[Misc] upgrade to vllm main

[wangxiyuan]

What this PR does / why we need it?

This PR upgrades the core vLLM dependency to a newer version from the main branch (13397841ab469cecf1ed425c3f52a9ffc38139b5). This is necessary to keep our project up-to-date with the latest features and fixes from upstream vLLM.

1. vllm-project/vllm@ac32e66 pass file is moved.

• vLLM version: v0.15.0
• vLLM main: vllm-project/vllm@d7e17aa

[gemini-code-assist]

Summary of Changes

Hello @wangxiyuan, 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 aims to align the project with the latest vLLM main branch by updating a key dependency reference. To facilitate this upgrade, certain end-to-end tests that may be incompatible or require further investigation have been temporarily disabled, ensuring the continuous integration pipeline can proceed while these issues are addressed.

Highlights

• Dependency Version Update: The vLLM commit hash referenced in the versioning policy documentation has been updated to reflect a newer version of the vLLM main branch.
• Test Skipping: Two end-to-end tests, _run_worker_process in test_aclgraph_capture_replay.py and test_llama_lora in test_llama32_lora.py, have been temporarily marked as skipped with a 'fix me' reason.
• Test Infrastructure: The pytest module was explicitly imported in test_llama32_lora.py to support the test skipping decorator.

🧠 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

• docs/source/community/versioning_policy.md
  • Updated the referenced vLLM commit hash for the main branch from d7e17aaacd5ed1b4b4be6bcfef3a1b7cbc84fc9a to 13397841ab469cecf1ed425c3f52a9ffc38139b5.
• tests/e2e/multicard/2-cards/test_aclgraph_capture_replay.py
  • Marked the _run_worker_process test with @pytest.mark.skip(reason="fix me").
• tests/e2e/singlecard/test_llama32_lora.py
  • Added an import statement for pytest.
  • Marked the test_llama_lora function with @pytest.mark.skip(reason="fix me").

Ignored Files

• Ignored by pattern: .github/workflows/** (5)
  • .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

Activity

• Pull request created by wangxiyuan to upgrade to vllm main.

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. ↩

[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 upgrades the vLLM dependency. However, this has resulted in two end-to-end tests (test_models_aclgraph_capture_replay_metrics_dp2 and test_llama_lora) being disabled with @pytest.mark.skip. While temporarily skipping tests can unblock an upgrade, it introduces a risk of regressions going undetected. It is critical to create follow-up issues to fix and re-enable these tests promptly. I have added comments with this suggestion on the respective lines.

To align with the repository's contribution guidelines, here are suggestions for the PR title and summary:

Suggested PR Title:

[Misc] Upgrade vLLM dependency and skip broken tests

Suggested PR Summary:

### What this PR does / why we need it?
This PR upgrades the core vLLM dependency to a newer version from the main branch (`13397841ab469cecf1ed425c3f52a9ffc38139b5`). This is necessary to keep our project up-to-date with the latest features and fixes from upstream vLLM.

As a consequence of this upgrade, some end-to-end tests are currently failing. To proceed with the upgrade, the following tests have been temporarily disabled:
- `test_models_aclgraph_capture_replay_metrics_dp2` in `tests/e2e/multicard/2-cards/test_aclgraph_capture_replay.py`
- `test_llama_lora` in `tests/e2e/singlecard/test_llama32_lora.py`

Follow-up work is required to fix and re-enable these tests.

### Does this PR introduce _any_ user-facing change?
No, this is an internal dependency upgrade.

### How was this patch tested?
CI will run existing tests. The tests that are broken by this upgrade have been explicitly skipped to allow CI to pass.

[gemini-code-assist]

Skipping this end-to-end test (test_models_aclgraph_capture_replay_metrics_dp2) reduces test coverage and might hide potential regressions. While it's understandable to temporarily skip a broken test during an upgrade, it's crucial to create a follow-up issue to track the fix and re-enable it as soon as possible. Please add a ticket number to the reason string for better tracking, for example: @pytest.mark.skip(reason="fix me - see TICKET-123").

[gemini-code-assist]

This test (test_llama_lora) is being skipped, which can lead to regressions going unnoticed. It's important to address the underlying issue causing the test to fail and re-enable it. Please consider creating a ticket to track this and reference it in the skip reason, e.g., @pytest.mark.skip(reason="Broken after upgrade, see #issue_number").