[Cherry-pick][releases/v0.26.0rc][Bugfix][MRV2][Spec Decode] Fix draft token offset in bad words kernel (from #14433)

[vllm-ascend-ci]

Cherry-pick of PR #14433 onto releases/v0.26.0rc.

Original PR: #14433
Original author: @SOMEONEUNSEEN

---

What this PR does / why we need it?

同步上游更改
vllm-project/vllm#52311

Does this PR introduce any user-facing change?

How was this patch tested?

• vLLM version: v0.26.0
• vLLM main: vllm-project/vllm@d02df74

[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 cherry-picks a fix from the upstream repository to address an off-by-one error occurring during speculative decoding. By adjusting the memory offset when loading draft tokens, the kernel now correctly identifies tokens, ensuring accurate filtering of bad words.

Highlights

• Bug Fix: Corrected the draft token offset calculation in the bad words kernel to properly account for the last committed token.

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:

[Ops][BugFix] Correct draft token offset in bad_words_kernel

Suggested PR Summary:

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

This PR fixes an indexing issue in `_bad_words_kernel` when loading draft tokens. It adds `+ 1` to the offset calculation because the token at local position 0 is the last committed token, and draft tokens start at local position 1.

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

No.

### How was this patch tested?

Not specified in the patch.

I have reviewed the changes and have no additional feedback to provide as there are no review comments.

[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.

---

Tip

💡 Consider Linking a Related Issue or RFC

Your PR title contains the [BugFix] tag, indicating a bug fix or new feature.

Linking a related issue or RFC in the PR description is strongly encouraged — it gives reviewers helpful context and speeds up the review. You can use any of these keywords:

• Fixes #<issue_number>
• Closes #<issue_number>
• Resolves #<issue_number>
• Refs #<rfc_or_issue_number> (for RFCs)

🙏 Thanks for helping us keep the project well-organized!