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

Simplify GPU distribution #16

Open
wants to merge 3 commits into
base: torchserve-23mt-v0.8.0
Choose a base branch
from
Open

Simplify GPU distribution #16

wants to merge 3 commits into from

Conversation

mpoemsl
Copy link
Collaborator

@mpoemsl mpoemsl commented Mar 4, 2024

Simplify GPU distribution so it can be controlled better in a multi-model_server setup.

Changes:

  • Add env var override_gpu_id that makes GPUManager always assign a specified GPU to new workers. Default value is -1, which does not have any effect.
  • Remove GPU failure tracking logic since it is not practical
  • Stochastic GPU distribution weighted by current free memory distribution remains

@mpoemsl mpoemsl requested a review from pypae March 4, 2024 10:41
@mpoemsl
Copy link
Collaborator Author

mpoemsl commented Mar 4, 2024

I'm building multi-platform images for this now as textshuttle/pytorch-serve:torchserve-23mt-v0.8.0-v3-{DEVICE}.

@mpoemsl mpoemsl mentioned this pull request Mar 4, 2024
Open
@mpoemsl
Copy link
Collaborator Author

mpoemsl commented Mar 4, 2024 •
edited
Loading

There exists now a multi-arch image textshuttle/pytorch-serve:torchserve-23mt-v0.8.0-v3-cpu and a single-arch amd image textshuttle/pytorch-serve:torchserve-23mt-v0.8.0-v3-gpu.

JeffWigger
JeffWigger approved these changes Mar 5, 2024
View reviewed changes
Copy link

@JeffWigger JeffWigger left a comment

Choose a reason for hiding this comment

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

These changes look good.

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

@JeffWigger JeffWigger JeffWigger approved these changes

@pypae pypae Awaiting requested review from pypae

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@mpoemsl @JeffWigger