Use out_dtype instead of element_size for microscaling condition

[wdziurdz]

New contributor declaration

• I am not making a trivial change, such as fixing a typo in a comment.

• I have written a PR description following these
  rules.

• I have run pre-commit run --from-ref origin/main --to-ref HEAD.

• Select one of the following.

  • I have added tests.
    • /test for lit tests
    • /unittest for C++ tests
    • /python/test for end-to-end tests
  • This PR does not need a test because FILL THIS IN.

• Select one of the following.

  • I have not added any lit tests.
  • The lit tests I have added follow these best practices,
    including the "tests should be minimal" section. (Usually running Python code
    and using the instructions it generates is not minimal.)

PR Description
Fix microscaling condition for split_k > 1 (use out_dtype instead of element_size)
Issue: #8518

[lezcano]

Can you add a test?

[wdziurdz]

Can you add a test?

But these tests already exist in the repo. You probably skipped them.

triton/python/triton_kernels/tests/test_matmul.py

Lines 269 to 271 in 4d85824

	Case(1000, 704, 800, "ragged", "mxfloat8_e4m3fn", "mxfloat4_e2m1", 8, 2, split_k=9),
	Case(1000, 704, 800, "ragged", "mxfloat8_e4m3fn", "mxfloat4_e2m1", 8, 2, split_k=9, hbm_swizzling=True),
	Case(1000, 704, 800, "ragged", "mxfloat8_e4m3fn", "mxfloat4_e2m1", 8, 2, split_k=9, colmajor_mxfp_weight=False),

[lezcano]

can you check where are these tests skipped and can you unskip them if so?