[ExecuTorch][llm] Add quantized_moe_ffn custom op with C++ kernel

[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 a fused quantized_moe_ffn custom op for MoE feed-forward with INT4/INT8 weight quantization via torchao.

The C++ runtime kernel implements router GEMM, scoring, top-k, counting-sort permutation, per-expert grouped GEMMs, SwiGLU, and weighted scatter-add unpermute. On aarch64, expert GEMMs use torchao::linear_operator from D112958457; otherwise a portable reference path unpacks the torchao blob, dequantizes to fp32, and calls cpublas::gemm.

The AOT shim registers the schema, provides CompositeExplicitAutograd dispatch, and exposes a _quantized_moe_ffn_active sentinel op. Build integration covers Buck and CMake.

Differential Revision: D102382000

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/21119

• 📄 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

✅ You can merge normally! (2 Unrelated Failures)

As of commit f700b8a with merge base 21554e5 ():

FLAKY - The following jobs failed but were likely due to flakiness present on trunk:

• pull / test-arm-backend-no-driver (test_pytest_models_tosa) / linux-job (gh) (matched linux rule in flaky-rules.json)
  The runner has received a shutdown signal. This can happen when the runner service is stopped, or a manually started runner is canceled.
• pull / test-qnn-testsuite-linux / test-backend-linux (qnn, models) / linux-job (gh) (detected as infra flaky with no log or failing log classifier)

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.