[model server] add multi node args check

[rnetser]

Description

How Has This Been Tested?

Merge criteria:

• The commits are squashed in a cohesive manner and have meaningful messages.
• Testing instructions have been added in the PR body (for PRs involving changes that are not immediately obvious).
• The developer has manually tested the changes and verified that the changes work

Summary by Sourcery

Add a test to verify that model arguments are correctly passed to the head pod in multi-node deployments and refactor related test fixtures.

Enhancements:

• Rename and refactor the patched_multi_node_worker_spec fixture to patched_multi_node_spec to handle patching different parts of the predictor spec.

Tests:

• Add test_model_args_added_to_vllm_command to ensure spec.model.args from the InferenceService are included in the vLLM container arguments for the head pod.
• Update existing multi-node tests to use the refactored patched_multi_node_spec fixture for setting pipeline and tensor parallel sizes.

Summary by CodeRabbit

• Tests
  • Updated test parameter names and structure for multi-node NVIDIA model serving tests.
  • Added tests to verify that specific model arguments are correctly added or removed from the model specification.
  • Introduced a utility to check for argument presence in deployed model specs.
  • Improved pod deletion handling in test utilities to ensure completion before proceeding.

[sourcery-ai]

Reviewer's Guide by Sourcery

This pull request renames a test fixture and its corresponding parameter in multi-node tests and adds a new test to verify that model arguments are correctly propagated to the vLLM command in the head pod.

No diagrams generated as the changes look simple and do not need a visual representation.

File-Level Changes

Change	Details	Files
Rename multi-node test fixture and parameter	Rename the patched_multi_node_worker_spec fixture to patched_multi_node_spec. Update test functions to use the new patched_multi_node_spec parameter name. Modify how the fixture accesses parameters from request.param["worker-spec"] to request.param["spec"].	tests/model_serving/model_server/multi_node/test_nvidia_multi_node.py tests/model_serving/model_server/multi_node/conftest.py
Add test for model argument propagation	Add a constant for a specific model argument. Introduce a new test function test_model_args_added_to_vllm_command. Verify that the specified model argument is present in the container arguments of the head pod.	tests/model_serving/model_server/multi_node/test_nvidia_multi_node.py

---

Tips and commands

Interacting with Sourcery

• Trigger a new review: Comment @sourcery-ai review on the pull request.
• Continue discussions: Reply directly to Sourcery's review comments.
• Generate a GitHub issue from a review comment: Ask Sourcery to create an
  issue from a review comment by replying to it. You can also reply to a
  review comment with @sourcery-ai issue to create an issue from it.
• Generate a pull request title: Write @sourcery-ai anywhere in the pull
  request title to generate a title at any time. You can also comment
  @sourcery-ai title on the pull request to (re-)generate the title at any time.
• Generate a pull request summary: Write @sourcery-ai summary anywhere in
  the pull request body to generate a PR summary at any time exactly where you
  want it. You can also comment @sourcery-ai summary on the pull request to
  (re-)generate the summary at any time.
• Generate reviewer's guide: Comment @sourcery-ai guide on the pull
  request to (re-)generate the reviewer's guide at any time.
• Resolve all Sourcery comments: Comment @sourcery-ai resolve on the
  pull request to resolve all Sourcery comments. Useful if you've already
  addressed all the comments and don't want to see them anymore.
• Dismiss all Sourcery reviews: Comment @sourcery-ai dismiss on the pull
  request to dismiss all existing Sourcery reviews. Especially useful if you
  want to start fresh with a new review - don't forget to comment
  @sourcery-ai review to trigger a new review!

Customizing Your Experience

Access your dashboard to:

• Enable or disable review features such as the Sourcery-generated pull request
  summary, the reviewer's guide, and others.
• Change the review language.
• Add, remove or edit custom review instructions.
• Adjust other review settings.

Getting Help

• Contact our support team for questions or feedback.
• Visit our documentation for detailed guides and information.
• Keep in touch with the Sourcery team by following us on X/Twitter, LinkedIn or GitHub.

[github-actions]

The following are automatically added/executed:

• PR size label.
• Run pre-commit
• Run tox
• Add PR author as the PR assignee

Available user actions:

• To mark a PR as WIP, add /wip in a comment. To remove it from the PR comment /wip cancel to the PR.
• To block merging of a PR, add /hold in a comment. To un-block merging of PR comment /hold cancel.
• To mark a PR as approved, add /lgtm in a comment. To remove, add /lgtm cancel.
  lgtm label removed on each new commit push.
• To mark PR as verified comment /verified to the PR, to un-verify comment /verified cancel to the PR.
  verified label removed on each new commit push.
• To Cherry-pick a merged PR /cherry-pick <target_branch_name> to the PR. If <target_branch_name> is valid,
  and the current PR is merged, a cherry-picked PR would be created and linked to the current PR.

Supported labels

{'/hold', '/verified', '/wip', '/lgtm'}

[sourcery-ai]

Hey @rnetser - I've reviewed your changes and they look great!

