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

Optimize speed and gpu usage for embed #16

Merged
merged 1 commit into from
Oct 13, 2024
Merged

Optimize speed and gpu usage for embed #16

merged 1 commit into from
Oct 13, 2024

Conversation

harshitgupta412
Copy link
Collaborator

torch.cat needs double the memory since it persists original tensors as well as newly created concatenated tensors.

torch.cat needs double the memory since it persists original tensors as well as newly created concatenated tensors.
Copy link
Collaborator

@sidjha1 sidjha1 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@sidjha1 sidjha1 merged commit 863f0b2 into guestrin-lab:main Oct 13, 2024
1 of 2 checks passed
@harshitgupta412 harshitgupta412 deleted the patch-1 branch October 14, 2024 07:34
@sidjha1 sidjha1 mentioned this pull request Oct 22, 2024
sidjha1 added a commit that referenced this pull request Oct 22, 2024
Minor fix from bug caused by
#16. We need to place the
tensors on the proper device. Note: add GPU tests in the future, since
all the tests run on CPU at the moment.
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.

2 participants