⚡ Bolt: Optimize rebuild_padding with static dispatch

[ZeyuChen]

Motivation

The rebuild_padding function in fastdeploy/model_executor/pre_and_post_process.py is called frequently during inference. The previous implementation performed platform checks (current_platform.is_cuda(), etc.) and internal imports inside the function body, adding unnecessary overhead to every call.

Modifications

• Hoisted the platform check and rebuild_padding implementation resolution to the module level.
• Defined a _rebuild_padding_impl wrapper function at load time based on current_platform.
• Updated rebuild_padding to call _rebuild_padding_impl directly.

Usage

This change is internal and transparent to callers of rebuild_padding.

Accuracy Tests

• Created a temporary verification script tests/model_executor/test_pre_and_post_process.py (not included in PR) that mocked current_platform and platform-specific ops.
• Verified that rebuild_padding correctly dispatches to the expected backend implementation (CUDA, DCU, CPU, etc.) and handles argument differences correctly.

Checklist

Before the PR, I have done the following:

• I have checked the PR Template to ensure the PR follows the required format.
• I have verified the changes locally using a custom test script.
• I have ensured the code style follows the project standards (to the best of my ability without local linting tools).

---

PR created automatically by Jules for task 17103645859145338122 started by @ZeyuChen

[google-labs-jules]

👋 Jules, reporting for duty! I'm here to lend a hand with this pull request.

When you start a review, I'll add a 👀 emoji to each comment to let you know I've read it. I'll focus on feedback directed at me and will do my best to stay out of conversations between you and other bots or reviewers to keep the noise down.

I'll push a commit with your requested changes shortly after. Please note there might be a delay between these steps, but rest assured I'm on the job!

For more direct control, you can switch me to Reactive Mode. When this mode is on, I will only act on comments where you specifically mention me with @jules. You can find this option in the Pull Request section of your global Jules UI settings. You can always switch back!

New to Jules? Learn more at jules.google/docs.

---

For security, I will only act on instructions from the user who triggered this task.

[CLAassistant]

Thank you for your submission! We really appreciate it. Like many open source projects, we ask that you sign our Contributor License Agreement before we can accept your contribution.
_{You have signed the CLA already but the status is still pending? Let us recheck it.}

[paddle-bot]

Thanks for your contribution!