[CI/NPU] Fix ascend CI issue

[ocss884]

Motivation

See: https://github.com/sgl-project/sglang/actions/runs/20914212553/job/60083859620?pr=16945

Modifications

Accuracy Tests

Benchmarking and Profiling

Checklist

• Format your code according to the Format code with pre-commit.
• Add unit tests according to the Run and add unit tests.
• Update documentation according to Write documentations.
• Provide accuracy and speed benchmark results according to Test the accuracy and Benchmark the speed.
• Follow the SGLang code style guidance.

Review Process

1. Ping Merge Oncalls to start the PR flow. See the PR Merge Process.
2. Get approvals from CODEOWNERS and other reviewers.
3. Trigger CI tests with comments or contact authorized users to do so.
   • /tag-run-ci-label, /rerun-failed-ci, /tag-and-rerun-ci
4. After green CI and required approvals, ask Merge Oncalls to merge.

[gemini-code-assist]

Summary of Changes

Hello @ocss884, 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 provides a targeted fix for a CI issue affecting Ascend NPU tests. The problem stemmed from an incorrect method of passing command-line arguments to a subprocess, where a list of tokens was being treated as a single argument rather than being expanded into multiple distinct arguments. The change ensures that the test suite can now correctly configure and run the piecewise CUDA graph prefill tests on Ascend hardware, thereby stabilizing the CI pipeline for this specific environment.

Highlights

• CI Fix for Ascend NPU: This pull request addresses and resolves a continuous integration (CI) failure specifically impacting tests for Ascend NPU (Neural Processing Unit) environments.
• Argument Unpacking Correction: The core change involves correcting how a list of tokens (TOKENS_TO_CAPTURE) is passed as arguments to a subprocess command. By using the * operator, the list is now properly unpacked into individual arguments, which was essential for the command to execute correctly.

🧠 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.

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.

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

This PR correctly fixes an issue with command-line argument passing in an Ascend CI test by unpacking a list of tokens. I've added a comment to point out a similar issue in another test within the same file that should also be addressed to ensure consistency and correctness across all related tests.

[gemini-code-assist]

This change correctly fixes the argument passing. A similar issue exists in the TestPiecewiseGraphPrefillBenchmark class on line 82, where TOKENS_TO_CAPTURE also needs to be unpacked. Please apply the same fix there to ensure the benchmark test runs correctly.

Suggested change for line 82:

                *TOKENS_TO_CAPTURE,

[ping1jing2]

/tag-and-rerun-ci

[ping1jing2]

thanks for your contribution, and we have another duplicate PR #16933 fix it.

[ping1jing2]

sorry for close it, i found your changes is better than his, thank you.

[OrangeRedeng]

need the same fix here

[iforgetmyname]

/tag-and-rerun-ci

[iforgetmyname]

/rerun-failed-ci

[iforgetmyname]

nice work! thx