Stream: AI
Time: 11:15 - 12:00
This is a demo showcasing the journey of deploying an AI model using IBM's Z Deep Learning Compiler (zDLC) from end to end . I will walk you through the process of building as well as training a simple torch model and converting that model to Open Neural Network Exchange (ONNX). From there we will compile the model with zDLC and deploy the same model with Triton. Learn how the zDLC enables you to easily use the IBM Telum on-chip AI accelerator. Come join me on this technical journey and learn why and how to use zDLC especially from a customer perspective. If you are not familiar with some of these terms or products, no worries!! I will make sure to break down each process step by step into the most simplistic explanation. This is something you do not want to miss!
There is currently no attachment for Implementing your AI use cases with IBM's Z Deep Learning Compiler
Megan Hampton is a Backend Developer and Iteration Manager for the IBM Z Deep Learning Compiler (zDLC). Her job consists of writing lower level compiler code in C/ C++ for the IBM and Open Source Community. In addition to development, Megan is also leading a service team for the newly appointed AI ToolKit which provides a plethora of support for AI products on Z. Megan has her Bachelor's Degree from NYU Tandon School of Engineering in Electrical Engineering and her Master's Degree from Marist College in Computer Science. In her free time, Megan loves to volunteer, dance, read, travel and run!
Click here to give some Feedback so we can make it even better next year!