[ez][release blocker fix] Insert linalg_vector_norm into decomp table used for Edge export

[pytorchbot]

Summary:

Context

Addresses this release blocker issue. Some models cannot export because they use linalg_vector_norm which is not currently an ATen operator.

I initially tried adding the op to the core decomp table, but the decomp is not passing pytorch correctness tests. Please see pytorch/pytorch#150241 for more details.

Changes

Since we currently cannot include the op in PyTorch's decomp table, instead we can insert the op into the edge decomp table directly.

This PR is a simple change to add linalg_vector_norm directly to the edge decomp table.

Test Plan:
Tested exporting and running a model with the linalg_vector_norm op via the following script.

import torch
from executorch.exir import to_edge_transform_and_lower, EdgeCompileConfig
from torch.export import Dim, export

from executorch.extension.pybindings.portable_lib import (  # @manual
    _load_for_executorch_from_buffer,
)

class Model(torch.nn.Module):
    def __init__(self):
        super().__init__()

    def forward(self, x):
        return torch.linalg.vector_norm(x, 2)

model = Model()
inputs = (torch.randn(1,1,16,16),)
dynamic_shapes = {
    "x": {
        2: Dim("h", min=16, max=1024),
        3: Dim("w", min=16, max=1024),
    }
}

exported_program = export(model, inputs, dynamic_shapes=dynamic_shapes)
executorch_program = to_edge_transform_and_lower(
    exported_program,
    compile_config=EdgeCompileConfig(_check_ir_validity=False),
).to_executorch()


executorch_module = _load_for_executorch_from_buffer(
    executorch_program.buffer
)

model_output = executorch_module.run_method(
    "forward", tuple(inputs)
)

print(model_output)

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/9999

• 📄 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

As of commit 151d6da with merge base 771588a ():

NEW FAILURES - The following jobs have failed:

• pull / unittest-arm / linux-job (gh)
  RuntimeError: Command docker exec -t c36867ad9b7403b2aaf272e19368dbdb645dd0ee6e35bda49de5fe91392af66c /exec failed with exit code 1
• trunk / test-arm-reference-delegation / linux-job (gh)
  RuntimeError: Command docker exec -t e466c2734c0065dc0e8ea036ac8ab99865ce954a1f21560d2d4ecfeabc1feac4 /exec failed with exit code 1
• trunk / unittest-release / linux / linux-job (gh)
  backends/xnnpack/test/ops/test_multiply.py::TestMul::test_qs8_mul_relu

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

[metascroy]

@SS-JIA can you have a look at the failing test?

[SS-JIA]

Failure is legit. Will have to revert original PR and reland.

[SS-JIA]

@metascroy I ended up adding expected failures the failing tests on main with #10043, see the PR for more analysis.

Lmk how you want to proceed. We can land the two cherry picks separately, or I can manually create a cherry pick with both changes.

[SS-JIA]

To clarify, this change only causes one of the failures:

• pull / unittest-arm / linux-job (pull_request)

The other two seems to be transient (failed correctness tests that exceed error tolerance) and are most ilkely not related to my change:

• `trunk / unittest-release / linux / linux-job (push)
• trunk / test-arm-reference-delegation / linux-job (push)