Can i deploy TTS models using C++ APIs for Triton inference server and Triton client using Python APIs

An-BN · May 12, 2021, 7:29am

Hi!
I built a Triton server for TTS (Tacotron2, waveglow) models using C++ APIs (DeepLearningExamples/PyTorch/SpeechSynthesis/Tacotron2/trtis_cpp at master · NVIDIA/DeepLearningExamples · GitHub). For client side, I tried deploying Triton client C++ APIs, but I met some problems which I still don’t know how to solve. So I want to ask if Python APIs can be used for Triton client when my Triton server is written in C++.
client/src/python at main · triton-inference-server/client · GitHub

Topic		Replies	Views
C++ made '.trt' model feed into Python TRT API TensorRT	3	365	October 12, 2021
Mask RCNN TensorRT in Triton TensorRT	3	579	July 9, 2020
Is there C++ API of TensorRT.Lite? TensorRT	2	455	May 2, 2018
Model deployment in Triton TensorRT inference-server-triton	1	690	November 2, 2022
TensorRT Triton server for multiple model instances DRIVE AGX Orin General driveos-dl	2	638	December 1, 2022
Triton inference server on jetson xavier Jetson Xavier NX inference-server-triton	3	2016	October 18, 2021
Mask RCNN TensorRT in Triton Triton Inference Server - archived	0	753	July 9, 2020
How to pass inputs for my triton model using tritionclient python package General Topics and Other SDKs inference-server-triton	1	429	June 7, 2023
Can I use tf-trt with C++ API? TensorRT	1	785	November 11, 2019
Support for Triton Inference Server on Jetson NX Jetson Xavier NX cuda , jetson-inference , inference-server-triton , jetson , deepstream61	2	880	November 2, 2022