I am getting confused in these two terminology. How different are ?
While doing inference using RIVA… it works on riva-speech-server docker image. So where do Tritron Inference images used?
pls do respond
Triton Inference server (GitHub - triton-inference-server/server: The Triton Inference Server provides an optimized cloud and edge inferencing solution.) is the inference engine riva users. the riva-speech image uses Triton internally and provides additional functionality and speech specific grpc based APIs.