DISABLED test_main_loop_scaling_shape0_use_fast_accum_False_scaling_block_sizes0_cuda (__main__.TestFP8LoweringCUDA)

This test fails consistently on CUDA (seen on `Limited CI on H100 / linux-jammy-cuda13.0-py3.10-gcc11-sm90 / test-osdc (smoke, 1, 1, mt-l-x86iamx-22-225-h100)`) with:

```
ValueError: scale_b must have shape N x ceil_div(K,128) Float elements, got [transposed]
```

Root cause: for `w = BlockWise1x128` recipes, the test builds `scale_b` (w's inverse scale) in `[K/128, N]` layout, but eager `torch._scaled_mm_v2` requires `[N, K/128]`. This is a pre-existing test/kernel scale-layout mismatch; CI only began exercising it on 2026-06-29.

Repro:
```
python test/inductor/test_fp8.py TestFP8LoweringCUDA.test_main_loop_scaling_shape0_use_fast_accum_False_scaling_block_sizes0_cuda
```

One of ~14 failing `test_main_loop_scaling` parametrizations (`w = BlockWise1x128` recipes). See also #188675, #188704.

cc @ptrblck @msaroufim @eqy @tinglvv @nWEIdia

Start with test/inductor/test_fp8.py and run the reported TestFP8LoweringCUDA.test_main_loop_scaling_shape0_use_fast_accum_False_scaling_block_sizes0_cuda reproduction. Inspect the BlockWise1x128 scale_b construction alongside the eager torch._scaled_mm_v2 shape requirement, then verify the affected test and related test_main_loop_scaling parametrizations pass on CUDA.

Written by the indexing model from the issue text.