[Misc] Upgrade vllm version to 0408

[Potabk]

What this PR does / why we need it?

For the fusedmoe:
vllm-project/vllm#33049
vllm-project/vllm#35949
FusedMoe refactor

For the qwen3_vl:
vllm-project/vllm#34539
A new Triton kernel has been added for fast rope position encoding. I've added a patch to fallback to native. We'll consider registering custom operators and implementing ascending later.

vllm-project/vllm#38361

Does this PR introduce any user-facing change?

How was this patch tested?

• vLLM version:
• vLLM main: vllm-project/vllm@29e4870

[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 updates the vLLM dependency to a newer commit and aligns the Ascend-specific implementation with recent upstream architectural changes. Key adjustments include refactoring the MoE runner to handle gate parameter storage correctly and cleaning up the input batch initialization logic to reduce code duplication and improve maintainability.

Highlights

• vLLM Version Upgrade: Updated the vLLM dependency to commit 5af684c31912232e5c89484c2e8259e0fac6c55b across all Dockerfiles and documentation.
• MoE Runner Refactoring: Refactored AscendMoERunner to accommodate upstream changes in how gate parameters are stored, ensuring compatibility with the updated FusedMoE implementation.
• Input Batch Optimization: Simplified NPU input batch initialization by leveraging the upstream base class and streamlining NPU-specific tracking structures.

🧠 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/** (6)
  • .github/workflows/bot_pr_create.yaml
  • .github/workflows/dockerfiles/Dockerfile.lint
  • .github/workflows/pr_test_full.yaml
  • .github/workflows/pr_test_light.yaml
  • .github/workflows/schedule_codecov_refresh.yaml
  • .github/workflows/schedule_test_benchmarks.yaml

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. ↩

[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]

Code Review

This pull request updates the vLLM commit hash across multiple Dockerfiles and documentation files to synchronize with the latest upstream changes. It also refactors the MoE runner initialization in vllm_ascend to resolve circular dependencies and potential AttributeError issues by bypassing the FusedMoE.shared_experts property during object construction. Additionally, it cleans up unused imports and refines the NPUInputBatch initialization logic to improve compatibility with upstream structures. The review comments identified critical circular dependency risks in the _init_runner methods, suggesting safer getattr usage to prevent initialization failures.

[github-actions]

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

[Potabk]

The full test passed here https://github.com/vllm-project/vllm-ascend/actions/runs/24225696146/job/70726469550?pr=8060

[Potabk]

VLLM_TAG