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

Draft an integration of TGI with Jetstream/pytorch #59

Open
tengomucho opened this issue Jun 19, 2024 · 1 comment
Open

Draft an integration of TGI with Jetstream/pytorch #59

tengomucho opened this issue Jun 19, 2024 · 1 comment
Assignees

Comments

@tengomucho
Copy link
Collaborator

Jetstream is a very performant solution for inference for TPUs. The idea is to use their Pytorch implementation and try to use it as backend for TGI.
If the solution is successful, it could eventually replace current optimum-tpu TGI, and the code might land directly as part of TGI.
Note that this will require the models obtained from #58.

@tengomucho tengomucho self-assigned this Aug 30, 2024
@tengomucho
Copy link
Collaborator Author

This is being done in #88

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

1 participant