Faster and Cheaper Offline Batch Inference with Ray
Offered By: Anyscale via YouTube
Course Description
Overview
Explore the capabilities of Ray Data, an open-source library for large-scale data processing in machine learning applications, with a focus on offline batch inference. Learn how to efficiently process terabytes of data using pretrained models, understand the limitations of traditional data processing tools for modern deep learning applications, and discover how to leverage Ray Data for faster and more cost-effective inference compared to solutions like Spark or SageMaker. Delve into the importance of offline inference for LLM workloads and witness a demonstration of an end-to-end offline batch inference use case. Gain insights into user success stories and understand why Ray Data is considered the optimal solution for offline batch inference and processing, particularly when working with unstructured data and deep learning models.
Syllabus
Faster and Cheaper Offline Batch Inference with Ray
Taught by
Anyscale
Related Courses
Artificial Intelligence for RoboticsStanford University via Udacity Intro to Computer Science
University of Virginia via Udacity Design of Computer Programs
Stanford University via Udacity Web Development
Udacity Programming Languages
University of Virginia via Udacity