[XPU] fix xpu to set cudagraph batch sizes

[calvin0327]

Fix: #23039

From the current code, XPU does not support cudagragh, However, XPUModelRunner is intergrated with GPUModelRuner, and the calcaulation of cudagragh_batch_size in GPUModelRunner is not compatible with XPU.

Purpose

Test Plan

Test Result

(Optional) Documentation Update

---

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.

[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.

🚀

[gemini-code-assist]

Code Review

This pull request aims to fix an issue with setting CUDA graph batch sizes on XPU by conditionally initializing cudagraph_batch_sizes only when cudagraph_mode is not NONE. The change is correct for its intended purpose. However, I've identified a critical edge case where an IndexError can occur if CUDA graphs are enabled but no capture sizes are provided, leading to a crash. I've suggested a change to handle this gracefully by disabling CUDA graphs in this scenario and logging a warning.

[LucasWilkinson]

LGTM, thanks for the contribution!