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.

Sign up for GitHub

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

Jump to bottom

INT_MAX `local2global` #79

Open

bhack opened this issue Apr 17, 2024 · 0 comments

bhack commented Apr 17, 2024 •

edited

Loading

aot-benchmark/networks/layers/attention.py

Lines 402 to 404 in 6852c2d

    
           global_attn[local_mask.expand(batch_size, self.num_head, 
        
                                         -1, -1, -1)] = local_attn.transpose( 
        
                                             -1, -2).reshape(-1)

This is going to potentially hit pytorch/pytorch#51871 limits also at inference only.

Can you reformulate it e.g. with where or with any other solution?

The text was updated successfully, but these errors were encountered:

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment