[CI/Build] Use spawn multiprocessing mode for V1 test pipeline

[russellb]

I've seen multiple failures related to forking new processes after
cuda has been initialized in this pipeline. Other pipelines use spawn,
so this change applies the same to this one.

Signed-off-by: Russell Bryant [email protected]

[github-actions]

👋 Hi! Thank you for contributing to the vLLM project.

💬 Join our developer Slack at https://slack.vllm.ai to discuss your PR in #pr-reviews, coordinate on features in #feat- channels, or join special interest groups in #sig- channels.

Just a reminder: PRs would not trigger full CI run by default. Instead, it would only run fastcheck CI which starts running only a small and essential subset of CI tests to quickly catch errors. You can run other CI tests on top of those by going to your fastcheck build on Buildkite UI (linked in the PR checks section) and unblock them. If you do not have permission to unblock, ping simon-mo or khluu to add you in our Buildkite org.

Once the PR is approved and ready to go, your PR reviewer(s) can run CI to test the changes comprehensively before merging.

To run CI, PR reviewers can either: Add ready label to the PR or enable auto-merge.

🚀

[youkaichao]

@russellb can you help investigate which line initializes cuda too early?

[youkaichao]

you can check https://github.com/vllm-project/vllm/blob/main/tests/standalone_tests/lazy_imports.py to see how to find the first line that does anything (e.g. initialize cuda, imports a module).