Fix error in Blackwell document of referring to Mxf4 format as NVF4

[zianglih]

Fixed the error of referring to Mxf4 format as NVF4.

[CalebDu]

Hello @zianglih, Thank you for the PR.

2. [NVF4 Gemm with block scaling and NVF4 output matrix](https://github.com/NVIDIA/cutlass/tree/main/examples/72_blackwell_narrow_precision_gemm/72b_blackwell_nvfp4_nvfp4_gemm.cu)

This NVF4 output is not typo. NVF4 can be with e8m0 or e4me SF, but restricted with vector_size=16. Please update this line.

[zianglih]

Hi @CalebDu , thanks for the correction. Now I see the OutputSFVectorSize is 16:

cutlass/examples/72_blackwell_narrow_precision_gemm/72b_blackwell_nvfp4_nvfp4_gemm.cu

Line 126 in 8dbce01

constexpr int OutputSFVectorSize = InputSFVectorSize;

I have reverted the line change.