Arm backend: Disable relu-fusing for sym. quant

[oscarandersson8218]

Adds new checks to quantization annotation to not fuse conv+relu patterns when output_qspec is symmetric. Symmetric quantization would force the zero-point to be 0, and in order for us to fuse relu the zero-point must equal qmin. Also adds new tests to verify that it works.

cc @freddan80 @per @zingo @digantdesai

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/16286

• 📄 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, 1 Unrelated Failure

As of commit d6b4cd5 with merge base cf8496a ():

NEW FAILURES - The following jobs have failed:

• Build documentation / build (buck2) / Build doc (gh)
  Process completed with exit code 1.
• pull / test-openvino-linux / linux-job (gh)
  RuntimeError: Command docker exec -t 43bbc5d5e1277e90068830538a11a1590581ef6215c1162e9b8fca4d3a2dcd32 /exec failed with exit code 1

UNSTABLE - The following job is marked as unstable, possibly due to flakiness on trunk:

• pull / android / run-emulator (gh) (#16137)
  Timeout waiting for emulator to boot.

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

[zingo]

Got fail, retrigger failed test job to see if it's random

FAILED backends/arm/test/ops/test_sub.py::test_sub_tensor_tosa_INT_alpha[rand_4D_pi] - AssertionError: Output 0 does not match reference output.
Given atol: 0.001, rtol: 0.001.
Output tensor shape: torch.Size([1, 10, 20, 30]), dtype: torch.float32
Difference: max: 0.24429035186767578, abs: 0.24429035186767578, mean abs error: 4.071505864461263e-05.
-- Model vs. Reference --
Numel: 6000, 6000
Median: 0.0, 0.0
Mean: 0.06314905179540316, 0.06310833673675854
Max: 32.00203323364258, 32.00203323364258
Min: -30.292001724243164, -30.292001724243164

[zingo]

it worked, other fails are unrelated