feat: support 1d ITensor offsets for embedding_bag converter

[zewenli98]

Description

Support 1d ITensor offsets for embedding_bag converter.
Note that this is only for 1d inputs.

There's a bug that same offsets with different types (tensor or ITensor) when include_last_offset=True will give different results. I doubt this is a bug from PyTorch, I'm still investigating it.

Fixes #2345

Type of change

• New feature (non-breaking change which adds functionality)

Checklist:

• My code follows the style guidelines of this project (You can use the linters)
• I have performed a self-review of my own code
• I have commented my code, particularly in hard-to-understand areas and hacks
• I have made corresponding changes to the documentation
• I have added tests to verify my fix or my feature
• New and existing unit tests pass locally with my changes
• I have added the relevant labels to my PR in so that relevant reviewers are notified

[gs-olive]

Overall a great improvement to embedding_bag; added a few small comments and suggestions

[zewenli98]

Thanks for the review! I just refactored the embedding_bag with native TRT layers.

[gs-olive]

Overall, looks good! Added one small comment, and pending CI validation

[zewenli98]

This is currently blocked by a Myelin bug. Filed a NVBug internally.

[zewenli98]

With the latest Pytorch, TRT-10 GA, and Torch-TRT main branch, the embedding_bag converter works on DLRM now.