Slow response time

#2
by raminh921 - opened

Hi,
I have test Qari notebook using A100 GPU but it takes about 30 seconds to generate response. (Depending on text length in the image). Do you have any idea to get it faster?
https://colab.research.google.com/github/NAMAA-ORG/public-notebooks/blob/main/Qari_Free_Colab.ipynb

Sign up or log in to comment