Support multimethod in runner

[lucylq]

Stack from ghstack (oldest at bottom):

• [wip] Support multimethod in export_llama_lib #17231
• [wip] Introduce MultimethodLoraConfig #17230
• Introduce LoraConfig #17229
• -> Support multimethod in runner #17228

Specify which method to call in the runner.

Update CLAUDE.md for fbcode/xplat.

Differential Revision: D92225533

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/17228

• 📄 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, 2 Unrelated Failures

As of commit e21341c with merge base eac0673 ():

NEW FAILURES - The following jobs have failed:

• Lint / lintrunner / linux-job (gh)
• pull / unittest / macos / macos-job (gh)
  examples/models/test/test_export.py::ExportTest::test_mv3_export_to_executorch
• Test CUDA Builds / export-model-cuda-artifact (openai, whisper-small, non-quantized) / linux-job (gh)
  RuntimeError: Command docker exec -t efb3ea03b556f62d1f2ddfb67885bf04fb10aec52e3aa529ec344ba780f93ded /exec failed with exit code 1

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

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

• pull / test-samsung-models-linux / linux-job (gh) (trunk failure)
  ##[error]The operation was canceled.
• pull / test-samsung-quantmodels-linux / linux-job (gh) (trunk failure)
  ##[error]The operation was canceled.

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.

[Copilot]

Pull request overview

This PR adds multimethod support to the LLM runner infrastructure, allowing users to specify which method to execute in the model instead of hardcoding "forward". This is part of a larger stack implementing multimethod and LoRA support.

Changes:

• Added method_name parameter to TextDecoderRunner and related factory functions, with "forward" as the default
• Updated all runner code to use the configurable method name instead of hardcoded "forward"
• Added command-line flag --method_name to the llama example
• Included minor documentation updates to CLAUDE.md about fbcode/xplat conventions

Reviewed changes

Copilot reviewed 9 out of 9 changed files in this pull request and generated no comments.

Show a summary per file

File	Description
extension/llm/runner/text_decoder_runner.h	Added method_name constructor parameter, member variable, and getter method
extension/llm/runner/text_decoder_runner.cpp	Updated constructor and step() to use configurable method_name; fixed typo in error message
extension/llm/runner/test/test_text_decoder_runner.cpp	Added tests for default and custom method names
extension/llm/runner/llm_runner_helper.h	Added method_name parameter to create_text_llm_runner function signatures
extension/llm/runner/llm_runner_helper.cpp	Propagated method_name through factory functions; added logging for method name
examples/models/llama/runner/runner.h	Added method_name parameter to create_llama_runner functions
examples/models/llama/runner/runner.cpp	Propagated method_name through create_llama_runner implementations
examples/models/llama/main.cpp	Added --method_name command-line flag
CLAUDE.md	Added documentation about fbcode/xplat directory structure; minor formatting fixes

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.