Skip to content

Conversation

israel-hdez
Copy link

@israel-hdez israel-hdez commented Jul 31, 2025

What this PR does / why we need it:

Port the existing storage-related functionality from single-node workloads to support PVC, OCI, Hugging Face, S3 in multi-node setups.

Both leader and worker pods in the LeaderWorkerSet receive model artifact configuration, and also P/D configurations is covered.

The mutation of the main container command to specify the model location had to be removed from the code and hard-coded in the templates. The motivation is because multi-node (LWS based) deployments are using a smarter start-up script which turns the command more complex. This effectively aligns LLMIsvc implementation to how InferenceServices work: the templates consistently use /mnt/models as the location for loading the model.

Which issue(s) this PR fixes (optional, in fixes #<issue number>(, fixes #<issue_number>, ...) format, will close the issue(s) when PR gets merged):

Related to https://issues.redhat.com/browse/RHOAIENG-27817

Type of changes
Please delete options that are not relevant.

  • New feature (non-breaking change which adds functionality)

Feature/Issue validation/testing:

  • Help needed

Checklist:

  • Have you added unit/e2e tests that prove your fix is effective or that this feature works?
  • Has code been commented, particularly in hard-to-understand areas?
  • [N/A] Have you made corresponding changes to the documentation?
  • Have you linked the JIRA issue(s) to this PR?

Copy link

openshift-ci bot commented Jul 31, 2025

Skipping CI for Draft Pull Request.
If you want CI signal for your change, please convert it to an actual PR.
You can still manually trigger a test run with /test all

Copy link

coderabbitai bot commented Jul 31, 2025

Important

Review skipped

Auto reviews are disabled on base/target branches other than the default branch.

Please check the settings in the CodeRabbit UI or the .coderabbit.yaml file in this repository. To trigger a single review, invoke the @coderabbitai review command.

You can disable this status message by setting the reviews.review_status to false in the CodeRabbit configuration file.

✨ Finishing Touches
🧪 Generate unit tests
  • Create PR with unit tests
  • Post copyable unit tests in a comment

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share
🪧 Tips

Chat

There are 3 ways to chat with CodeRabbit:

  • Review comments: Directly reply to a review comment made by CodeRabbit. Example:
    • I pushed a fix in commit <commit_id>, please review it.
    • Explain this complex logic.
    • Open a follow-up GitHub issue for this discussion.
  • Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query. Examples:
    • @coderabbitai explain this code block.
  • PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
    • @coderabbitai gather interesting stats about this repository and render them as a table. Additionally, render a pie chart showing the language distribution in the codebase.
    • @coderabbitai read src/utils.ts and explain its main purpose.
    • @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.

Support

Need help? Create a ticket on our support page for assistance with any issues or questions.

CodeRabbit Commands (Invoked using PR comments)

  • @coderabbitai pause to pause the reviews on a PR.
  • @coderabbitai resume to resume the paused reviews.
  • @coderabbitai review to trigger an incremental review. This is useful when automatic reviews are disabled for the repository.
  • @coderabbitai full review to do a full review from scratch and review all the files again.
  • @coderabbitai summary to regenerate the summary of the PR.
  • @coderabbitai generate docstrings to generate docstrings for this PR.
  • @coderabbitai generate sequence diagram to generate a sequence diagram of the changes in this PR.
  • @coderabbitai generate unit tests to generate unit tests for this PR.
  • @coderabbitai resolve resolve all the CodeRabbit review comments.
  • @coderabbitai configuration to show the current CodeRabbit configuration for the repository.
  • @coderabbitai help to get help.

Other keywords and placeholders

  • Add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.
  • Add @coderabbitai summary to generate the high-level summary at a specific location in the PR description.
  • Add @coderabbitai anywhere in the PR title to generate the title automatically.

CodeRabbit Configuration File (.coderabbit.yaml)

  • You can programmatically configure CodeRabbit by adding a .coderabbit.yaml file to the root of your repository.
  • Please see the configuration documentation for more information.
  • If your editor has YAML language server enabled, you can add the path at the top of this file to enable auto-completion and validation: # yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json

Documentation and Community

  • Visit our Documentation for detailed information on how to use CodeRabbit.
  • Join our Discord Community to get help, request features, and share feedback.
  • Follow us on X/Twitter for updates and announcements.

