NVIDIA / NVIDIA/TensorRT-LLM

Test gemma models after upgrade to latest transformers

Open
#4,740 0 comments 0 reactions 1 assignee View on GitHub

@sugunav14 is already working on this.

Since May 28, 2025.

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

Description

Gemma3 models fail during export stage due to a .item() call on a meta tensor in modeling_gemma.py file. The latest transformers has a different implementation, but this version of transformers currently break tensorrt_llm. Need to test Gemma models with auto deploy once tensorrt_llm upgrades to the latest transformers.

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.