Qualcomm AI Engine Direct - BC CI Fix and Custom Annotation Fix

[winskuo-quic]

Summary

• This PR will fix BC CI to use the right tokenizer, initially 260k accidently use 110m tokenizer during runtime.
• Fix custom annotation where conv has bias node.

Test plan

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/13212

• 📄 Preview Python docs built from this PR

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

❌ 2 New Failures, 1 Unrelated Failure

As of commit c2e3ba5 with merge base be221c6 ():

NEW FAILURES - The following jobs have failed:

• Build documentation / build (buck2) / Build doc (gh)
  At least one of the pre-conditions you specified did not hold
• pull / test-moshi-linux / linux-job (gh)
  RuntimeError: Command docker exec -t 15afba60400efe4626244a3d5409528e214ebd9d2bdd3166e14f1fa5aa41818f /exec failed with exit code 1

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

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

• pull / test-openvino-linux / linux-job (gh) (trunk failure)
  AttributeError: '_OpNamespace' 'quantized_decomposed' object has no attribute 'convert_element_type'

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.

[winskuo-quic]

Hi @cccclai,

1. We notice currently there are a couple of Qualcomm PRs failing in BC CI. This fix is cherry-picked from Qualcomm AI Engine Direct - Static Decoder Runner Support 16bit KV IO #13127. Please take your time reviewing Qualcomm AI Engine Direct - Static Decoder Runner Support 16bit KV IO #13127. However, we might need this PR go in first so we can unblock other PRs that is also failing this CI. Thanks!
2. Recently, conv_former CI is added. I made a small change to the CI since we won't be able to have access to dataset on CI machines. I have aligned the behavior of conv_former with other models, which is to use dummy input. Please have a look. Thanks

Hi @rohansjoshi,
This PR should fix the custom annotation issue you encountered when conv has bias node. Please have a look. Thanks