sherpa-onnx icon indicating copy to clipboard operation
sherpa-onnx copied to clipboard

Published 20 hours ago • verified publisher icon k2-fsa

[Help wanted] Support quantization

Open csukuangfj opened this issue 2 years ago • 2 comments
trafficstars

TODO

  • [ ] Support fp16 and/or int8 with TensorRT

csukuangfj avatar Feb 20 '23 07:02 csukuangfj

Hi @csukuangfj ,

Currently I am doing some experiments with Zipformer models, let me know if there are active developments going on from your end for TensorRT low precision support, else I will take up on this task :)

manickavela29 avatar Mar 14 '24 10:03 manickavela29

else I will take up on this task :)

Thanks! That would be great. We don't have a plan to support tensorrt in the near future.

csukuangfj avatar Mar 14 '24 12:03 csukuangfj