[Doc] Translated Doc files 2026-09-10

[vllm-ascend-ci]

Auto-Translation Summary

Translated 13 file(s):

• /home/runner/_work/vllm-ascend/vllm-ascend/docs/source/locale/zh_CN/LC_MESSAGES/community/slash-commands.po
• /home/runner/_work/vllm-ascend/vllm-ascend/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/Design_Documents/context_parallel.po
• /home/runner/_work/vllm-ascend/vllm-ascend/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/Design_Documents/quantization.po
• /home/runner/_work/vllm-ascend/vllm-ascend/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/contribution/testing.po
• /home/runner/_work/vllm-ascend/vllm-ascend/docs/source/locale/zh_CN/LC_MESSAGES/getting_started/installation/install_vllm_ascend.inc.po
• /home/runner/_work/vllm-ascend/vllm-ascend/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/features/pd_disaggregation_mooncake_multi_node.po
• /home/runner/_work/vllm-ascend/vllm-ascend/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/features/pd_disaggregation_mooncake_single_node.po
• /home/runner/_work/vllm-ascend/vllm-ascend/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/DeepSeek-V4-Pro.po
• /home/runner/_work/vllm-ascend/vllm-ascend/docs/source/locale/zh_CN/LC_MESSAGES/user_guide/configuration/additional_config.po
• /home/runner/_work/vllm-ascend/vllm-ascend/docs/source/locale/zh_CN/LC_MESSAGES/user_guide/feature_guide/batch_invariance.po
• /home/runner/_work/vllm-ascend/vllm-ascend/docs/source/locale/zh_CN/LC_MESSAGES/user_guide/feature_guide/context_parallel.po
• /home/runner/_work/vllm-ascend/vllm-ascend/docs/source/locale/zh_CN/LC_MESSAGES/user_guide/feature_guide/kv_pool.po
• /home/runner/_work/vllm-ascend/vllm-ascend/docs/source/locale/zh_CN/LC_MESSAGES/user_guide/feature_guide/speculative_decoding.po

---

Workflow run

• vLLM main: vllm-project/vllm@b2f6858

[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 contains automated updates to the Chinese (zh_CN) localization files for the vllm-ascend documentation. These changes ensure that the translated documentation remains synchronized with the latest updates in the source English files, covering installation guides, feature guides, and technical design documents. The updates provide clearer instructions for deployment configurations, including QoS settings and quantization workflows.

Highlights

• Documentation Synchronization: Updated 13 Chinese (zh_CN) localization files to ensure documentation parity with the latest source updates.
• Technical Configuration Updates: Added detailed documentation for QoS configuration, quantization algorithm adaptation, and batch invariance requirements.
• Feature Guidance: Enhanced guides for speculative decoding, context parallelism, and KV pool configurations, including new support details for Model Runner V2.

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

Suggested PR Title:

[Doc][Misc] Update Chinese translations for various features and guides

Suggested PR Summary:

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

This pull request updates the Chinese translations (`.po` files) across multiple documentation modules. The updates cover community slash commands, context parallel design, quantization, testing contribution guides, installation, Mooncake multi-node/single-node features, DeepSeek-V4-Pro model deployment, additional configurations, batch invariance, KV pool, and speculative decoding.

Additionally, a review feedback was provided regarding the translation of "Batch invariance" in `batch_invariance.po`. It was translated as "批处理不变性" in some newly added blocks, which is inconsistent with the rest of the file where it is translated as "批次不变性" or "批量不变性". "批处理" refers to batch processing, which is semantically incorrect for deep learning batch size invariance. It is recommended to update these translations to "批次不变性" for consistency and technical accuracy.

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

No, this PR only updates documentation translations.

### How was this patch tested?

Not applicable as these are documentation translation updates.

[gemini-code-assist]

In the newly added translation blocks, "Batch invariance" is translated as "批处理不变性" (e.g., in lines 216, 223, and 240). However, throughout the rest of this file, "Batch invariance" is consistently translated as "批次不变性" (or "批量不变性").

In deep learning and LLM inference, "batch" refers to a batch of requests/sequences (批次), and "batch invariance" refers to the output being invariant to the batch size (批次大小). "批处理" refers to batch processing (offline jobs), which is semantically incorrect here.

Please update these translations to "批次不变性" to maintain terminology consistency and technical accuracy.

msgid "Batch invariance supports Atlas A2, A3, and Ascend 950 products."
msgstr "批次不变性支持 Atlas A2、A3 和 Ascend 950 产品。"

msgid ""
"Batch invariance requires custom operators for Atlas A2, A3, and Ascend 950 "
"products. Set `VLLM_BATCH_INVARIANT=1` before building vllm-ascend from "
"source to build and install the required operator packages."
msgstr ""
"批次不变性需要为 Atlas A2、A3 和 Ascend 950 产品提供自定义算子。在从源码构建 vllm-ascend 之前设置 "
"`VLLM_BATCH_INVARIANT=1`，以构建并安装所需的算子包。"

msgid "**Ascend 950:**"
msgstr "**Ascend 950：**"

msgid ""
"The A2, A3, and Ascend 950 Docker images for Ubuntu and openEuler build "
"vllm-ascend from source with `VLLM_BATCH_INVARIANT=1`, so the image build "
"installs both the AscendC operator run package and the `batch_invariant_ops`"
" wheel. This build-time environment variable is not retained as a runtime "
"setting. Set `VLLM_BATCH_INVARIANT=1` when starting the server or running "
"offline inference to enable batch invariance."
msgstr ""
"用于 Ubuntu 和 openEuler 的 A2、A3 和 Ascend 950 Docker 镜像在从源码构建 vllm-ascend 时设置了 "
"`VLLM_BATCH_INVARIANT=1`，因此镜像构建会同时安装 AscendC 算子运行包和 `batch_invariant_ops` "
"wheel。该构建时环境变量不会保留为运行时设置。在启动服务器或运行离线推理时设置 `VLLM_BATCH_INVARIANT=1` "
"以启用批次不变性。"