[wip] speed up nvfp4 triton kernel

[vkuzo]

Summary:

Test Plan:

pytest test/prototype/mx_formats/test_nvfp4_tensor.py -s -x -k test_triton_nvfp4_quantize_equivalence

Reviewers:

Subscribers:

Tasks:

Tags:

[vkuzo]

Stack from ghstack (oldest at bottom):

• -> [wip] speed up nvfp4 triton kernel #3202

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/3202

• 📄 Preview Python docs built from this PR

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

❌ 1 New Failure, 1 Unrelated Failure

As of commit cc3f03f with merge base 2d8a4c1 ():

NEW FAILURE - The following job has failed:

• PR Label Check / Check PR Labels (gh)
  Process completed with exit code 1.

BROKEN TRUNK - The following job failed but were present on the merge base:

👉 Rebase onto the `viable/strict` branch to avoid these failures

• Run Regression Tests / test-nightly (CUDA Nightly, linux.g5.12xlarge.nvidia.gpu, --pre torch --index-url https://downloa... / linux-job (gh) (trunk failure)
  test/dtypes/test_nf4.py::TestComm::test_comm

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