Add LWS worker-index 0 to sample DS manifest

[abatilo]

If you don't set leaderworkerset.sigs.k8s.io/worker-index=0 for the
router selector like this, then the behavior of the router will
potentially match against one of the non-head pods which is invalid. The
non-head pod will return a 404 and your generations will stall.

Actually, other example manifests have this already. It was just this
one that seems to be missing this label expression.

[gemini-code-assist]

Summary of Changes

Hello @abatilo, 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 resolves a critical issue in a sample DeepSeek manifest by ensuring the inference router correctly identifies and targets the primary worker pod. The change introduces a specific Kubernetes label selector to the manifest, which is essential for stable and error-free operation of the inference service. Additionally, minor formatting inconsistencies within the file have been corrected.

Highlights

• Configuration Correction: I've identified and addressed a critical configuration issue in the deepseek-rdma-pd-rt.yaml manifest. Specifically, I've added the leaderworkerset.sigs.k8s.io/worker-index=0 label selector to both the --prefill-selector and --decode-selector arguments. This ensures that the router consistently targets the correct head pod (worker-index 0) for inference operations, preventing potential 404 errors and stalled generations.
• Manifest Formatting: I've also performed minor clean-up on the deepseek-rdma-pd-rt.yaml file. This includes removing a trailing whitespace character from the --context-length argument and ensuring the file ends with a newline character, improving overall manifest hygiene.

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 in your pull request via creating an issue comment (i.e. comment on the pull request page) using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands.

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 issue 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 is currently in preview and 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 to provide feedback.

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 leaderworkerset.sigs.k8s.io/worker-index=0 selector to the DeepSeek RDMA manifest, which ensures the router targets the LWS head pod, preventing generation stalls. It also includes a suggestion to improve the robustness of how selector arguments are passed to the router script.