NVIDIA / NVIDIA/TensorRT-LLM

[RFC]: Upcoming Model Deprecation

Open
#19,301 0 comments 0 reactions 3 assignees View on GitHub

@laikhtewari is already working on this.

Since Sep 16, 2026.

RFC
Dominant language
Python
Stars
14.7k
Forks
2.8k
Avg merge
2d 23h
Merged PRs (30d)
489

Description

Motivation.

To keep an accurate understanding of models that are tested and well supported, the TRTLLM team plans to deprecate models that have low usage. This will mean the models will no longer be actively tested against new changes and requested fixes to the model will be reviewed on a case by case basis.

Proposed Change.

We are currently planning to deprecate the following models and their deployment guides:

  • llama3.3-70b
  • llama4-scout
  • kimi-k2-thinking
  • deepseek-r1

If you use any of these models with new versions of TRTLLM and are depending on quality being maintained, please comment!

Feedback Period.

2 weeks

CC List.

No response

Any Other Things.

No response

Before submitting a new issue...
  • Make sure you already searched for relevant issues, and checked the documentation and examples for answers to frequently asked questions.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.