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

Lack the flexibility to express deploy primitives #81

Open
kerthcet opened this issue Aug 12, 2024 · 4 comments
Open

Lack the flexibility to express deploy primitives #81

kerthcet opened this issue Aug 12, 2024 · 4 comments
Labels
needs-priority Indicates a PR lacks a label and requires one. needs-triage Indicates an issue or PR lacks a label and requires one. question Further information is requested

Comments

@kerthcet
Copy link
Member

What would you like to be cleaned:

For example, people want to deploy the model with different scheduling primitives, colocated or exclusive?

Why is this needed:

Expressing deploy primitives.
@kerthcet kerthcet added the cleanup Categorizes issue or PR as related to cleaning up code, process, or technical debt. label Aug 12, 2024
@InftyAI-Agent InftyAI-Agent added needs-triage Indicates an issue or PR lacks a label and requires one. needs-kind Indicates a PR lacks a label and requires one. needs-priority Indicates a PR lacks a label and requires one. labels Aug 12, 2024
@kerthcet kerthcet changed the title Less the flexibility to express deploy primitives Lack the flexibility to express deploy primitives Aug 12, 2024
@kerthcet
Copy link
Member Author

/kind question
/remove-kind cleanup

@InftyAI-Agent InftyAI-Agent added question Further information is requested and removed cleanup Categorizes issue or PR as related to cleaning up code, process, or technical debt. needs-kind Indicates a PR lacks a label and requires one. labels Aug 12, 2024
@kerthcet
Copy link
Member Author

Right now, people can deploy a more advanced inference workload via Service, this is supported. But with playground, this is not workable.

@kerthcet
Copy link
Member Author

However, especially for multi-host scenarios, topology is important, this is a key problem I think.

@kerthcet
Copy link
Member Author

The general ides would be:

  • For Service, because user has accesses to the whole yaml, so it's supported
  • For Playground, we may support the topologies as another API

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
needs-priority Indicates a PR lacks a label and requires one. needs-triage Indicates an issue or PR lacks a label and requires one. question Further information is requested
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@kerthcet @InftyAI-Agent