[doc]add GLM5.md by nakairika · Pull Request #6709 · vllm-project/vllm-ascend

nakairika · 2026-02-11T14:31:00Z

What this PR does / why we need it?

Add GLM5 doc

Does this PR introduce any user-facing change?

No

How was this patch tested?

vLLM version: v0.15.0
vLLM main: vllm-project/vllm@9562912

gemini-code-assist · 2026-02-11T14:31:13Z

Summary of Changes

Hello @nakairika, 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 new documentation for the GLM-5 model, providing users with essential information to set up, deploy, and evaluate the model effectively within the vLLM-Ascend ecosystem. The added guide covers environment preparation, detailed deployment scenarios for both single and multi-node configurations, and outlines the recommended evaluation procedures, thereby enhancing the platform's support for advanced Mixture-of-Experts models.

Highlights

New Model Documentation: Added a comprehensive documentation file for the GLM-5 model, detailing its integration and usage within the vLLM-Ascend framework.
Environment Setup: Provided instructions for preparing the environment, including model weight downloads and installation steps for both Docker and source builds of vLLM and vLLM-Ascend.
Deployment Guides: Included detailed guides for single-node and multi-node deployment of GLM-5, with specific command-line arguments and environment variable configurations for optimal performance on Atlas A3 devices.
Evaluation Methods: Outlined methods for accuracy and performance evaluation using tools like AISBench and vLLM Benchmark, with references to existing documentation.

🧠 New Feature in Public Preview: You can now enable Memory 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.

Changelog

docs/source/tutorials/models/GLM5.md
- Added new documentation for the GLM-5 model.

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.

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 adds a new documentation page for the GLM-5 model. The documentation provides setup and deployment instructions. My review has identified a few issues that should be addressed to improve the quality and usability of the documentation. The new markdown file contains broken links due to incorrect syntax and includes sections with placeholder text ('Not test yet.'), indicating it is incomplete. Furthermore, the new documentation file is not added to the main table of contents in docs/source/tutorials/models/index.md, which will make it an orphaned page. Also, GLM-5 is not added to the table of supported models in docs/source/user_guide/support_matrix/supported_models.md.

gemini-code-assist · 2026-02-11T14:32:32Z

+Refer to [supported features]([Supported Models — vllm-ascend](https://docs.vllm.ai/projects/ascend/en/latest/user_guide/support_matrix/supported_models.html)) to get the model's supported feature matrix.
+
+Refer to [feature guide]([Supported Features — vllm-ascend](https://docs.vllm.ai/projects/ascend/en/latest/user_guide/support_matrix/supported_features.html)) to get the feature's configuration.


The markdown syntax for these links is incorrect, which will result in them being broken in the rendered documentation. The format [display text]([link text](url)) is not valid. It should be [display text](url).

Suggested change

Refer to [supported features]([Supported Models — vllm-ascend](https://docs.vllm.ai/projects/ascend/en/latest/user_guide/support_matrix/supported_models.html)) to get the model's supported feature matrix.

Refer to [feature guide]([Supported Features — vllm-ascend](https://docs.vllm.ai/projects/ascend/en/latest/user_guide/support_matrix/supported_features.html)) to get the feature's configuration.

Refer to [supported features](https://docs.vllm.ai/projects/ascend/en/latest/user_guide/support_matrix/supported_models.html) to get the model's supported feature matrix.

Refer to [feature guide](https://docs.vllm.ai/projects/ascend/en/latest/user_guide/support_matrix/supported_features.html) to get the feature's configuration.

gemini-code-assist · 2026-02-11T14:32:32Z

+
+### Prefill-Decode Disaggregation
+
+Not test yet.


This section contains placeholder text indicating it is incomplete. Please either provide the content for this section or remove it before merging. Shipping documentation with 'Not test yet' is confusing for users and makes the documentation seem unfinished.

Suggested change

Not test yet.

Not tested yet.

gemini-code-assist · 2026-02-11T14:32:32Z

+
+### Using Language Model Evaluation Harness
+
+Not test yet.


