Intel announced support for Microsoft's Phi-3 AI models across its entire range of CPU and GPU product portfolios.
Microsoft's Phi-3 model will take personalized AI computing to a whole new level, running well on all of Blue Team's CPU and GPU products.
Before we get into the details, let's review Microsoft's Phi-3 family of open models. The firm's new GenAI models move beyond industry norms and focus on delivering capabilities at a smaller and more efficient scale. With Phi-3, we can see the emergence of Small Language Models (SLMs), which are ideal for low-power devices with limited processing power.
Fortunately, Intel has become one of the first hardware manufacturers to add support for SLM to its product lineup, and now includes Intel's Gaudi AI accelerator, Xeon and Core Ultra CPUs, and Intel's Arc GPUs (discrete and integrated) are optimized to support Phi. 3 models from Microsoft.
We provide users and developers with powerful AI solutions that use the industry's most advanced AI models and software. Our active collaboration with fellow leaders in the AI software ecosystem, such as Microsoft, is key to making AI ubiquitous. We're proud to work closely with Microsoft to ensure Intel hardware – spanning the data center, edge and client – actively supports several new Phi-3 models.
– Pallavi Mahajan, Intel Corporate VP and GM, Data Center and AI Software
Microsoft has released a number of Phi-3 GenAI models, rated by their respective parameters. These include small, small and medium models. Interestingly, Intel has revealed the performance of its products across all Open models. Starting with Intel's 6th Gen Xeon CPUs (Granite Rapids), the firm benchmarked the Phi-3 Medium 4k and 128k variants, and the platform delivered 2X more performance than its 5th Gen Xeon (Emerald Rapids) counterparts. Presented
Moving on to Intel's Core Ultra CPU platform, the firm says the Phi-3 models will power edge AI processes and offer several benefits such as “personality and responsiveness.” Additionally, the company tested the Phi-3 mini model with Intel's Core Ultra 7 165H, with an Arc A770 discrete GPU onboard, and the benchmarks showed impressive performance and token generation latency. .
The debut of Microsoft's Phi-3 AI models will truly open new doors in the era of personalized AI computing, and with the performance of modern-day processors, running such models will not be a problem.
News Source: Intel