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

Questions about Autoregressive rollout (loop in python) #116

Closed
helloworld-ren opened this issue Dec 25, 2024 · 3 comments
Closed

Questions about Autoregressive rollout (loop in python) #116

helloworld-ren opened this issue Dec 25, 2024 · 3 comments

Comments

@helloworld-ren
Copy link

Hi,

I tried running the gencast_mini_demo.ipynb in Colaboratory but got a error at the cell block entitled. I don't konw I should how to run it. Any idea on how to get the mini demo running successfully ?

See error:

ValueError: Only interpret mode is supported on CPU backend.

pic2

@vksastry
Copy link

vksastry commented Jan 3, 2025

According to me this is coming from the splash attention which currently only works for TPU. So if you want to use it to run on CPU or GPU override the denoiser_architecture_config.sparse_transformer_config.attention_type to triblockdiag_mha.

@andrewlkd
Copy link
Collaborator

Indeed, as in #113 (comment), this is because of running on CPU.

@helloworld-ren
Copy link
Author

Thank you very much for your reply.I will try your suggestion to run in TPU environment

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

No branches or pull requests

3 participants