… (LWS)

Port the existing storage-related functionality from single-node workloads to support PVC, OCI, Hugging Face, S3 in multi-node setups.

Both leader and worker pods in the LeaderWorkerSet receive model artifact configuration, and also P/D configurations is covered.

The mutation of the `main` container command to specify the model location had to be removed from the code and hard-coded in the templates.  The motivation is because multi-node (LWS based) deployments are using a smarter start-up script which turns the command more complex. This effectively aligns LLMIsvc implementation to how InferenceServices work: the templates consistently use /mnt/models as the location for loading the model.

Signed-off-by: Edgar Hernández <[email protected]>
Add test coverage for PVC storage configuration in multi-node LLM workloads using LeaderWorkerSet, ensuring reconcileMultiNodeWorkload correctly attaches model artifacts from PVC storage.

Signed-off-by: Edgar Hernández <[email protected]>
Add test coverage for OCI storage configuration in multi-node LLM workloads using LeaderWorkerSet, ensuring reconcileMultiNodeWorkload correctly attaches model artifacts from OCI storage

Signed-off-by: Edgar Hernández <[email protected]>
Add test coverage for HF storage configuration in multi-node LLM workloads using LeaderWorkerSet, ensuring reconcileMultiNodeWorkload correctly attaches model artifacts from HF storage

Signed-off-by: Edgar Hernández <[email protected]>
Add test coverage for S3 storage configuration in multi-node LLM workloads using LeaderWorkerSet, ensuring reconcileMultiNodeWorkload correctly attaches model artifacts from S3 storage

Signed-off-by: Edgar Hernández <[email protected]>
- For multi-node, the prefill spec should also include workers and parallelism configurations
- Removing the assertions on the command to specify /mnt/models. This is not compatible with multi-workers case. Since the templates have been changed to hard-coded to use /mnt/models this assertion would no longer be applicable (i.e. assertion on a hard-coded value may not make sense).
- The config_presets_test.go is updated to use /mnt/models.

Signed-off-by: Edgar Hernández <[email protected]>
@israel-hdez israel-hdez force-pushed the llm-storage-multi-node-main-workloads branch from 219b860 to b24e105 Compare August 5, 2025 00:29
@israel-hdez israel-hdez marked this pull request as ready for review August 5, 2025 00:35
@israel-hdez israel-hdez added the tide/merge-method-merge Change lgtm to use a merge commit label Aug 5, 2025
Signed-off-by: Edgar Hernández <[email protected]>
Copy link
Member

@pierDipi pierDipi left a comment

Choose a reason for hiding this comment

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

/lgtm
/approve

Copy link

openshift-ci bot commented Aug 7, 2025

[APPROVALNOTIFIER] This PR is APPROVED

This pull-request has been approved by: israel-hdez, pierDipi

The full list of commands accepted by this bot can be found here.

The pull request process is described here

Needs approval from an approver in each of these files:
  • OWNERS [israel-hdez,pierDipi]

Approvers can indicate their approval by writing /approve in a comment
Approvers can cancel approval by writing /approve cancel in a comment

@openshift-ci openshift-ci bot removed the lgtm label Aug 8, 2025
Copy link

openshift-ci bot commented Aug 8, 2025

New changes are detected. LGTM label has been removed.

Signed-off-by: Edgar Hernández <[email protected]>
@israel-hdez israel-hdez force-pushed the llm-storage-multi-node-main-workloads branch from eb0ac8c to e7fdaa5 Compare August 8, 2025 23:28
@israel-hdez israel-hdez merged commit 7142a8b into opendatahub-io:release-v0.15 Aug 11, 2025
32 of 33 checks passed
@github-project-automation github-project-automation bot moved this from New/Backlog to Done in ODH Model Serving Planning Aug 11, 2025
@israel-hdez israel-hdez deleted the llm-storage-multi-node-main-workloads branch August 11, 2025 03:42
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
approved llm-d tide/merge-method-merge Change lgtm to use a merge commit
Projects
Status: Done
Development

Successfully merging this pull request may close these issues.

2 participants