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

feat: Add sample blueprint to run stable diffusion model on inferentia2 #405

Closed
wants to merge 0 commits into from

Conversation

ratnopamc
Copy link
Collaborator

@ratnopamc ratnopamc commented Jan 24, 2024

What does this PR do?

🛑 Please open an issue first to discuss any significant work and flesh out details/direction - we would hate for your time to be wasted.
Consult the CONTRIBUTING guide for submitting pull-requests.

This PR showcases a sample blueprint that deploys a stable diffusion model using rayserve on inferentia2 accelerator.

Motivation

This addresses existing issue - #371

More

  • Yes, I have tested the PR using my local account setup (Provide any test evidence report under Additional Notes)
  • Mandatory for new blueprints. Yes, I have added a example to support my blueprint PR
  • Mandatory for new blueprints. Yes, I have updated the website/docs or website/blog section for this feature - work in progress.
  • Yes, I ran pre-commit run -a with this PR. Link for installing pre-commit locally

For Moderators

  • E2E Test successfully complete before merge?

Additional Notes

@ratnopamc ratnopamc changed the title Example blueprint to run stable diffusion model on inferentia2 feat:Example blueprint to run stable diffusion model on inferentia2 Jan 24, 2024
@ratnopamc ratnopamc changed the title feat:Example blueprint to run stable diffusion model on inferentia2 feat: Add sample blueprint to run stable diffusion model on inferentia2 Jan 24, 2024
Copy link
Collaborator

@vara-bonthu vara-bonthu left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks @ratnopamc ! I have added few comments. Could you also write a Website Doc for end to end deployment?

ai-ml/trainium-inferentia/variables.tf Outdated Show resolved Hide resolved
ai-ml/trainium-inferentia/variables.tf Outdated Show resolved Hide resolved
ai-ml/trainium-inferentia/variables.tf Outdated Show resolved Hide resolved
memory: "8G"
nodeSelector:
#provisioner: default
workload: "rayhead"
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Is this using CS or karpenter? you can remove commented config or add details about why its commented


labels = {
instance-type = "inf2-8xl"
//provisioner = "cluster-autoscaler"
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

remove the commented line

ai-ml/trainium-inferentia/eks.tf Outdated Show resolved Hide resolved
ai-ml/trainium-inferentia/eks.tf Outdated Show resolved Hide resolved
instance-type = "inf2"
provisioner = "cluster-autoscaler"
instance-type = "inf2-24xl"
//provisioner = "cluster-autoscaler"
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

remove the comment

@ratnopamc
Copy link
Collaborator Author

Closed. A new PR #406 is tracking this issue.

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

Successfully merging this pull request may close these issues.

2 participants