fix: remove GPU node selector from benchmark jobs

[abatilo]

Benchmark jobs execute performance tests against inference services and
don't require GPU resources themselves. Removing the nvidia.com/gpu node
selector allows these jobs to run on any available node, improving
scheduling flexibility and resource utilization.

[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 optimizes the scheduling and resource utilization for benchmark jobs by removing their explicit dependency on GPU-enabled nodes. Since these jobs perform performance tests against inference services and do not inherently require GPU resources, this change allows them to be scheduled more flexibly across the cluster, enhancing overall efficiency.

Highlights

• Resource Optimization: Removed the nvidia.com/gpu node selector and associated tolerations from the default pod specifications for benchmark jobs. This ensures that benchmark jobs, which do not require GPU resources, are no longer constrained to GPU-enabled nodes.
• Scheduling Flexibility: By removing the GPU node affinity, benchmark jobs can now be scheduled on any available node within the cluster, significantly improving scheduling flexibility.
• Improved Resource Utilization: This change contributes to better overall cluster resource utilization by preventing non-GPU-dependent benchmark jobs from occupying valuable GPU node capacity, freeing up those resources for workloads that genuinely require them.

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 removes the hardcoded GPU node selector and tolerations from benchmark jobs, improving scheduling flexibility. There is a suggestion to improve maintainability by reducing code duplication.

[slin1237]

GenAI-bench requires tokenizer
That tokenizer is currently only available in GPU nodes
the problem is probably how we handled getting the tokenizer benchmark controller