[FEA] Support Roberta model

NVIDIA / TensorRT-LLM

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.

https://nvidia.github.io/TensorRT-LLM

Apache License 2.0

8.31k stars 932 forks source link

[FEA] Support Roberta model #124

Open esnvidia opened 11 months ago

esnvidia commented 11 months ago

As title suggests, support the HF Roberta model with the pretrained weights here: https://huggingface.co/roberta-large

jdemouth-nvidia commented 11 months ago

Hi @esnvidia ,

Thanks for the suggestion. We will add it to the list of feature requests. Not sure if/when we will have time to implement it but we will keep it in mind.

Thanks, Julien