[Doc]Add InternVL3.5 documentation

[nakairika]

What this PR does / why we need it?

Upload doc for InternVL3_5 on Ascend

Does this PR introduce any user-facing change?

How was this patch tested?

ci test refers to #10002

• vLLM version: v0.20.2
• vLLM main: vllm-project/vllm@9090368

[github-actions]

👋 Hi! Thank you for contributing to the vLLM Ascend project. The following points will speed up your PR merge:‌‌

• A PR should do only one thing, smaller PRs enable faster reviews.
• Every PR should include unit tests and end-to-end tests ‌to ensure it works and is not broken by other future PRs.
• Write the commit message by fulfilling the PR description to help reviewer and future developers understand.

If CI fails, you can run linting and testing checks locally according Contributing and Testing.

[gemini-code-assist]

Summary of Changes

Hello, 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 introduces documentation for the InternVL3.5 multimodal model family. It provides users with necessary environment preparation steps, deployment configurations for both single and multi-NPU setups, and guidance on performing accuracy and performance evaluations within the vLLM-Ascend ecosystem.

Highlights

• Documentation Addition: Added comprehensive documentation for the InternVL3.5 model family, including setup, deployment, and evaluation instructions.
• Model Support: Included specific guidance for deploying InternVL3_5-38B and InternVL3_5-241B-A28B models on Ascend NPU environments.

New Features

🧠 You can now enable Memory (public preview) to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

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 the 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 counterproductive. 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.

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 introduces documentation for the InternVL3.5 model family on Ascend NPUs, covering installation, deployment, accuracy evaluation, and performance benchmarking. The review feedback suggests updating the PR title and summary to comply with the repository's style guide, and fixing a tab synchronization conflict where the model selection tab-set incorrectly shares the 'install' sync-group with the installation tab-set.

[gemini-code-assist]

Please update the Pull Request title and summary to adhere to the repository's Pull Request Summary Style Guide.

Suggested PR Title:

[Doc][Misc] Add InternVL3.5 documentation

Suggested PR Summary:

### What this PR does / why we need it?

This PR adds the documentation for the `InternVL3.5` family of models (`InternVL3_5-38B` and `InternVL3_5-241B-A28B`) on Ascend NPUs. It covers supported features, environment preparation (including Docker container setup), deployment (online serving), accuracy evaluation using `lm_eval`, and performance benchmarking.

### Does this PR introduce _any_ user-facing change?

No, this is a documentation-only update.

### How was this patch tested?

This is a documentation update and does not require code testing.

References

1. The Pull Request title and summary must follow the format specified in the Pull Request Summary Style Guide. ^(link)

[gemini-code-assist]

The sync-group for the model selection tab-set is set to install, which is the same as the installation tab-set. Since both tab-sets share the same sync-group and some tab-items share the sync key multi, clicking a model tab (e.g., InternVL3_5-241B-A28B) will unexpectedly switch the active tab in the installation section. Please change the sync-group to a different identifier, such as model, to keep these tab-sets independent.

Suggested change

	:::::{tab-set}
	:sync-group: install
	::::::{tab-set}
	::sync-group: model

[Ronald1995]

should we add doc for multi-node?

[Ronald1995]

it seems like this env is not defined.

[Ronald1995]

As an example, take the mmmu_valdataset as a test dataset, and run accuracy evaluation ofInternVL3_5-241B-A28B in offline mode. you shell script is not matched with description.