Skip to content

Conversation

cornzz
Copy link
Contributor

@cornzz cornzz commented Aug 28, 2024

Fixes #215

Attention bias was being created on cuda:0 regardless of the selected cuda device as the correct device was not being passed to from_seqlens() in BufferCache.get_input_metadata()

cornzz added 2 commits August 28, 2024 14:09
Attention bias was being moved to cuda:0 regardless of the selected cuda device
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

Successfully merging this pull request may close these issues.

[BUG] Device error when running on other cuda device than cuda:0

2 participants