Support exporting Nemotron-340B for TensorRT-LLM

[jinyangyuan-nvidia]

What does this PR do ?

Add a one line overview of what this PR aims to accomplish.

Collection: [Note which collection this PR will affect]

Changelog

• Add specific line by line info of high level changes in this PR.

Usage

• You can potentially add a usage example below

# Add a code snippet demonstrating how to use this 

GitHub Actions CI

The Jenkins CI system has been replaced by GitHub Actions self-hosted runners.

The GitHub Actions CI will run automatically when the "Run CICD" label is added to the PR.
To re-run CI remove and add the label again.
To run CI on an untrusted fork, a NeMo user with write access must first click "Approve and run".

Before your PR is "Ready for review"

Pre checks:

• Make sure you read and followed Contributor guidelines
• Did you write any new necessary tests?
• Did you add or update any necessary documentation?
• Does the PR affect components that are optional to install? (Ex: Numba, Pynini, Apex etc)
  • Reviewer: Does the PR have correct import guards for all optional libraries?

PR Type:

• New Feature
• Bugfix
• Documentation

If you haven't finished some of the above items you can still open "Draft" PR.

Who can review?

Anyone in the community is free to review the PR once the checks have passed.
Contributor guidelines contains specific people who can review PRs to various areas.

Additional Information

• Related to # (issue)

[juney-nvidia]

@oyilmaz-nvidia Hi Onur, can you help review this PR?
In TRT-LLM 0.14 release, we are working to prepare documentation for multi-node deployment and we want to use Nemotron as an example. Without this fix, we cannot run through Nemotron on multi-node.

[meatybobby]

It seems the changes in nemo/export/trt_llm/converter/model_converter.py is not necessary. I tested parallel_embedding still works without the changes. Could we remove the change on this file?