This section contains placeholder text indicating it is incomplete. Please either provide the content for this section or remove it before merging. Shipping documentation with 'Not test yet' is confusing for users and makes the documentation seem unfinished.

Suggested change

Not test yet.

Not tested yet.

wangxiyuan · 2026-02-11T14:36:47Z

+### Model Weight
+
+- `GLM-5`(BF16 version): [Download model weight](https://www.modelscope.cn/models/ZhipuAI/GLM-5).
+- `GLM-5-w4a8`(Quantized version without mtp): [Download model weight](https://modelers.cn/models/Eco-Tech/GLM-5-w4a8).


make sure the weight is avaliable

wangxiyuan · 2026-02-11T14:37:30Z

+# Update the vllm-ascend image according to your environment.
+# Note you should download the weight to /root/.cache in advance.
+# Update the vllm-ascend image
+export IMAGE=m.daocloud.io/quay.io/ascend/vllm-ascend:v0.14.0rc1-a3


update the image tag once it's ready

change to:
glm5
glm5-a3
glm5-openeuler
glm5-a3-openeuler

wangxiyuan · 2026-02-11T14:37:53Z

+git clone https://github.com/vllm-project/vllm-ascend.git
+cd vllm-ascend
+git submodule update --init --recursive
+git checkout ff3a50d011dcbea08f87ebed69ff1bf156dbb01e


make sure the hash is correct

github-actions · 2026-02-11T16:46:26Z

👋 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.

Signed-off-by: nakairika <982275964@qq.com>

…to qwen3next_rebase * 'main' of https://github.com/vllm-project/vllm-ascend: [Docs] Fix GLM-5 deploy command (vllm-project#6711) [npugraph_ex]enable npugraph_ex by default (vllm-project#6664) [doc]add GLM5.md (vllm-project#6709) [Model] GLM5 adaptation (vllm-project#6642) [Bugfix] Update target probs to target logits in rejection sample (vllm-project#6685) [Main][Ops] Make triton rope support index_selecting from cos_sin_cache (vllm-project#5450) [CI]fix nightly multi node test error for wait for pod ready (vllm-project#6675) [main to main] upgrade main 0210 (vllm-project#6673) [main][Quant] Remove unused rotation functions and parameters from W4A4 LAOS quantization (vllm-project#6648) [Test][BugFix] Fix torch.rand usage in triton penalty test (vllm-project#6680) Add Worker Interface:check_health (vllm-project#6681)

### What this PR does / why we need it? Add GLM5 doc ### Does this PR introduce _any_ user-facing change? No ### How was this patch tested? - vLLM version: v0.15.0 - vLLM main: vllm-project/vllm@9562912 Signed-off-by: nakairika <982275964@qq.com> Signed-off-by: momochenchuw <chenchuw@huawei.com>

### What this PR does / why we need it? Add GLM5 doc ### Does this PR introduce _any_ user-facing change? No ### How was this patch tested? - vLLM version: v0.15.0 - vLLM main: vllm-project/vllm@9562912 Signed-off-by: nakairika <982275964@qq.com>

### What this PR does / why we need it? Add GLM5 doc ### Does this PR introduce _any_ user-facing change? No ### How was this patch tested? - vLLM version: v0.15.0 - vLLM main: vllm-project/vllm@9562912 Signed-off-by: nakairika <982275964@qq.com> Signed-off-by: zrj026 <zhangrunjiang026@gmail.com>

### What this PR does / why we need it? Add GLM5 doc ### Does this PR introduce _any_ user-facing change? No ### How was this patch tested? - vLLM version: v0.15.0 - vLLM main: vllm-project/vllm@9562912 Signed-off-by: nakairika <982275964@qq.com>

### What this PR does / why we need it? Add GLM5 doc ### Does this PR introduce _any_ user-facing change? No ### How was this patch tested? - vLLM version: v0.15.0 - vLLM main: vllm-project/vllm@9562912 Signed-off-by: nakairika <982275964@qq.com> Signed-off-by: zrj026 <zhangrunjiang026@gmail.com>

