other: fix circular import error

[rebel-seinpark]

Pull Request Description

Fix circular import in modeling_attention_utils

Importing constants like DEFAULT_FLASH_ATTN_PARTITION_LENGTH from modeling_attention_utils as the first entry point triggers a circular import error. This happens because the module unconditionally imports RBLNDecoderOnlyModelForCausalLMConfig at the top level, which kicks off a cycle back to this module before it finishes initializing.
Since RBLNDecoderOnlyModelForCausalLMConfig is only used in type annotations, move the import under TYPE_CHECKING and quote the annotation strings.

⚠️ Important: Branch Target

• New features, enhancements, and non-critical fixes: Merge to dev branch
• Critical hotfixes only: Merge to main branch (must also merge to dev)

Please ensure you've selected the correct base branch before submitting!

Type of Change

• Release (dev → main merge for production release)
• New Model Support
• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• Documentation update
• Performance improvement
• Code refactoring
• Other (please describe):

Changes Overview

Motivation and Context

Related Issues

---

Conventional commit

type(optional scope): description

---

Type candidate

• Model Updates
  • model: Adding New models or Bugfix for existing models
    • ex) Add LlavaNext
    • ex) Bugfix Whisper
• Enhancements
  • performance: Optimizing some models or this library itself
    • ex) Loading RBLNModel faster
    • ex) Optimizing Memory Usage of DecoderOnlyModel
• Code Refactor
  • refactor: Re-arrange class architecture, or more.
    • ex) Refactor Seq2Seq
• Documentation
  • doc: Update docstring only
• Library Dependencies
  • dependency: Update requirements, something like that.
• Release
  • release: Merging dev to main for production release
    • ex) Release v1.2.0
• Other
  • other: None of above.
    • ex) ci update
    • ex) pdm update