrates how to boost PyTorch Inductor performance on Windows for CPU Devices with Intel oneAPI DPC++/C++ Compiler

12/23/2024

Unlock powerful performance insights with Intel VTune Profiler in Google Cloud VMs! Learn how to profile applications in PMU-enabled environments to optimize workloads and boost efficiency. Leverage advanced profiling techniques to elevate your cloud applications. https://intel.ly/41GVehB

This recipe helps you set up a virtual machine (VM) instance in the Google Cloud Platform* to profile application performance with Intel® VTune™ Profiler.

12/19/2024

Intel's 2025.0 AI Tools and frameworks are here! From PyTorch and TensorFlow optimizations to JAX integration and neural compressors, these tools redefine GenAI productivity and scalability. Streamline your AI workloads, optimize model size, and scale seamlessly with Intel's cutting-edge solutions. https://intel.ly/3DgmusN

12/19/2024

Ready to elevate your AI applications? Optimize your AI workloads with Intel VTune Profiler and OpenVINO! This new recipe helps you profile and boost the performance of OpenVINO applications, allowing you to fine-tune inference workloads and improve efficiency. Explore the latest tips for performance optimization. https://intel.ly/41oZC4G

12/18/2024

Unlock faster AI inference with Intel and PyTorch! By using torch.compile, developers can accelerate model performance and improve efficiency. Explore how this integration can speed up your AI workflows and drive innovation. https://intel.ly/3OMi2EO

We are excited to announce that PyTorch* 2.5 has introduced support for the torch.compile feature on Windows* CPU, thanks to the collaborative efforts of Intel and Meta*. This enhancement aims to speed up PyTorch code ex*****on over the default eager mode, providing a significant performance boost.....

12/17/2024

Optimize large language models with Intel VTune Profiler! Discover how this tool provides insights to fine-tune performance, reduce bottlenecks, and maximize efficiency in AI workloads. Empower your LLMs to run smarter and faster with advanced profiling. https://intel.ly/4is68gK

This recipe demonstrates how you use Intel® VTune™ Profiler to analyze Large Language Models (LLMs) and improve the performance of AI applications. This recipe uses an LLM deployed on the Intel® Distribution of OpenVINO™ toolkit.

12/16/2024

Durham University is harnessing the power of Intel oneAPI Threading Building Blocks (oneTBB) to advance its ExaHyPE engine. This collaboration accelerates simulations, pushing the boundaries of astrophysics research. Explore how innovation drives discovery and helps to push the open spec forward. https://intel.ly/3ZDGPRD

oneAPI Centre of Excellence at Durham University Brings Its Experience from ExaHype into oneTBB

12/12/2024

Maximize AI/ML performance with Intel VTune Profiler! Discover how this powerful tool provides insights to optimize your applications, streamline processes, and deliver faster results. Take your AI projects to the next level with smarter performance tuning. https://intel.ly/3OK8jPe

12/10/2024

Unlock the full potential of your Intel architecture with deep insights into performance monitoring!

In the latest Intel VTune Profiler Cookbook recipe, explore how to analyze Uncore PerfMon events for Intel DDIO. Whether optimizing workloads or improving application performance, these insights can help you make smarter decisions.

Learn more about maximizing performance: https://intel.ly/4grKSpT