Session: Deploying Models at Scale with Apache Beam
Apache Beam is an open source tool for building distributed scalable data pipelines. This talk will explore how Beam can be used to perform common machine learning tasks, with a heavy focus on running inference at scale. The talk will include a demo component showing how Beam can be used to deploy and update models efficiently on both CPUs and GPUs for inference workloads.
An attendee can expect to leave this talk with a high level understanding of Beam, the challenges of deploying models at scale, and the ability to use Beam to easily parallelize their inference workloads.
