[FA-qk-fp8] Add fp8 FA to 06-fused-attention-fwd-transV.py

[zhanglx13]

This PR adds the FA qkfp8 kernel, in which only the first gemm is done in fp8.

To make things simpler, it is assumed that the torch has native support for AMD fp8 data types.

And also remove ( ) in gemm thanks to fix in https://github.com/ROCmSoftwarePlatform/triton/pull/445