Support for Embeddings with XLM-RoBERTa and Adapters

[jfhetzer]

What does this PR do?

This PR adds support for XLM-RoBERTa with FlashInfer to Lorax. The XLM-RoBERTa implementation supports embeddings and adapter loading. Changes included in this PR are:

• added modelling for RoBERTa
• added XLM-RoBERTa model supporting embeddings and adapter loading
• added support for adapters in the /embd endpoint (see changes in router and augmented batch in server)

Before submitting

• This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
• Was this discussed/approved via a Github issue or the discord / slack channel? Please add a link
  to it if that's the case.
• Did you write any new necessary tests?

Who can review?

Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.

@tgaddair

[tgaddair]

This is awesome! Thanks for the PR @jfhetzer.

I'll do a quick test locally before landing, but LGTM!

[jfhetzer]

Thanks for the quick review @tgaddair
Lmk when something pops up in your test!