### What this PR does / why we need it? Add GLM5 doc ### Does this PR introduce _any_ user-facing change? No ### How was this patch tested? - vLLM version: v0.15.0 - vLLM main: vllm-project/vllm@9562912 Signed-off-by: nakairika <982275964@qq.com>

nakairika requested review from LCAIZJ, Yikun and wangxiyuan as code owners February 11, 2026 14:31

gemini-code-assist Bot reviewed Feb 11, 2026

View reviewed changes

wangxiyuan reviewed Feb 11, 2026

View reviewed changes

github-actions Bot added the documentation Improvements or additions to documentation label Feb 11, 2026

nakairika force-pushed the main branch 6 times, most recently from c0d31f7 to f38e682 Compare February 11, 2026 17:51

nakairika closed this Feb 11, 2026

nakairika reopened this Feb 11, 2026

nakairika force-pushed the main branch from 8c49ad3 to 5cb798e Compare February 11, 2026 18:49

add glm5

a52f1bb

Signed-off-by: nakairika <982275964@qq.com>

nakairika force-pushed the main branch from 5cb798e to a52f1bb Compare February 11, 2026 18:51

Yikun merged commit b86ea66 into vllm-project:main Feb 11, 2026
11 checks passed

wangxiyuan mentioned this pull request Feb 24, 2026

[Misc]: test #6787

Closed

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

[doc]add GLM5.md#6709

[doc]add GLM5.md#6709
Yikun merged 1 commit intovllm-project:mainfrom
nakairika:main

nakairika commented Feb 11, 2026 •

edited by Yikun

Loading

Uh oh!

gemini-code-assist Bot commented Feb 11, 2026

Uh oh!

gemini-code-assist Bot left a comment

Uh oh!

gemini-code-assist Bot Feb 11, 2026

Uh oh!

gemini-code-assist Bot Feb 11, 2026

Uh oh!

gemini-code-assist Bot Feb 11, 2026

Uh oh!

wangxiyuan Feb 11, 2026

Uh oh!

wangxiyuan Feb 11, 2026

Uh oh!

wangxiyuan Feb 11, 2026

Uh oh!

wangxiyuan Feb 11, 2026

Uh oh!

github-actions Bot commented Feb 11, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

		Refer to [supported features]([Supported Models — vllm-ascend](https://docs.vllm.ai/projects/ascend/en/latest/user_guide/support_matrix/supported_models.html)) to get the model's supported feature matrix.

		Refer to [feature guide]([Supported Features — vllm-ascend](https://docs.vllm.ai/projects/ascend/en/latest/user_guide/support_matrix/supported_features.html)) to get the feature's configuration.

Conversation

nakairika commented Feb 11, 2026 • edited by Yikun Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

What this PR does / why we need it?

Does this PR introduce any user-facing change?

How was this patch tested?

Uh oh!

gemini-code-assist Bot commented Feb 11, 2026

Summary of Changes

Highlights

Footnotes

Uh oh!

gemini-code-assist Bot left a comment

Choose a reason for hiding this comment

Code Review

Uh oh!

gemini-code-assist Bot Feb 11, 2026

Choose a reason for hiding this comment

Uh oh!

gemini-code-assist Bot Feb 11, 2026

Choose a reason for hiding this comment

Uh oh!

gemini-code-assist Bot Feb 11, 2026

Choose a reason for hiding this comment

Uh oh!

wangxiyuan Feb 11, 2026

Choose a reason for hiding this comment

Uh oh!

wangxiyuan Feb 11, 2026

Choose a reason for hiding this comment

Uh oh!

wangxiyuan Feb 11, 2026

Choose a reason for hiding this comment

Uh oh!

wangxiyuan Feb 11, 2026

Choose a reason for hiding this comment

Uh oh!

github-actions Bot commented Feb 11, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

nakairika commented Feb 11, 2026 •

edited by Yikun

Loading