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

hardware-agnostic front- and backend #2

Open
smedegaard opened this issue Oct 5, 2024 · 1 comment · May be fixed by #5
Open

hardware-agnostic front- and backend #2

smedegaard opened this issue Oct 5, 2024 · 1 comment · May be fixed by #5
Assignees
@smedegaard

Comments

@smedegaard
Copy link
Collaborator

smedegaard commented Oct 5, 2024 •
edited
Loading

The Problem

The detection of, and communication with, AMD GPUs are not implemented in a robust way in Torch Serve.

Suggested Solution

Refactor the Java frontend and python backend so it’s not cuda-centric, without introducing any breaking changes.
@smedegaard smedegaard self-assigned this Oct 15, 2024
@smedegaard smedegaard changed the title Refactor frontend to be hardware-agnostic hardware-agnostic front- and backend Nov 1, 2024
@smedegaard smedegaard linked a pull request Nov 12, 2024 that will close this issue
2 hardware agnostic front and backend #5
Open
15 tasks
@smedegaard
Copy link
Collaborator Author

#5

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

@smedegaard smedegaard

Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

2 hardware agnostic front and backend nod-ai/serve
1 participant
@smedegaard