Fix amd_ck_fp8.hpp macro definitions

[xli]

Proposed changes

1. Remove CK_USE_FNUZ_FP8 and CK_USE_OCP_FP8 definitions, they are default behavior of preprocessor before compilation. Undefined macro is replaced with 0 when used in #if. In rocm 6.4, there is include/ck/config.h header file defines both CK_USE_FNUZ_FP8 and CK_USE_OCP_FP8 as ON, the current definition inside amd_ck_fp8.hpp will cause macro-redefined error.
2. Prefix __assert_fnuz_support and __assert_ocp_support with namespace fp8_impl to avoid redefined error when building with rocm 6.4 (include/hip/amd_detail/amd_hip_fp8.h)

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

[andriy-ca]

@xli , do you have a reproducer for the issue?

The originally proposed changes did not pass our CI. Could you verify the latest commit? 92fcbea

[xli]

@xli , do you have a reproducer for the issue?

The originally proposed changes did not pass our CI. Could you verify the latest commit? 92fcbea

this works for me.

[xli]

@andriy-ca what is broken now?