Add 16a4w_block QAT config

[sxu]

Summary: Introduce a FakeQuantizer subclass. It falls back to LPBQ observer's convert. _derived_bias_quant_spec also looks for it to correctly derive bias scale.

Open to suggestions on how to test. Naveen launched a QAT run and it seems to produce reasonable results.

Differential Revision: D87194388

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/15878

• 📄 Preview Python docs built from this PR

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

❌ 3 New Failures, 2 Unrelated Failures

As of commit 0a8fd5c with merge base b4d72f1 ():

NEW FAILURES - The following jobs have failed:

• Lint / lintrunner / linux-job (gh)
  >>> Lint for backends/qualcomm/tests/test_qnn_delegate.py:
• pull / test-llama-runner-qnn-linux (fp32, qnn_16a16w, qnn) / linux-job (gh)
  RuntimeError: Command docker exec -t 49c760a0e4ec9f05d0b6d834dd883a29d1ab9c9f28b19d5ff7c23805eaff6473 /exec failed with exit code 92
• pull / test-models-linux (w2l, portable, linux.4xlarge.memory) / linux-job (gh)
  RuntimeError: Command docker exec -t 68b431304cd05ad0870fcc6478bb3bee28f5f8b69cd944da0bd22b779cd2d43a /exec failed with exit code 1

FLAKY - The following job failed but was likely due to flakiness present on trunk:

• pull / unittest-editable / linux / linux-job (gh) (similar failure)
  exir/backend/test/test_lowered_backend_module.py::TestBackendAPI::test_emit_nested_lowered_backend_module

BROKEN TRUNK - The following job failed but was present on the merge base:

👉 Rebase onto the `viable/strict` branch to avoid these failures

• pull / unittest / linux / linux-job (gh) (trunk failure)
  exir/backend/test/test_lowered_backend_module.py::TestBackendAPI::test_emit_nested_lowered_backend_module

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

[meta-codesync]

@sxu has exported this pull request. If you are a Meta employee, you can view the originating Diff in D87194388.

[billmguo]

@winskuo-quic can you review and approve this diff?

[haowhsu-quic]

Would it be simpler if calling torchao.quantization.quant_primitives._fake_quantize_affine directly?

[DannyYuyang-quic]

I think for QAT testing we can use pseudo labels generated by the FP32 model, do a few mini training steps on the fake-quant model, and then compare outputs against the FP32 baseline (pseudo labels) within acceptable atol/rtol thresholds as usual.