Many organizations are already making significant investments in the GenAI and LLMs space. A common challenge that arises centers on how to efficiently scale and productionize these AI workloads.
In this webinar with Anyscale and AWS, you will learn how to leverage the open-source project Ray and EKS (Amazon Elastic Kubernetes Service) to build and scale GenAI and LLM apps.
You will gain insights into using Ray for common ML tasks, such as data preprocessing, model training, and serving. You will discover KubeRay, an open-source Kubernetes operator that simplifies Ray deployments while utilizing both CPU and GPU instances (on-demand and spot). Additionally, you will learn how to quickly set up your Ray project on EKS to streamline your path to production.
Join this session to learn more about:
Ray, an open-source library for scalable, production-grade GenAI and LLM workflows.
KubeRay, a Kubernetes operator that simplifies Ray deployments.
Ray on EKS, including the tools ecosystem and best practices.
Technical demo.
Speakers
Kai-Hsun Chen, SWE at Anyscale and core contributor to KubeRay.
Apoorva Kulkarni, Senior Solutions Architect, AWS.