Update AITER CK dependency for gfx1250 grouped GEMM

[aris134]

Description

Updates the bundled AITER CK dependency required to build and run the gfx1250 CK backend in TE.

Fetched changes include:

• grouped GEMM quant mixed-precision fix
• MXFP8 grouped GEMM support using the TDM pipeline on gfx1250

This PR updates the AITER submodule pointer only; no direct TE kernel logic changes are introduced.

Fixes # (issue)

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:

• Change A
• Change B

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

[ipanfilo]

Is this version of AITER support building with gfx1250 for MHA?

[aris134]

Is this version of AITER support building with gfx1250 for MHA?

I have not validated gfx1250 MHA support with this AITER version. This update was specifically to pull in the CK changes required for the gfx1250 CK grouped GEMM / MXFP8 grouped GEMM path in TE.