NVIDIA-NeMo/NeMo

Speed up RNNT model inference using TRT

Open

#14,531 opened on 2025年8月20日

GitHub で見る
 (1 comment) (0 reactions) (1 assignee)Python (3,421 forks)github user discovery
ASRcommunity-requesthelp wantedwaiting-on-customer

Repository metrics

Stars
 (17,298 stars)
PR merge metrics
 (平均マージ 12d) (30d で 49 merged PRs)

説明

Hi,

I previously trained an RNNT model and now want to accelerate it by converting it to TensorRT. I’ve exported the model to ONNX and have encoder.onnx and decoder.onnx.

I’m using the TensorRT 25.03 Docker image and trtexec to convert the models. The decoder works fine with --fp16, but when I use --fp16 for the encoder, some outputs return NaN and the results are incorrect.

Has anyone encountered this issue or knows how to fix it?

Are there any methods to accelerate RNNT model inference?

コントリビューターガイド