aws / aws/amazon-sagemaker-examples

memory deallocation issue

Open
#1,424 0 comments 0 reactions 0 assignees View on GitHub
Dominant language
Jupyter Notebook
Stars
11k
Forks
7k
Avg merge
8h 29m
Merged PRs (30d)
8

Description

after serving the request, the instance is not de allocating the used up memory. the graph in the invocation matrices remains flatline after peaking when the request is completed? any idea why it's happening and how to counter
![memory_graph](https://user-images.githubusercontent.com/64765934/90888708-61b44f00-e3d4-11ea-84fc-e6a9028c6ed2.PNG)

Contributor guide

Open the contributing guide

Research direction

No file, notebook, test, or entry point is identified; begin by locating the SageMaker serving example that produced the attached invocation-metrics graph and reproduce the request. Determine whether the flatline is expected managed-instance behavior or an application memory issue, then document the evidence and a verified countermeasure.

Written by the indexing model from the issue text.

Assessment

Tech stack
aws, jupyter-notebook, machine-learning
Domain
cloud, machine-learning, performance
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.