-
Notifications
You must be signed in to change notification settings - Fork 14
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
Can't use torch.compile #12
Comments
@shikhartuli, not sure if you are still working on this but I have added a compilable vesion of scattermoe here: Also, you seem familiar 🤔 I am still testing it but it seems to work without any graph breaks |
@mayank31398 I was not able to get any speed up with your version when training a 1.5B MoE model on H200s. Could you share your profiling implementation? Also, remember me from IIT? |
@shikhartuli the speedup is more for the full moe. this is the repo: https://github.com/IBM/dolomite-engine I used for training PS: yeah I remember LOL |
When I compile the model, I get the following error. Any idea how to fix this?
The text was updated successfully, but these errors were encountered: