[Neuron][CI][WIP] Refactor Neuron kernel tests to improve coverage

[lingfanyu]

This PR aims to modularize testing logic and decompose combinatorial test spaces into many small tests to improve test coverage and code reuse.

Changes in this PR:

• Move input sampling code and pytorch cpu reference version into utils.py
• A FlashPagedAttentionTest to perform Neuron kernel testing logic. This class will be subclassed in later BlockSparse Kernel PR (#13249 )
• [WIP] decompose large test into many small tests for different corner cases

[github-actions[bot]]

👋 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.

🚀

[mergify[bot]]

This pull request has merge conflicts that must be resolved before it can be merged. Please rebase the PR, @lingfanyu.

https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/working-with-forks/syncing-a-fork