perf(mlx): rope supports batch offset

[TianyiZhao1437]

📋 PR Title Format

The PR title should follow the format:

type(scope): concise message (max 50 chars)

Where:

• type is one of: feat, fix, docs, refactor, perf, test, chore.
• scope is optional and describes the part of the codebase affected (e.g., auth, ui, api).
• concise message is a short description of the change (max 50 chars).

📝 Change Type

Please select the type of change this PR introduces (choose one or more):

• feat: New feature.
• fix: Bug fix.
• docs: Documentation only changes.
• refactor: A code change that neither fixes a bug nor adds a feature.
• perf: Performance improvement.
• test: Adding missing tests or correcting existing tests.
• chore: Maintenance tasks (e.g., updating dependencies).

💡 Description

MLX rope now supports batch offset ml-explore/mlx#2564. Improve engine performance when handling batch.

Qwen/Qwen3-8B on M4 Max bs=16 per decode layer:
before: 2.5ms
after: 0.3ms

🔗 Related Issues

List any issues this PR closes or relates to:

• Closes #IssueNumber (e.g., Closes #123)

✅ Checklist

Please ensure the following points are addressed before merging:

• I have performed a self-review of my own code.
• I have added/updated tests that prove my fix or feature works (if applicable).
• I have updated the documentation (if necessary).
• My code follows the project's style guidelines.