Fix bug in add op to ignore alpha != 1 (fixes: #11683)

[abhinaykukkadapu]

Summary

Add node of XNNPack backend doesn't consider alpha value, this fixes the bug by falling back to portable ops and avoid partitioning the node.

(fixes: #11683)

Test plan

python -m unittest backends/xnnpack/test/ops/test_add.py

----------------------------------------------------------------------
Ran 11 tests in 26.689s

OK

import torch
from executorch.backends.xnnpack.partition.xnnpack_partitioner import XnnpackPartitioner
from executorch.exir import to_edge_transform_and_lower
from executorch.extension.pybindings.portable_lib import _load_for_executorch_from_buffer

class Model(torch.nn.Module):
    def forward(self, x, y):
        return torch.add(x, y, alpha=10)

inputs = (
    torch.randn(10),
    torch.randn(10),
)
model = Model()

ep = torch.export.export(model, inputs)
lowered = to_edge_transform_and_lower(
    ep,
    partitioner=[XnnpackPartitioner()],
).to_executorch()

et_model = _load_for_executorch_from_buffer(lowered.buffer)

eager_output = model(*inputs)
et_output = et_model([*inputs])[0]

tolerance=1e-5
if torch.allclose(eager_output, et_output, atol=tolerance):
    print("Outputs are within the tolerance level.")
else:
    print("Outputs differ beyond the tolerance level.")

Output of above run (tolerance = 1e-5)

Outputs are within the tolerance level.

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/11777

• 📄 Preview Python docs built from this PR

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

✅ You can merge normally! (3 Unrelated Failures)

As of commit 6e12599 with merge base f072e64 ():

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

• pull / test-llama-runner-linux (fp32, xnnpack+quantize_kv, linux.2xlarge, executorch-ubuntu-22.04-clang12) / linux-job (gh) (detected as infra flaky with no log or failing log classifier)

BROKEN TRUNK - The following jobs 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)
  examples/models/llama/tests/test_ring_attention.py::TestRingAttention::test_sliding_window_attention_custom
• pull / unittest-editable / linux / linux-job (gh) (trunk failure)
  examples/models/llama/tests/test_ring_attention.py::TestRingAttention::test_sliding_window_attention_custom

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

[GregoryComer]

Thanks for taking this. Looks good.

[facebook-github-bot]

@abhinaykukkadapu has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator.

[facebook-github-bot]

@abhinaykukkadapu has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator.

[facebook-github-bot]

@abhinaykukkadapu has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator.

[facebook-github-bot]

@abhinaykukkadapu has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator.