[New Model]: Add Support for T5Gemma Architecture

[0Unicorn]

The model to consider.

Please add official support for google/t5gemma-s-s-prefixlm in tensorrt-llm.

T5Gemma (aka encoder-decoder Gemma) was proposed in a research paper by Google. It is a family of encoder-decoder large language models, developed by adapting pretrained decoder-only models into encoder-decoder.

This model was released on 2025-04-08 and added to Hugging Face Transformers on 2025-06-25.

Thanks!

The closest model TensorRT-LLM already supports.

enc-dec

What's your difficulty of supporting the model you want?

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.

[karljang]

Thanks for bringing up this model!
We don’t have any immediate plans to support it right now, as our focus is on text‑generation decoder‑based models.
That said, contributions are always welcome!