Support biased SwiGLU in MXFP4 MoE

[XiaobingSuper]

Add bias-aware SwiGLU handling to the MXFP4 MoE gridwise paths and keep split-k epilogues from accumulating stale data when k_batch is one.

Proposed changes

• Add bias support to MXFP4 MoE BNS/BPreShuffle device and gridwise paths.
• Add swiglustep_and_mul handling for MXFP4 MoE with GPT-OSS style SwiGLU clamp/alpha behavior.
• Fix CK-Tile MoE GEMM1 split-k epilogue behavior so k_batch == 1 stores instead of accumulating stale output.

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

If this is a relatively large or complex change, feel free to start a discussion by explaining why you chose the solution you did and what alternatives you considered