[P/D] [Bugfix] mooncake connector device_ids out of index

[LCAIZJ]

What this PR does / why we need it?

In #3579, the local DP rank was changed to the global DP rank, causing users to encounter an error when using the export PHYSICAL_DEVICES=$(ls /dev/davinci* 2>/dev/null | grep -o '[0-9]\+' | sort -n | paste -sd',' -).
@liziyu179

Does this PR introduce any user-facing change?

How was this patch tested?

• vLLM version: v0.11.0
• vLLM main: vllm-project/vllm@83f478b

[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

The pull request effectively addresses the reported bug by correctly using data_parallel_rank_local for device ID calculations, which resolves potential out-of-index errors when determining physical device IDs. The change is clear and directly targets the issue, improving the robustness of the Mooncake connector's device allocation logic.

[github-actions]

This pull request has conflicts, please resolve those before we can evaluate the pull request.