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
GPU Out of Memory #43
Comments
What model and config are you running? You can always reduce the model size by reducing number of layers (e.g. |
I successfully installed the CUDA extension but the script output indicated the extension was not used. Is there anything particular I have to do after installing the extension? |
I am using sashimi and youtube-mix. |
Do you see the extension |
I am running into OOM too. Where do we set Thanks! |
You can pass those in on the command line. Which config/command are you running, and are you using either of the efficient kernels? |
I am running this on colab, so I changed a bit of the code so it works with Python 3.7. I am trying to run the sc09 dataset, and I don't believe I am using any of the efficient kernels. How can I use some of the more efficient kernels? |
You can install pykeops following their instructions: https://www.kernel-operations.io/keops/python/installation.html If you're using the standalone model and not this codebase, you will have to adjust parameters such as |
It worked, I just reduced the layer size. Thank you so much! |
Great! I'm a little confused why the model needs to be shrunk so aggressively, though. I believe our AR generation configs should all fit in a 16Gb GPU (@krandiash is that right?) |
That's correct, you should not need to reduce the size of the model, our models were trained on single 16GiB V100s. If there are differences in terms of available GPU memory I recommend:
|
Sorry for the late reply, but this worked. Thank you so much! |
@davidmrau , I'm closing this issue for now. Feel free to reopen or open a new issue for further questions about GPU memory or the CUDA extension. |
I was wondering what parameters I could change to be able to run it on GPU with limited RAM. I tried reducing the layers to 4, which did not help. Also, it seems like batch size is set to 1 by default. I am using 4x TITAN RTX 24GB.
The text was updated successfully, but these errors were encountered: