[CPU] Fix AWQ on CPU after refactoring

[Xia-Weiwen]

Fix the CPU path of AWQ after the refactoring of AWQ implementation by #2400

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/2688

• 📄 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 8e94408 with merge base 7dbc816 ():

NEW FAILURES - The following jobs have failed:

• Run Regression Tests / test (CPU 2.5.1, linux.4xlarge, torch==2.5.1 --index-url https://download.pytorch.org/whl/cpu, cp... / linux-job (gh)
  test/prototype/test_awq.py::TestAWQ::test_awq_loading_vllm_0_cpu
• Run Regression Tests / test (CUDA 2.5.1, linux.g5.12xlarge.nvidia.gpu, torch==2.5.1 --index-url https://download.pytorch... / linux-job (gh)
  test/prototype/test_awq.py::TestAWQ::test_awq_loading_vllm_0_cpu

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

[Xia-Weiwen]

@pytorchbot label "not user facing"

[pytorch-bot]

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

[Xia-Weiwen]

@pytorchbot label "topic: not user facing"

[Xia-Weiwen]

Hi @jerryzh168 Could you please review this PR? Thanks.

[jerryzh168]

we have some planned changes for AWQ actually, which might require refactoring the CPU path, I'll put up soon

[jerryzh168]

@Xia-Weiwen can you work on splitting out Int4CPUAQTTensorImpl from AffineQuantizedTensor and have a separate Int4SomePackingFormatTensor following the implementation in #2687

or you can wait a bit for a dev guide that we'll have as well, hopefully will come out in 2 weeks

[Xia-Weiwen]

@jerryzh168 Thanks for the info. Sure, I can wait until your new design is ready.