[Feat] Allow declaring modelSpec resources directly

[danhubern]

Currently, specifying resources for models is only possible with the modelSpec[].request/limit fields. However, not all use cases are mapped. E.g., setting ephemeral storage resources is not possible.

This PR allows users to declare model resources directly. They take precedence over any request/limit fields. However, if no resources are declared, request/limit fields are used as fallback to avoid breaking changes.

---

• Make sure the code changes pass the pre-commit checks.
• Sign-off your commit by using -s when doing git commit
• Try to classify PRs for easy understanding of the type of changes, such as [Bugfix], [Feat], and [CI].

Detailed Checklist (Click to Expand)

Thank you for your contribution to production-stack! Before submitting the pull request, please ensure the PR meets the following criteria. This helps us maintain the code quality and improve the efficiency of the review process.

PR Title and Classification

Please try to classify PRs for easy understanding of the type of changes. The PR title is prefixed appropriately to indicate the type of change. Please use one of the following:

• [Bugfix] for bug fixes.
• [CI/Build] for build or continuous integration improvements.
• [Doc] for documentation fixes and improvements.
• [Feat] for new features in the cluster (e.g., autoscaling, disaggregated prefill, etc.).
• [Router] for changes to the vllm_router (e.g., routing algorithm, router observability, etc.).
• [Misc] for PRs that do not fit the above categories. Please use this sparingly.

Note: If the PR spans more than one category, please include all relevant prefixes.

Code Quality

The PR need to meet the following code quality standards:

• Pass all linter checks. Please use pre-commit to format your code. See README.md for installation.
• The code need to be well-documented to ensure future contributors can easily understand the code.
• Please include sufficient tests to ensure the change is stay correct and robust. This includes both unit tests and integration tests.

DCO and Signed-off-by

When contributing changes to this project, you must agree to the DCO. Commits must include a Signed-off-by: header which certifies agreement with the terms of the DCO.

Using -s with git commit will automatically add this header.

What to Expect for the Reviews

We aim to address all PRs in a timely manner. If no one reviews your PR within 5 days, please @-mention one of YuhanLiu11
, Shaoting-Feng or ApostaC.

[gemini-code-assist]

Summary of Changes

Hello @danhubern, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request enhances the Helm chart for model deployments by providing a more flexible and direct way to specify resource requirements. It allows users to define comprehensive resource configurations, including types not previously supported by the request/limit fields. The change prioritizes these new direct declarations while maintaining compatibility with existing configurations by falling back to the older method if direct resources are not specified.

Highlights

• Direct Resource Declaration: Introduced the ability to declare model resources directly within the modelSpec configuration, offering more granular control over resource allocation.
• Resource Precedence: Directly declared resources now take precedence over existing request/limit fields, allowing for more specific resource definitions like ephemeral storage.
• Backward Compatibility: Implemented a fallback mechanism where if no direct resources are declared, the system will default to using the request/limit fields, ensuring no breaking changes.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request adds the ability to declare model resources directly, with a fallback mechanism for backward compatibility. The implementation in deployment-vllm-multi.yaml is functionally correct. I have provided one suggestion to refactor the template logic to be more concise and maintainable. For this feature to be fully usable, please also consider updating values.yaml to document the new resources field and values.schema.json to add it to the schema.

[gemini-code-assist]

To make the template more concise and avoid repeating the resources: key, you can use the ternary function to conditionally define the resource content in a variable. This improves readability and maintainability by reducing code duplication.

          {{- $resourceContent := ternary (toYaml $modelSpec.resources) (include "chart.resources" $modelSpec) $modelSpec.resources }}
          resources: {{- $resourceContent | nindent 12 }}

[danhubern]

In my opinion the proposed change by gemini does not increase readability. However, I will happily apply it if that is the preferred way to go. @YuhanLiu11 or @zerofishnoodles what do you think?

[zerofishnoodles]

LGTM