Intel Select Solutions for AI Inferencing – Intel Conversations in the Cloud – Episode 170

 
Share
 

Manage episode 231569587 series 29991
By Discovered by Player FM and our community — copyright is owned by the publisher, not Player FM, and audio streamed directly from their servers.

In this Intel Conversations in the Cloud audio podcast: On this week’s episode of Conversations in the Cloud, we talk to Prashant Shah, Director of Engineering for Health and Life Sciences at Intel. Prashant provides a grounding in what inferencing, which is when a model that’s been built and trained is then productized and put into the real world, to be applied to use cases with new data.

Intel Select Solutions for AI Inferencing is meant for companies looking to productize AI models for a range of use cases. Ultimately customers want a robust solution that is also cost effective, which is where the Intel Select Solutions for AI Inferencing comes in, providing a high performance inferencing solution on general purpose hardware. With the second generation Intel Xeon Scalable processor, there are new features like Intel Deep Learning Boost, which helps accelerate deep learning applications and allows companies to deploy the solution for real-time use cases. Prashant notes a customer that is working with medical imaging workloads was able to achieve 5.5X faster performance. Prashant notes that as inferencing models are refine and new ones created, that we will see more complex offerings for a broader range of applications.

For more information visit:
AI.intel.com
intel.com/selectsolutions

See the white paper at:
intel.ai/wp-content/uploads/sites/69/SiemensHealthineers2ndGenXeonScalable.pdf

883 episodes available. A new episode about every day .