Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Estimate memory usage of TensorFlow model #2137

Closed
ndeepesh opened this issue Apr 28, 2023 · 2 comments
Closed

Estimate memory usage of TensorFlow model #2137

ndeepesh opened this issue Apr 28, 2023 · 2 comments

Comments

@ndeepesh
Copy link

Question

Is there a way to estimate TF Memory usage before serving the model. We would like to take actions based on this information like if we want to undeploy some models to meet memory usage limit. Also, can we get this information for before and after model warmup? Since Model Warmup will lead to increased memory usage (based on the fact that tf serving only initializes internal data structures lazily)

@singhniraj08
Copy link

@ndeepesh,

Could you try the memory profiling tool to see if it helps?
You could also take a look at get_memory_info, which provides the current and peak memory that TensorFlow is actually using. If you are more interested in monitoring GPU usage, we already have a ongoing feature request #1407 in progress. Requesting you to close this issue and follow and +1 similar thread for updates.
Thank you!

@google-ml-butler
Copy link

Are you satisfied with the resolution of your issue?
Yes
No

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

No branches or pull requests

2 participants