Loading…
December 5-6, 2022
Yokohama, Japan + Virtual
View More Details & Registration
Note: The schedule is subject to change.

The Sched app allows you to build your schedule but is not a substitute for your event registration. You must be registered for Open Source Summit Japan 2022 to participate in the sessions. If you have not registered but would like to join us, please go to the event registration page to purchase a registration.

This schedule is automatically displayed in Japan Standard Time (UTC +9). To see the schedule in your preferred timezone, please select from the drop-down menu to the right, above "Filter by Date."

IMPORTANT NOTE: The timing of sessions and room locations are subject to change.

Tuesday, December 6 • 16:50 - 17:30
How to Create a Custom Serving Runtime in KServe ModelMesh to Serve Your Models - Rafael Vasquez & Christian Kadner, IBM

Sign up or log in to save this to your schedule, view media, leave feedback and see who's attending!

Feedback form is now closed.
KServe ModelMesh comes with a few built-in serving runtimes to serve models in common ML frameworks. However, at times there is a need to serve models in custom runtimes, specially built to satisfy various requirements. In this talk, we will introduce ModelMesh key features, and then share hands-on experience of building a new container image with support for the desired framework. The following will be covered: - Overview of ModelMesh - Demo of loading models in existing model server - Metrics and dashboard - How to create a new custom serving runtime - Demo of running prediction using custom serving runtime

Speakers
avatar for Christian Kadner

Christian Kadner

Software Developer, IBM
Christian Kadner is a software developer at the IBM with a background in systems engineering and data management. Most recently he has been working on Kubeflow Pipelines on Tekton, the Machine Learning eXchange (MLX) and KServe/ModelMesh.



Tuesday December 6, 2022 16:50 - 17:30 JST
414&415
  Open AI & Data Forum