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

[Feature] Use shared memory from the GPU #191

Closed
NickAcPT opened this issue Dec 19, 2019 · 2 comments
Closed

[Feature] Use shared memory from the GPU #191

NickAcPT opened this issue Dec 19, 2019 · 2 comments
Labels
enhancement New feature or request feature New feature for Spleeter GPU GPU device related issues

Comments

@NickAcPT
Copy link

NickAcPT commented Dec 19, 2019

Description

Since I'm using a laptop, my GPU (GTX 1050) has both dedicated memory (4 GB) and shared memory (it depends on the system's RAM).

The idea behind this request is that sometimes I get an OOM because it only has 4 GB of ram that get used.
Thus, it would be awesome to have spleeter use the whole RAM that's available.
Image with an example of available memory of a GPU

@NickAcPT NickAcPT added enhancement New feature or request feature New feature for Spleeter labels Dec 19, 2019
@aidv
Copy link

aidv commented Dec 19, 2019

I think, but not sure, that that's out of devs control.
I assume it has to be a Tensorflow thing rather than a Spleeter thing.

@aidv
Copy link

aidv commented Dec 19, 2019

Maybe @mmoussallam can confirm? :)

@mmoussallam mmoussallam added the GPU GPU device related issues label May 10, 2020
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request feature New feature for Spleeter GPU GPU device related issues
Projects
None yet
Development

No branches or pull requests

3 participants