Intel Core Ultra Shows Its AI Magic, Runs Over 500 Models Optimized

Intel Core Ultra Shows Its AI Magic, Runs Over 500 Models Optimized

Intel's Core Ultra CPUs bring great AI capabilities through their NPU, as they manage. Run over 500 AI models. On a machine.

Intel demonstrates the capabilities of Core Ultra's dedicated NPUs, managing to run hundreds of AI models.

(News for the newspaper): Today, Intel announced that it has released over 500 AI models running optimized on the new Intel Core Ultra processors – the industry's largest AI PC processor available on the market today, with new AI experiences. , immersive graphics, and great battery life included. This significant milestone is the result of Intel's investments in client AI, AI PC transformation, framework optimization, and AI tools, including the OpenVINO toolkit.

500 models, which can be deployed in central processing unit (CPU), graphics processing unit (GPU), and neural processing unit (NPU), are available from popular industry sources, including OpenVINO Model Zoo, A huggable face, ONX model zoo And P Torch. Models are drawn from categories of spatial AI inference, including big language, diffusion, super-resolution, object detection, image classification/segmentation, computer vision, and others.

Why this is important: The passing of 500 AI models is an important moment for Intel's efforts to nurture and support the AI ​​PC transformation. Not only is the Intel Core Ultra processor the fastest-growing AI PC processor of all time—selling more units per quarter than all competing processors combined in 2023—it's the fastest growing AI PC processor ever. is also the most robust platform, with more AI models, frameworks and runtimes enabled than any other processor vendor.

Models form the backbone of AI-enhanced software features such as object removal, image super-resolution, or text summarization. There is a direct correlation between the number of enabled/optimized models and the breadth of user-facing AI features that can be brought to market. Without a model, a feature cannot be designed. Without runtime optimization, the feature cannot reach its optimal performance.

How AI models work: AI models are one of many important layers in the software stack that determine the ultimate performance, stability, and capabilities of an AI-powered application. AI models are trained to analyze large amounts of data, draw conclusions and take actions based on such findings. Developers building new AI PC features can use and build on these models. The more AI models there are, the more AI PC features will be enabled.

AI models can operate on text, speech, audio, images, and other audiovisual sources common to the PC experience. AI models form the basis of AI-enhanced features designed for users to enjoy, such as automatic text summarization, reducing energy consumption during teleconferencing, or removing unwanted objects from an image. OpenVINO Optimizes runtime for Intel Core Ultra by load balancing across compute units, compressing models to run efficiently in AI PCs, and taking advantage of memory bandwidth and core architecture in Intel Core Ultra .

Continued efforts to enable an unprecedented set of high-performance models on Intel Core Ultra offer a wide field of innovation for software developers and make it easier to deliver AI PC applications and features to users.

About additional features and benefits: Features and benefits of over 500 optimized AI models:

  • Facilitates development and deployment.
  • Covers more than 20 categories of AI, including big language, diffusion, super-resolution, object detection, and computer vision.
  • Contains Phi-2, Mistral, Llama, Bert, Whisper, and Stable Diffusion 1.5.
  • Improves system stability, reliability and performance.

Share this story.



About the Author

Leave a Reply