What needs to be done to make it respond very quickly in the text?
#1
by
ahmetab06
- opened
What needs to be done to make it respond very quickly in large texts? How to activate Cuda or is there any other method. Do I need to pre-train the text? How can I pre-train?
The solution will be using Onnx runtime. Please see
https://medium.com/@furcifer/deploying-triton-inference-server-in-5-minutes-67aa09a84ca6
savasy
changed discussion status to
closed