[ExecuTorch][llm] Add MoE source transformation with INT4 quantized packing

[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 moe.py with a QuantizedMoEFFN module wrapping llama::quantized_moe_ffn, INT4 symmetric group quantization, torchao packing, and recursive module replacement. Preserve fp32 buffers and output dtype across model casts.

Dequantize a torchao-quantized gate into the custom op fp32 buffer so QAT models can be captured by torch.export without tensor-subclass dispatch failures.

Differential Revision: D102381994

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/21121

• 📄 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 11b27ac with merge base bfed808 ():

NEW FAILURES - The following jobs have failed:

• Build Presets / apple (ios-simulator) / build (gh)
  Can't find 'action.yml', 'action.yaml' or 'Dockerfile' under '/Users/runner/work/executorch/executorch/test-infra/.github/actions/check-disk-space'. Did you forget to run actions/checkout before running your local action?
• Build Presets / apple (llm) / build (gh)
  Can't find 'action.yml', 'action.yaml' or 'Dockerfile' under '/Users/runner/work/executorch/executorch/test-infra/.github/actions/check-disk-space'. Did you forget to run actions/checkout before running your local action?
• Build Presets / apple (macos) / build (gh)
• pull / unittest-buck / macos / macos-job (gh)
  RuntimeError: Command bash /Users/ec2-user/runner/_work/_temp/exec_script failed with exit code 3

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

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

• pull / unittest-buck / linux / 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.