fix eval_llama_qnn custom annotation

[DannyYuyang-quic]

Summary

Fix eval_llama_qnn: retrieve custom annotation from quantization recipe

Test plan

python -m executorch.examples.qualcomm.oss_scripts.llama.eval_llama_qnn --decoder_model qwen2_5-0_5b --quant_linear_only --max_seq_length 1024 --ptq 16a4w

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/15953

• 📄 Preview Python docs built from this PR

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

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

[DannyYuyang-quic]

Hi @cccclai,

The previous PR #15807 moved all LLM quantization related configs into the quantization recipe.
As a result, custom_annotation was no longer accessible from the model config(LLMModelConfig), causing the unit test to fail.
https://github.com/pytorch/executorch/actions/runs/19558624238/job/56006215617#step:16:17963

This fix updates eval_llama_qnn.py to retrieve custom_annotation from the quantization recipe instead.

Please have a look, thanks!

[DannyYuyang-quic]

@pytorchbot label "release notes: qualcomm"

[cccclai]

lint is failing, can you fix it?

[DannyYuyang-quic]

lint is failing, can you fix it?

Done, thanks!

[cccclai]

Thank you