[Inductor] Support scaled mm on inductor

[shiyang-weng]

Blocked by #2379

Fuse following pattern to scaled_mm

    #   + - - - - | - - - - - -  | - - - -  +
    #   |    dq_per_tensor  dq_per_tensor   |
    #   |         |              |          |
    #   |    OPT(to_bf16)    OPT(to_bf16)   |
    #   |         |             |           |
    #   |    OPT(reshape)     permute       |
    #   |          \           /            |
    #   |             addmm/mm              |
    #   |                |                  |
    #   |      OPT(quant_per_tensor)        |
    #   |                |                  |
    #   |          OPT(reshape)             |

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/2411

• 📄 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.

[jerryzh168]

I believe this is the training float8 test file, float8 inference is using https://github.com/pytorch/ao/blob/main/test/dtypes/test_affine_quantized_float.py

[shiyang-weng]

I believe this is the training float8 test file, float8 inference is using https://github.com/pytorch/ao/blob/main/test/dtypes/test_affine_quantized_float.py

Ok. I change the ut path on last pr #2379