[Plot] Rename plot axis label and xlimt start from 0 and update docs

[upfixer]

Rename plot axis label

• Server Output Throughput (tokens/sec)
• Per-Request Inference Speed (tokens/sec)
  plot x-axis start from 0
• Remove y-axis plot cap

[gemini-code-assist]

Summary of Changes

Hello @upfixer, 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 clarity and consistency of performance metric visualizations and reports. It standardizes the terminology used for plot axis labels and titles throughout the application, from user documentation to generated reports and the UI. Additionally, it improves the visual presentation of plots by enforcing that their x-axes always begin at zero, which helps in better understanding the data trends.

Highlights

• Standardized Plot Labels: Renamed plot axis labels and titles across documentation, Excel reports, plot configurations, and UI elements for consistency. Specifically, 'Output Inference Speed per Request (tokens/s)' is now 'Per-Request Inference Speed (tokens/s)' and 'Output Throughput of Server (tokens/s)' is now 'Server Output Throughput (tokens/s)'.
• Improved Plot Visualization: Ensured that the x-axis for relevant plots always starts from zero, providing a clearer and more accurate visual representation of data.

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 renames plot axis labels for consistency and sets the x-axis to start from zero for better visualization. The changes are applied across documentation, plot configurations, plotting functions, UI components, and tests.

[CatherineSue]

What is the reason of the naming change?

[CatherineSue]

Please state in the PR description regarding why we are doing this.

[CatherineSue]

Should we also update the naming on the dashboard here: https://github.com/sgl-project/genai-bench/blob/main/genai_bench/ui/dashboard.py#L244-L253?

To show the difference that one is Server output

[CatherineSue]

Please also:

• Replace plot_experiment_data with plot_experiment_data_flexible in cli.py
• Replace plot_experiment_data with plot_experiment_data_flexible in examples/experiment_plots.py`
• Have a new plot result attached here, use any existing benchmark folder you have

[key4ng]

Have a new plot result attached here, use any existing benchmark folder you have

ran file: examples/experiment_plots.py