[XPU] Add xpu torch.compile support

[jikunshang]

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.

Purpose

This PR enable torch compile on XPU platform. user can enable with -O3 option
limitations:

• due to xpu still use ipex kernels for now, custom ops are not register. all custom ops (except attention) are not enabled, will use torch native impl. we will improve this with vllm-xpu-kernels. meanwhile, almost all custom passes are not supported.
• xpu not support graph mode yet. so bypass graph capture, which means we still need --enforce-eager on xpu platform.

Test Plan

add a test in CI.

Test Result

(Optional) Documentation Update

[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 adds torch.compile support for the XPU platform. The changes correctly bypass CUDA graph capture and functionalization passes which are not yet supported on XPU. However, there is a critical issue where the XPU platform is configured to use CUDAPiecewiseBackend, which contains CUDA-specific API calls for graph capture. This will lead to runtime errors on XPU. I've provided a comment with a suggested fix.

[gemini-code-assist]

Using CUDAPiecewiseBackend for XPU is problematic as it contains CUDA-specific code (e.g., torch.cuda.CUDAGraph) that will fail on XPU platforms.

The PR description mentions that XPU does not support graph mode yet, which suggests that graph capture should be disabled. However, compilation_config.use_cudagraph is enabled by default for the V1 engine and is not disabled for the XPU platform. This will cause CUDAPiecewiseBackend to attempt CUDA graph capture, leading to a runtime error.

To fix this, you should disable CUDA graph capture for the XPU platform within torch.compile. A possible fix is to add vllm_config.compilation_config.use_cudagraph = False to the XPUPlatform.check_and_update_config method. Alternatively, you could create a new XPUPiecewiseBackend that does not contain CUDA-specific graph capture logic and use it here.