NeMo icon indicating copy to clipboard operation
NeMo copied to clipboard

Support TRTLLM Pytorch backend Deployment

Open meatybobby opened this issue 9 months ago • 6 comments

[!IMPORTANT]
The Update branch button must only be pressed in very rare occassions. An outdated branch is never blocking the merge of a PR. Please reach out to the automation team before pressing that button.

What does this PR do ?

Support TRTLLM Pytorch backend Deployment and minor changes for query

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The Jenkins CI system has been replaced by GitHub Actions self-hosted runners.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

  • [x] 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)

meatybobby avatar Apr 22 '25 17:04 meatybobby

I would be great to fill in the MR description with usage example as a form of documenting what happens here.

janekl avatar Apr 29 '25 14:04 janekl

This PR is stale because it has been open for 14 days with no activity. Remove stale label or comment or update or this will be closed in 7 days.

github-actions[bot] avatar May 14 '25 02:05 github-actions[bot]

@janekl Applied several changes. Could you review it again?

meatybobby avatar May 19 '25 22:05 meatybobby

We will need a functional test for this new feature. Please have a look at some examples from tests/functional_tests for inspirations.

janekl avatar May 23 '25 11:05 janekl

  • If I'm not mistaken, it should be possible to use tensorrt_llm.llmapi.LLM with LLM(..., backend='pytorch'), instead of tensorrt_llm._torch.LLM, right?
  • Would it be possible to make this class a general wrapper of LLM for any backed? That would be useful for deploying modelopt unified checkpoints and HFAutoModels in trt-llm

Laplasjan107 avatar May 29 '25 13:05 Laplasjan107

This PR is stale because it has been open for 14 days with no activity. Remove stale label or comment or update or this will be closed in 7 days.

github-actions[bot] avatar Jun 13 '25 02:06 github-actions[bot]

This PR was closed because it has been inactive for 7 days since being marked as stale.

github-actions[bot] avatar Jun 21 '25 02:06 github-actions[bot]