Run Hugging Face models via Optimum on CI

[guangy10]

Summary

Export and run native Hugging Face models via optimum-executorch.

Cross-repo integration tests to ensure compatibility (optimum-executorch@main -> executorch@main), to minimize the chance of getting issue like huggingface/optimum-executorch#14 in future releases.

The recipe script is no longer needed as those models will just works via Hugging Face optimum library

Test plan

CI

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/8630

• 📄 Preview Python docs built from this PR

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

❌ 1 New Failure

As of commit 90ebf46 with merge base ad4675a ():

NEW FAILURE - The following job has failed:

• pull / test-llava-runner-linux / linux-job (gh)
  RuntimeError: Command docker exec -t f3a498f45fd12b91cad048e4b8d1b57c86f8af7a123e8bcc36ec06843e62e0d4 /exec failed with exit code 139

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

[guangy10]

The llava failure is irrelevant to this PR. All HF models passed on CI

[mergennachin]

Nice!!

Can you talk about optimum-executorch during the team meeting on Monday? There's some time for demo