NVIDIA / NVIDIA/TensorRT-LLM

Patch for create_causal_mask() function in transformers masking_utils.py

Open
#4,783 1 comment 0 reactions 1 assignee View on GitHub

@h-guo18 is already working on this.

Since Oct 13, 2025.

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

Description

The latest version of gemma3 uses create_causal_mask() function provided by transformers, which breaks torch export. We can try to patch this function with our own version that is exportable to support these family of models in auto deploy

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.