[digantdesai]

Stack from ghstack (oldest at bottom):

• [ET][native] Verify bundled LLM samples through the runner #24175
• -> [ET][native] Bundle LLM prefill and decode samples from export_hf_llm #24174
• [ET][native] Read bundled samples in C++ #24173
• [ET][native] Make the LLM runner's next-token choice pluggable #24172
• [ET][native] Bundle sample method calls in .ptn packages #24171

export_hf_llm --samples N adds a golden set to forward: per
prompt, a prefill and 4 decode calls, each decode fed the previous eager
argmax. Tolerance is (1e-3, 1e-3) for float and (2.0, 5e-2) for quantized
weights, where engines quantize activations differently from torchao.

Authored with Claude Code.

Differential Revision: D125544388

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/24174

• 📄 Preview Python docs built from this PR

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

✅ No Failures

As of commit 069da81 with merge base 4db778e ():
💚 Looks good so far! There are no failures yet. 💚

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.

[SS-JIA]

Review automatically exported from Phabricator review in Meta.