float8 matmul benchmark: hook up cublas mxfp8 gemm

[vkuzo]

Summary:

Adds an option to benchmark the cuBLAS mxfp8 gemm in our float8 matmul
benchmarking script

Test Plan:

Reviewers:

Subscribers:

Tasks:

Tags:

[vkuzo]

Stack from ghstack (oldest at bottom):

• enable compile with mxfp8 and mxfp4 cutlass gemm #1838
• add mxfp8_cublas recipe to mx_formats #1831
• -> float8 matmul benchmark: hook up cublas mxfp8 gemm #1830

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/1830

• 📄 Preview Python docs built from this PR

Note: Links to docs will display an error until the docs builds have been completed.

This comment was automatically generated by Dr. CI and updates every 15 minutes.