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

[Examples] Add vLLM example #1623

Open
Tracked by #1782 ...
peterschmidt85 opened this issue Aug 26, 2024 · 10 comments
Open
Tracked by #1782 ...

[Examples] Add vLLM example #1623

peterschmidt85 opened this issue Aug 26, 2024 · 10 comments
Labels

Comments

@peterschmidt85
Copy link
Contributor

No description provided.

@peterschmidt85 peterschmidt85 added docs Improvements or additions to documentation examples labels Aug 26, 2024
Copy link

This issue is stale because it has been open for 30 days with no activity.

@github-actions github-actions bot added the stale label Sep 26, 2024
@github-actions github-actions bot removed the stale label Sep 28, 2024
@peterschmidt85 peterschmidt85 changed the title [Docs] Add vLLM example [Examples] Add vLLM example Oct 1, 2024
@peterschmidt85 peterschmidt85 removed the docs Improvements or additions to documentation label Oct 1, 2024
@bikash119
Copy link

Curious to know how vllm is different from this issue?

@peterschmidt85
Copy link
Contributor Author

Curious to know how vllm is different from this issue?

@bikash119
We'd like to have it as a separate example under the Deployment category (in addition to other categories such as Fine-tuning, Accelerators, etc.).

The example should feature most essential information around using vLLM with dstack.

Note, dstack allows to use vllm with both tasks and services. Should we show both, also explaining briefly the difference?

@bikash119
Copy link

Apologies for being a noob here. Under Deployment category means, to provide vllm as a serverless inference service on dstack?

@peterschmidt85
Copy link
Contributor Author

Apologies for being a noob here. Under Deployment category means, to provide vllm as a serverless inference service on dstack?

@bikash119 Currently, there are three categories on https://dstack.ai/examples/: Fine-tuning, Accelerators, and LLMs. Let's add Deployment - can be the first in the list.

@bikash119
Copy link

Ok, so under Deployment , we should have 2 examples shown

  • How to use vLLM for service
  • How to use vLLM for task
    Does this sound ok?

@peterschmidt85
Copy link
Contributor Author

Ok, so under Deployment , we should have 2 examples shown

  • How to use vLLM for service
  • How to use vLLM for task
    Does this sound ok?

Under Deployment, we are going to have one card "vLLM".

This will lead to https://dstack.ai/examples/deployment/vllm.

The sourcecode must be in examples/examples/deployment/vllm/README.md (it's copied to the docs when docs are built). See other cards on https://dstack.ai/examples/ to follow the structure and style.

Let me know if this helps

@bikash119
Copy link

Thank you @peterschmidt85 for being patient with my questions.

@bikash119
Copy link

bikash119 commented Oct 2, 2024

@peterschmidt85 : I have made the required changes. Verifed by executing mkdocs serve

Copy link

github-actions bot commented Nov 2, 2024

This issue is stale because it has been open for 30 days with no activity.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Projects
None yet
Development

Successfully merging a pull request may close this issue.

2 participants