Enable group mode (varlen) kernel generation for PyTorch integration

[chinmaydk99]

Proposed changes

This PR enables group mode (variable-length attention) kernel generation for PyTorch's CK SDPA backend.

Checklist

Please put an x into the boxes that apply. You can also fill these out after creating the PR. If you're not sure, please don't hesitate to ask.

• I have added tests relevant to the introduced functionality, and the unit tests are passing locally
• I have added the test to REGRESSION_TESTS list defined at the top of CMakeLists.txt in tests/CMakeLists.txt, IF the test takes more than 30 seconds to run.
• I have added inline documentation which enables the maintainers with understanding the motivation
• I have removed the stale documentation which is no longer relevant after this pull request
• (If this change is user-facing) I have added release notes which provide the end users with a brief summary of the improvement from this pull request
• I have run clang-format on all changed files
• Any dependent changes have been merged

Discussion

The change is minimal (single line deletion) but enables a significant feature: variable-length attention support for ROCm users via PyTorch's torch.nn.attention.varlen API.

[poyenc]

May I know why the group-mode kernels were not included previously, and why they are required now?

[chinmaydk99]

May I know why the group-mode kernels were not included previously, and why they are required now?

This is part of the ongoing parity effort to bridge feature gaps between CK and AOTriton backends in PyTorch. Varlen attention is one of the features being enabled

[pruthvistony]

@illsilin @poyenc ,
Please help on review on this PR.

[ammallya]

Imported to ROCm/rocm-libraries