[ExecuTorch][llm] Add source-transform and Meta-kernel tests for MoE op

[digantdesai]

Stack from ghstack (oldest at bottom):

• [ExecuTorch][llm] Wire --use_moe_quantized_op through export pipeline and LLM config #21126
• [ExecuTorch][llm] Add MoE quantized custom op documentation #21125
• [ExecuTorch][llm] Fuse w1+w3 into single GEMM in quantized_moe_ffn #21124
• [ExecuTorch][llm] Add numerical kernel tests for quantized_moe_ffn #21123
• -> [ExecuTorch][llm] Add source-transform and Meta-kernel tests for MoE op #21122
• [ExecuTorch][llm] Add MoE source transformation with INT4 quantized packing #21121
• [ExecuTorch][llm] Add Meta kernel and registration probe for quantized_moe_ffn #21120
• [ExecuTorch][llm] Add quantized_moe_ffn custom op with C++ kernel #21119

Add test_quantized_moe.py coverage for source transformation, INT4 packing, Meta-kernel validation, kernel registration, and shared-expert behavior.

Exercise the production torchao gate quantization recipe and assert that the transformed module exports a llama.quantized_moe_ffn call with an fp32 gate buffer.

Differential Revision: D102381997

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/21122

• 📄 Preview Python docs built from this PR

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

❗ 1 Active SEVs

There are 1 currently active SEVs. If your PR is affected, please view them below:

• Unrelated MacOS MPS test jobs time out (30 min) due to stale cpp_extension lock file poisoning self-hosted runners

❌ 4 New Failures, 1 Unrelated Failure

As of commit 45e1787 with merge base 21554e5 ():

NEW FAILURES - The following jobs have failed:

• pull / unittest / linux / linux-job (gh)
  extension/llm/custom_ops/test_quantized_moe.py::TestMetaKernelValidation::test_rejects_mismatched_packed_w1_w3_sizes
• pull / unittest / macos / macos-job (gh)
  extension/llm/custom_ops/test_quantized_moe.py::TestSourceTransform::test_buffers_stay_fp32_after_to_bfloat16
• pull / unittest-editable / linux / linux-job (gh)
  extension/llm/custom_ops/test_quantized_moe.py::TestSourceTransform::test_no_expert_bias_produces_empty_buffer
• pull / unittest-editable / macos / macos-job (gh)
  extension/llm/custom_ops/test_quantized_moe.py::TestSourceTransform::test_forward_output_dtype_matches_input

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

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

• pull / test-arm-backend-no-driver (test_pytest_models_tosa) / linux-job (gh) (trunk failure)

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

[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.