I have a quartznet model trained by nemo. I’m wondering is it possible to speed up inference of my quartznet by tensorrt. I guess it’s not supported now. I just can’t find any sample code.
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| How to deploy QuartzNet ASR in triton inference server? | 0 | 538 | November 16, 2020 | |
| TensorRt inference is taking 1.5 sec to inference a single frame.i want to speed up my inference.How can i do that | 3 | 812 | March 13, 2023 | |
| how to inference a net on tensorrt? | 1 | 884 | November 11, 2019 | |
| Accelerating Inference Up to 6x Faster in PyTorch with Torch-TensorRT | 18 | 3796 | September 7, 2023 | |
| Double PyTorch Inference Speed for Diffusion Models Using Torch-TensorRT | 1 | 49 | July 24, 2025 | |
| Deploying Deep Neural Networks with NVIDIA TensorRT | 17 | 874 | October 8, 2017 | |
| Video Tutorial: Accelerating Inference Performance of Recommendation Systems with TensorRT | 0 | 213 | August 21, 2022 | |
| Is it possible to add TensorRT plugin into FasterTransformer Decoder and Decoding | 4 | 857 | September 30, 2021 | |
| Slow inference UNet Industrial TF-TRT | 1 | 502 | July 2, 2023 | |
| TensorRT 3: Faster TensorFlow Inference and Volta Support | 0 | 276 | August 21, 2022 |