ray-project / ray

Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

Home Page:https://ray.io

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

[Serve] `serve run --reload` to auto-recover during a fatal failure

GeneDer opened this issue · comments

Description

Currently when serve run cli is called with --reload flag, Serve will keep the session alive, watch any file change, and redeploy with the changes. However, if there is a fatal failures with the file, the loop will break and shutdown serve. Ideally we should catch fatal failures and keep serve running until user hit control+c. Let's add a try-except block around the reload function and only break out loop if keyboard interrupt is raised.

Use case

No response