[docs] update vllm deploy DP docs

[Jintao-Huang]

#6114

[gemini-code-assist]

Summary of Changes

Hello @Jintao-Huang, 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 utility of vLLM deployment documentation and examples. It specifically refines the explanation of the vllm_data_parallel_size parameter's usage across swift commands and introduces a practical example script for setting up data-parallel vLLM deployments. Additionally, it improves the organization of the examples/deploy directory by consolidating related files.

Highlights

• Documentation Update: The documentation for vllm_data_parallel_size has been updated in both Chinese and English versions to clarify its applicability to swift deploy and rollout commands.
• Example Directory Restructuring: The examples/deploy/server directory has been refactored, moving README.md, sglang.sh, and vllm.sh directly into examples/deploy.
• New Data Parallelism Example: A new example script, vllm_dp.sh, has been added to demonstrate how to deploy vLLM with data parallelism using the swift deploy command.

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. ↩

[Jintao-Huang]

/gemini review

[gemini-code-assist]

Code Review

This pull request updates the documentation for vLLM deployment with data parallelism and adds a corresponding example script. I've found a couple of minor issues: one is a suggestion to improve the clarity of the documentation, and the other two are related to a new example script, which contains a typo in the JSON payload and is missing a final newline character.

[gemini-code-assist]

The phrasing "the number of data parallelism (dp) instances" is a bit verbose and less standard than the previous "Data parallelism size". I suggest rephrasing for better clarity and consistency with common terminology.

Suggested change

	- vllm_data_parallel_size: the number of data parallelism (dp) instances, default is `1`, effective in the `swift deploy/rollout` command.
	- vllm_data_parallel_size: Data parallelism size (DP), default is `1`, effective in the `swift deploy/rollout` command.

[gemini-code-assist]

It's a good practice for shell scripts and other text files to end with a newline character. This can prevent potential issues with file processing tools. Please add a newline at the end of the file.

Suggested change

	# }'
	}'

[gemini-code-assist]

Code Review

This pull request updates the documentation and adds an example for using data parallelism (DP) with vLLM for deployment. The changes accurately reflect that vllm_data_parallel_size is now supported in swift deploy. I've provided a couple of suggestions to improve the clarity of the documentation and the new example script. Overall, these are good improvements.

[gemini-code-assist]

For better clarity and conciseness, consider rephrasing this line. The current wording is a bit verbose.

Suggested change

	- vllm_data_parallel_size: Data parallelism size, default is `1`, effective in the `swift deploy/rollout` command.
	- vllm_data_parallel_size: Number of data parallelism (DP) replicas. Default is `1`, effective in the `swift deploy/rollout` command.