Here's what I looked at during the review

• 🟢 General issues: all looks good
• 🟢 Security: all looks good
• 🟢 Testing: all looks good
• 🟢 Complexity: all looks good
• 🟢 Documentation: all looks good

---

Sourcery is free for open source - if you like our reviews please consider sharing them ✨

• X
• Mastodon
• LinkedIn
• Facebook

_{Help me be more useful! Please click 👍 or 👎 on each comment and I'll use the feedback to improve your reviews.}

[rnetser]

/verified

[rnetser]

/verified

[coderabbitai]

Walkthrough

The changes update the multi-node model serving test suite and utilities. The fixture for patching multi-node worker specifications was renamed and its patching logic was updated to handle a new spec structure. Test methods were refactored to use the new fixture name and input structure. Two new tests were introduced to verify the addition and removal of a specific model argument in the deployment spec. Additionally, a utility function was added to check for the presence of a model argument in the deployed pod, and the pod deletion logic was adjusted to wait for completion.

Changes

File(s)	Change Summary
tests/model_serving/model_server/multi_node/conftest.py	Renamed fixture from patched_multi_node_worker_spec to patched_multi_node_spec and updated patching logic to use the new spec structure.
tests/model_serving/model_server/multi_node/test_nvidia_multi_node.py	Updated test method signatures to use the new fixture name and structure. Added two new tests for verifying the presence and absence of a specific model argument. Introduced a constant and used a helper function for argument checking.
tests/model_serving/model_server/multi_node/utils.py	Modified pod deletion to wait for completion. Added is_arg_in_model_spec function to check for a model argument in the head pod's spec.

Sequence Diagram(s)

sequenceDiagram
    participant Test as Test Case
    participant Client as DynamicClient
    participant ISVC as InferenceService
    participant Utils as utils.py

    Test->>Client: Request patched InferenceService deployment
    Test->>ISVC: Deploy InferenceService with patched spec
    Test->>Utils: Call is_arg_in_model_spec(client, isvc, arg)
    Utils->>Client: Retrieve pods by generation
    Utils->>ISVC: Identify head pod (not worker)
    Utils->>Client: Get container args from head pod
    Utils-->>Test: Return True/False if arg is present

Loading

Poem

In the warren of tests, a new patch appears,
With specs now more nested, and logic that clears.
Arguments checked, both present and gone,
Utilities waiting till deletions are done.
The rabbits rejoice in their orderly code,
Hopping through fixtures, down the new road!
🐇✨

---

📜 Recent review details

Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between eb79872 and b9c166f.

📒 Files selected for processing (3)

• tests/model_serving/model_server/multi_node/conftest.py (1 hunks)
• tests/model_serving/model_server/multi_node/test_nvidia_multi_node.py (4 hunks)
• tests/model_serving/model_server/multi_node/utils.py (2 hunks)

🔇 Additional comments (9)

tests/model_serving/model_server/multi_node/utils.py (2)

93-93: Good improvement: Wait for pod deletion to complete

Adding wait=True parameter to the pod deletion calls ensures the operation completes before continuing, preventing potential race conditions.

Also applies to: 96-96

---

127-147: Well-implemented function for model argument verification

This new utility function effectively checks if a specific argument is present in the model specification of the head pod, supporting the PR's goal of verifying model arguments are correctly passed to the head pod in multi-node deployments.

tests/model_serving/model_server/multi_node/conftest.py (2)

147-147: Good rename: Better reflects the fixture's purpose

Renaming from patched_multi_node_worker_spec to patched_multi_node_spec makes the fixture name more general, allowing it to patch different parts of the predictor specification beyond just the worker spec.

---

155-155: Improved patching structure for greater flexibility

Using request.param["spec"] directly as the value for the "predictor" key simplifies and makes the patching more flexible, allowing tests to specify different parts of the predictor spec to patch.

tests/model_serving/model_server/multi_node/test_nvidia_multi_node.py (5)

12-12: Good additions for model args testing

Adding the import for is_arg_in_model_spec and defining the MAX_NUM_BATCHED_TOKENS_ARG constant properly support the new tests for model argument verification.

Also applies to: 27-27

---

173-183: Well-adapted test for the new fixture structure

The test has been correctly updated to use the renamed fixture and modified to access the tensor parallel size through the new spec structure.

Also applies to: 186-186, 188-188, 192-192

---

205-216: Well-adapted test for the new fixture structure

The pipeline parallel size test has been correctly updated to use the renamed fixture and the new spec structure.

Also applies to: 219-219, 220-221

---

229-241: Effectively tests model args addition to the head pod

This new test verifies that model arguments from the InferenceService spec are correctly included in the vLLM container args for the head pod, directly addressing the PR objective.

The test uses the new is_arg_in_model_spec helper function to verify that the MAX_NUM_BATCHED_TOKENS_ARG is present in the container arguments when specified in the model spec.

---

242-248: Good complementary test for model args removal

This test verifies that the model arguments are properly removed when not specified in the InferenceService spec, providing complete test coverage for the model args functionality.

The dependency on the previous test ensures proper test execution order.

✨ Finishing Touches

• 📝 Generate Docstrings

---

🪧 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.
  • Generate unit testing code for this file.
  • 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 generate unit testing code for this file.
  • @coderabbitai modularize this function.
• 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 generate unit testing code.
  • @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.
  • @coderabbitai help me debug CodeRabbit configuration file.

Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments.

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 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.

[github-actions]

Status of building tag latest: success.
Status of pushing tag latest to image registry: success.