[Inductor][float8] Support qlinear for float8 in inductor

[shiyang-weng]

For float8_e4m3fn, support

register_qlinear_weight_prepack
_register_qlinear_unary_fusion
_register_qlinear_binary_fusion
quant_lift_up

on inductor.

For FP8, there are following issues

1. q/dq switch to use quantize_affine_float8/dequantize_affine_float8
2. The q/dq API change. The fp8 q/dq requires type(scale) is tensor.
3. pt2e not support float8.

Based on these issues,

1. Need to handle fp8 q/dq pattern separately.
2. Handle scale separately.
3. We implement the function(fp8_convert_), which can add q/dq before the linear in the model. We add the function to test/quantization/pt2e/test_x86inductor_fusion.py

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/2565

• 📄 Preview Python docs built from this PR

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

❌ 2 New Failures

As of commit 38de0e9 with merge base 11ce634 ():

NEW FAILURES - The following jobs have failed:

• Run Regression Tests / test-nightly (CPU Nightly, linux.4xlarge, --pre torch --index-url https://download.pytorch.org/wh... / linux-job (gh)
  test/quantization/pt2e/test_x86inductor_fusion.py::TestPatternMatcher::test_fp8_qlinear_relu_mixed_bf16_input_dim_exceeds_2
• Run Regression Tests / test-nightly (CUDA Nightly, linux.g5.12xlarge.nvidia.gpu, --pre torch --index-url https://downloa... / linux-job (gh)
  test/quantization/pt2e/test_x86inductor_fusion.py::TestPatternMatcher::test_fp8_qlinear_add_cpu_use_relu_True_mixed_bf16_True

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

[Xia-Weiwen]

Thanks for the PR!

[Xia-Weiwen]

LGTM

[pytorch-bot]

Didn't find following labels among repository labels: topic:,not,user,facing

[shiyang-weng]

@pytorchbot label "topic: not user facing"