We are delighted to kick off New Year with our first exclusive European Ray Meetup with talks from Ray community Ray Serve users in Europe. (Note the meetup is at 5:30-PM CET/ 8:30 AM PST)
Ray Serve is a scalable model serving library for building online inference APIs. Serve is framework agnostic, so you can use a single toolkit to serve everything from deep learning models built with frameworks like PyTorch, Tensorflow, and Keras, to Scikit-Learn models, to arbitrary Python business logic.
Argilla is a production-ready framework for building and improving datasets for NLP projects. This allows you to build robust NLP products through faster data labeling and curation. Argilla.io empowers teams with the easiest-to-use human-in-the-loop and programmatic labeling features.
Agenda: 5:30-PM CET/ 8:30 AM PST
Talk - 0: Welcome remarks & upcoming announcements - Jules Damji, Anyscale
Talk -1: A Brief overview of Ray Serve - Jules S. Damji, Anyscale
Talk -2: Scaling to/from zero on demand with Serve Handle API - Miha Jenko, Outbrain
Talk-3: Smart shortcuts for bootstrapping a modern NLP project - David Berenstein, Argilla.io
Talk 1: : A Brief overview of Ray Serve
Abstract: Ray Serve lets you serve machine learning models in real-time or batch using a simple Python API. Serve individual models or create composite model pipelines, where you can independently deploy, update, and scale individual components.
Bio: Jules S. Damji is a lead developer advocate with the Ray team at Anyscale Inc, an MLflow contributor, and co-author ofLearning Spark, 2nd Edition. He is a hands-on developer with over 25 years of experience. He has worked at leading companies, such as Sun Microsystems, Netscape, @Home, Opsware/LoudCloud, VeriSign, ProQuest, Hortonworks, and Databricks, building large-scale distributed systems. He holds a B.Sc and M.Sc in computer science (from Oregon State University and Cal State, Chico, respectively) and an MA in political advocacy and communication (from Johns Hopkins University).
Talk 2: Scaling to/from zero on demand with Serve Handle API
Abstract: In this talk, we will discuss an implementation of a REST API controller for on-demand scaling of Serve replicas. This process updates Serve Deployment configurations, similarly to the Serve REST API, which has been available since Ray 2.0.0. We will also cover the use case and motivations for this approach, as well as our experience with the Ray developer community.
Bio: Miha Jenko recently joined Outbrain as a data scientist. At his previous employer, he discovered a need for optimizing content management processes specific to e-commerce. This led him to gain experience in implementing various MLOps patterns.Talk 3: Smart shortcuts for bootstrapping a modern NLP project
Abstract: Within NLP, people often struggled with starting projects without decent training data. Nowadays, there are many shortcuts that one can use to get a head start with projects like these by applying techniques such as active learning, weak supervision, few-shot learning, and cross-lingual models. I will show you how to use them and make them work even better using Ray!
Bio: David Berenstein joined Argilla as a developer advocate after having worked on some NLP-related open-source side-projects at his previous company. I love making things work as pragmatic as possible given the available resources.