arbs-gpu

In sherpa/triton, joiner. onnx reasoning is very slow

4

I use this code[https://github.com/k2-fsa/sherpa/tree/master/triton/zipformer/model_repo_offline](url) to start the Triton service and send requests to count the time spent on the encoder, decoder, and joiner modules. I found that the joiner module...

The client terminal cannot use the multi-process program to send data

2

@csukuangfj The code for this client is in https://github.com/k2-fsa/sherpa/tree/master/triton/client/client.py After my test, if you do not use multi-process mode, that is, send data to the server with a single thread,...