[CI] Reduce the time for Diffusion Sequence Parallelism Test

[congw729]

PLEASE FILL IN THE PR DESCRIPTION HERE ENSURING ALL CHECKLIST ITEMS (AT THE BOTTOM) HAVE BEEN CONSIDERED.

Purpose

Reduce the time for the Diffusion Sequence Parallelism Test by separating the test into L2 and L3

Test Plan

Run L2 tests:

pytest -s -v tests/e2e/offline_inference/test_sequence_parallel.py -m core_model

Test Result

Now the time cost is under 10 mins in Buildkite:

Time cost before this PR:

---

Essential Elements of an Effective PR Description Checklist

• The purpose of the PR, such as "Fix some issue (link existing issues this PR will resolve)".
• The test plan, such as providing test command.
• The test results, such as pasting the results comparison before and after, or e2e results
• (Optional) The necessary documentation update, such as updating supported_models.md and examples for a new model.
• (Optional) Release notes update. If your change is user facing, please update the release notes draft.

BEFORE SUBMITTING, PLEASE READ https://github.com/vllm-project/vllm-omni/blob/main/CONTRIBUTING.md (anything written below this line will be removed by GitHub Actions)

[congw729]

@mxuax @yenuo26 PTAL. @hsliuustc0106 Please add a ready label.

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 68dbeaea08

ℹ️ About Codex in GitHub

Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".

[congw729]

@tjtanaa We reduced the test cases for CUDA when PR is labeled ready. Do you need this PR modify the AMD tests for you?

[tjtanaa]

@tjtanaa We reduced the test cases for CUDA when PR is labeled ready. Do you need this PR modify the AMD tests for you?

@congw729 yes. It would be great if you could help to fix the AMD tests as well. Thank you so much. Let me know if you encountered any difficulty.

[congw729]

@hsliuustc0106 This PR can be merged.