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.

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

Investigate GPU offload in scheduler #137

Open
antoniupop opened this issue Nov 25, 2024 · 3 comments
Open

Investigate GPU offload in scheduler #137

antoniupop opened this issue Nov 25, 2024 · 3 comments
Assignees
@antoniupop

Comments

@antoniupop
Copy link
Contributor

No description provided.

@antoniupop antoniupop self-assigned this Nov 25, 2024
@antoniupop
Copy link
Contributor Author

antoniupop commented Jan 20, 2025 •
edited
Loading

The use of Multi Bit PBS parameters alongside compression is not well supported due to an inconsistency in the HL API.

Issues linked to this:

Work to fix this is still ongoing.

@antoniupop
Copy link
Contributor Author

It is currently not possible to target specific GPUs for execution which restricts the scheduling options and forces multi-gpu usage to parallelize operations rather than across operations.
This has been requested as a feature from tfhe-rs and is now a Q1 ORK: https://github.com/zama-ai/tfhe-rs-internal/issues/889

Work ongoing.

@antoniupop
Copy link
Contributor Author

Performance inconsistencies in ERC20 benchmarks in particular between GPU types (on H100 - with NVLink or SXM).
Ongoing work: https://github.com/zama-ai/tfhe-rs-internal/issues/851

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

@antoniupop antoniupop

Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@antoniupop