[Refactor]310p_e2e test case update

[pu-zhe]

What this PR does / why we need it?

This pull request significantly enhances the test suite by adding new end-to-end test cases for Qwen3 models on the 310P hardware platform. The primary goal is to ensure the stability and correctness of these models under diverse operational conditions, including various parallelism strategies, data types, and quantization methods.

Does this PR introduce any user-facing change?

No

How was this patch tested?

E2E test

• vLLM version: v0.15.0
• vLLM main: https://github.com/vllm-project/vllm/commit/v0.15.0

[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]

Summary of Changes

Hello @pu-zhe, 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 significantly enhances the test suite by adding new end-to-end test cases for Qwen3 models on the 310P hardware platform. The primary goal is to ensure the stability and correctness of these models under diverse operational conditions, including various parallelism strategies, data types, and quantization methods. These additions are crucial for maintaining the quality and reliability of the vLLM-ascend project's support for Qwen3 models.

Highlights

• New End-to-End Tests for Qwen3 Models: This pull request introduces a series of new end-to-end test cases specifically designed for Qwen3 models on the 310P platform.
• Comprehensive Test Coverage: The added tests cover various configurations, including dense and Mixture-of-Experts (MoE) Qwen3 models, different tensor parallelism sizes (1, 2, and 4), FP16 data type, and W8A8 quantization with Ascend-specific settings.
• Single and Multi-Card Scenarios: New test files are organized to validate both single-card and multi-card (tensor parallelism) execution environments for Qwen3 models.

🧠 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

• tests/e2e/310p/multicard/test_qwen3_dense.py
  • Added new test file.
  • Introduced test_qwen3_dense_tp2_fp16 for Qwen3-8B with 2-way tensor parallelism and FP16.
  • Introduced test_qwen3_dense_tp4_w8a8 for Qwen3-32B-W8A8 with 4-way tensor parallelism, FP16, and Ascend quantization.
• tests/e2e/310p/multicard/test_qwen3_moe.py
  • Added new test file.
  • Introduced test_qwen3_moe_tp4_fp16 for Qwen3-30B-A3B (MoE) with 4-way tensor parallelism and FP16.
  • Introduced test_qwen3_moe_ep4_fp16 for Qwen3-30B-A3B (MoE) with 4-way tensor parallelism, FP16, and expert parallelism enabled.
• tests/e2e/310p/singlecard/test_qwen3_dense.py
  • Added new test file.
  • Introduced test_qwen3_dense_tp1_fp16 for Qwen3-8B with single-card (TP1) and FP16.
  • Introduced test_qwen3_dense_tp1_w8a8 for Qwen3-8B-W8A8 with single-card (TP1), FP16, and Ascend quantization.

Ignored Files

• Ignored by pattern: .github/workflows/** (1)
  • .github/workflows/_e2e_test.yaml

Activity

• The pull request was opened by pu-zhe.
• No review comments or approvals have been recorded yet.
• No specific progress updates or discussions have been noted.

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 pull request adds end-to-end tests for Qwen3 models on 310p devices. The new tests are a good addition. However, there is significant code duplication within each new test file. I've provided suggestions to refactor the tests using pytest.mark.parametrize. This will reduce duplication, improve readability, and make the tests more maintainable.