[Doc][Release] Prepare v0.18.0rc1 release state

[yiz-liu]

Summary

• align the v0.18.0rc1 release notes, version references, FAQ feedback link, contributors list, and manual release workflow options across the repo
• update the release prep so only durable docs/workflow changes are included; temporary release-note workspace artifacts are intentionally excluded
• surface the most important still-open milestone items for release readiness review before the RC is finalized

Pending milestone PRs to watch

The following open v0.18.0rc1 milestone PRs look most relevant to release readiness or user-facing messaging:

• [Core][DSA] multistream overlap support for DSA models #7577 — multistream overlap support for DSA models; explicit user-facing opt-in feature with latency/throughput impact
• [bugfix]fixed block_size incorrect setting issue in dsv3.2 #7630 — fixes incorrect DSV3.2 block size when users do not pass --block-size
• [Bugfix]fix ds3.2 dcp mtp #7617 — fixes a DS3.2 DCP/MTP overlap issue
• Qwen3.5 MoE supports flash comm #7486 — enables flash comm support for Qwen3.5 MoE
• fix uncompatible between fc1 and non-sp-padding #7614 — narrower Kimi2.5 + flashcomm compatibility fix, worth watching if that path is in RC scope

Does this PR introduce any user-facing change?

Yes.
It updates the published v0.18.0rc1 release notes and the user-facing documentation/version references that point users at the current RC.

How was this patch tested?

• created and updated the v0.18.0rc1 feedback issue and release checklist during release prep

• validated the modified workflow YAML files with yaml.safe_load()

• verified docs/source/conf.py substitutions by executing the file and checking the emitted version values

• manually reviewed the release note citations against the merged PRs used for this RC prep

• vLLM version: v0.18.0

• vLLM main: vllm-project/vllm@ed359c4

[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 focuses on preparing the vLLM Ascend project for its v0.18.0rc1 release candidate. It involves a comprehensive update of version numbers, dependency requirements, and documentation across the repository to reflect the upcoming release. The changes ensure that all user-facing information and internal configurations are consistent with the new release, providing clarity for users and developers alike.

Highlights

• Release Candidate Preparation: Prepared the repository for the v0.18.0rc1 release by aligning release notes, version references, FAQ feedback links, and the contributors list across various documentation files.
• Dependency Updates: Updated the required CANN version to 8.5.1 in documentation and configuration files.
• Version String Alignment: Synchronized vLLM Ascend and vLLM version strings to v0.18.0rc1 and v0.18.0 respectively, across README files, conf.py, and versioning_policy.md.
• Contributor List Update: Refreshed the list of contributors in docs/source/community/contributors.md to include recent contributions up to March 25, 2026.
• Detailed Release Notes: Added comprehensive release notes for v0.18.0rc1 in docs/source/user_guide/release_notes.md, detailing new features, performance improvements, dependency upgrades, documentation updates, and various fixes.

🧠 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.

Ignored Files

• Ignored by pattern: .github/workflows/** (2)
  • .github/workflows/schedule_image_build_and_push.yaml
  • .github/workflows/schedule_release_code_and_wheel.yml

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.

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][Feature] Update documentation for v0.18.0rc1 release

Suggested PR Summary:

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

This pull request updates various documentation and configuration files to reflect the release of `vLLM Ascend v0.18.0rc1` and its compatibility with `vLLM v0.18.0`. Key changes include:
- Updating `CANN` and `vLLM` version numbers in `README.md` and `README.zh.md`.
- Adding `v0.18.0rc1` to the release compatibility matrix and release cadence in `versioning_policy.md`.
- Updating `vLLM` and `vLLM Ascend` versions in `conf.py`.
- Adding a new FAQ entry for `v0.18.0rc1` and clarifying the versioning policy in `faqs.md`.
- Incorporating comprehensive release notes for `v0.18.0rc1` in `release_notes.md`, detailing new features, performance optimizations, dependency upgrades, and bug fixes.
- Updating the contributors list in `contributors.md`.
These updates are necessary to keep the project documentation current with the latest release candidate.

Fixes #

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

Yes, this PR introduces user-facing changes in the documentation, including updated version numbers, compatibility information, release notes detailing new features and fixes, and an updated FAQ section. These changes provide users with current information about the `v0.18.0rc1` release.

### How was this patch tested?

The changes are primarily documentation updates. No new tests were added. The existing CI should ensure that the documentation builds correctly.

[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.

[github-actions]

This pull request has conflicts, please resolve those before we can evaluate the pull request.