Feature support: eagle multimodal inputs
Open
@laikhtewari is already working on this.
Since May 30, 2025.
feature request
- Dominant language
- Python
- Stars
- 14.7k
- Forks
- 2.8k
- Avg merge
- 2d 23h
- Merged PRs (30d)
- 489
Description
Hi,
Currently lookhead has already supported multimodal inputs while eagle has not. As eagle's input for embedding layer is not 2-D so when batch size > 1, it cannot expand correctly. https://github.com/NVIDIA/TensorRT-LLM/blob/c6f7d423354214df818e206e87680fb2d513a718/tensorrt_llm/layers/embedding.py#L182
May I request for new feature that eagle supports multimodal input.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Assessment
This issue has not been assessed yet.