About the Ray Libraries (Data, Train, Tune, Serve) category

Ray Libraries (Data, Train, Tune, Serve)
1

Ray AI Runtime (AIR) is a scalable and unified toolkit for ML applications. AIR enables easy scaling of individual workloads, end-to-end workflows, and popular ecosystem frameworks, all in just Python.

AIR comes with ready-to-use libraries for Preprocessing, Training, Tuning, Scoring, Serving, and Reinforcement Learning, as well as an ecosystem of integrations.

Ray AIR Overview
Ray AIR Overview1548×546 45.1 KB

Use this category to post any questions that you may have about Ray AIR!

2

Hi,
dataset map_batches() is async, is it right.
so I need a way to wait map_batches() finish before do other thing.
can you give me solution?

3

Hi @duong_phuc, you do not need to wait map_batches to finish before doing other thing. Please give some extra context what’s other thing you want to do. Or you can use Dataset.materialize() to force execution of map_batches.