[Common] Optimize KV cache related kernels

[cyanguwa]

Description

This PR improves the runtime performance of the reindex_kv_cache and copy_to_kv_cache kernels.

Example problem size: b=64, max_s=1024, current_s=128, new_s=8, h=12, d=256, on Hopper
Before: reindex: 4.8ms, copy: 1.3ms
After: reindex: 46us, copy: 13us

Type of change

• Documentation change (change only to the documentation, either a fix or a new content)
• 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)
• Infra/Build change
• Code refactoring

Changes

Please list the changes introduced in this PR:

• Optimize reindex and copy kernels in KV caching

Checklist:

• I have read and followed the contributing guidelines
• The functionality is complete
• I have commented my code, particularly in hard-to-understand areas
• I have made corresponding changes to the documentation
• My changes generate no new warnings
• I have added tests that prove my fix is effective or that my feature works
• New and existing unit tests pass locally with my changes

[cyanguwa]

/te-ci pytorch L0