Add a16w8 per-op test for bmm

[christine-long-meta]

Summary:
Add int16 activation / int8 weight (a16w8) quantization tests for aten.bmm on Ethos-U55 and Ethos-U85.

Context

Batch matrix multiply (bmm) implements the core Q @ K^T and attn_weights @ V operations in the multi-head attention of the EMG2Pose Conformer. At int16 IO precision the accumulator width and rescale path differ between U55 and U85, so dedicated per-op coverage is needed to catch numerics divergence before it surfaces as an end-to-end SNR regression. The test matrix includes square, rectangular, and large-batch configurations to exercise different tiling strategies in the Vela backend.

Also removes unused aten_op_mm / exir_op_mm variables that were dead code in test_bmm.py.

Changes

• Add a16w8_bmm_test_parameters dict with 5 test configurations covering same-shape, different-shape, rectangular, batch-10, and negative-value tensors
• Add test_bmm_a16w8_u55_INT using EthosU55PipelineINT with a16w8_quantization=True, symmetric_io_quantization=True, qtol=128, epsilon=2**-16
• Add test_bmm_a16w8_u85_INT using EthosU85PipelineINT with same kwargs
• Remove unused aten_op_mm and exir_op_mm variables
• Register ops/test_bmm.py in fbcode/ and xplat/ targets.bzl

bypass-pytorch-oss-checks

Reviewed By: Ninja91

Differential Revision: D104532363

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/19599

• 📄 Preview Python docs built from this PR

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

❗ 2 Active SEVs

There are 2 currently active SEVs. If your PR is affected, please view them below:

• Run pull request jobs on OSDC runners in shadow mode
• Rollout OSDC prod cluster in us-west-1

⏳ No Failures, 269 Pending

As of commit 1c06ec5 with merge base 41a38d8 ():
💚 Looks good so far! There are no failures yet. 💚

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

[pytorch-bot]

Workflows were awaiting approval. CI has now been triggered for the ciflow labels on this PR.

[github-actions]

This PR needs a release notes: label

If your change should be included in the release notes (i.e. would users of this library care about this change?), please use a label starting with release notes:. This helps us keep track and include your important work in the next release notes.

To add a label, you can comment to pytorchbot, for example
@pytorchbot label "release notes: none"

For more information, see
https://github.com/pytorch/pytorch/wiki/PyTorch-AutoLabel-Bot#why-categorize-for-release-notes-and-how-does-it-work.

[meta-codesync]

@christine-long-meta has exported this pull request. If you are a Meta employee, you can view the originating Diff in D104532363.

[meta-codesync]

@christine-long-meta has exported this pull request. If you are a Meta employee, you can view the originating Diff in D104532363.

[zingo]

You seem to got a strange error in Yest ARM Backend, It seems very unrelated, I rerun the tests maybe it was a network glitch and will go away.

[zingo]

The test re-run passed, approving :) Thanks!