Select Your Ticket Type

Training 1: Introduction to Ray for Distributed Applications

An introduction to Ray, the system for scaling your Python and machine learning applications from a laptop to a cluster. We’ll start with a hands-on exploration of the core Ray API for distributed workloads, covering basic distributed Ray Core API patterns, and then move on to a quick introduction to Ray’s native libraries:

• Remote functions as tasks
• Remote objects as futures
• Remote classes as stateful actors
• Quick introduction to Ray’s native libraries

• Understand what the Ray ecosystem is and why to use it
• Learn about Ray Core basic APIs and Python APIs
• Use Ray APIs to convert Python functions and classes into distributed stateless and stateful tasks
• Use Dashboard for inspection
• Learn about the purpose of Ray native libraries and how to use them

Training 2: Machine Learning Model Deployment and Serving with Ray Serve

Ray Serve is a framework-agnostic and Python-first machine learning model serving library built on Ray. This training will cover how Ray Serve makes it easy to deploy, operate, and scale a machine learning model using Ray Serve APIs.

Key takeaways:

• Understand Ray Serve architecture, components, and flow of requests across replicas
• Learn how to use Ray Serve APIs to create, access, and deploy your models and mechanisms to access model deployments via Python APIs and HTTPs endpoints
• Implement common model deployment patterns for serving ML models using the inference graph API as a directed acyclic graph (DAG)
• Scale up/down individual components of an inference graph node, utilizing appropriate hardware resources (GPUs/CPUs) and replicas
• Use operational-friendly APIs to integrate with your custom CI/CD
• Inspect load and deployments in a Ray dashboard

Training 3: Introduction to Reinforcement Learning with RLlib

In this training, you will learn how to apply cutting-edge reinforcement learning (RL) techniques in production with Ray RLlib.

We’ll start with a brief overview of RL concepts, and will then cover how to use Ray RLlib to train and tune contextual bandits as well as the SlateQ algorithm, train off offline data using cutting-edge offline algorithms, and deploy RL models into a live service.

RLlib offers high scalability, a large list of algorithms to choose from (offline, model-based, model-free, etc.), support for TensorFlow and PyTorch, and a unified API for a variety of applications and customizations.

Key takeaways:

• Understand the key concepts, terminology, and algorithms used in RL
• Learn how to use RLlib to train and tune your models
• State-of-the-art RL algorithms with RLlib
• Unified APIs across other Ray native libraries