slow response from service

[jiangweiatgithub]

I have been comparing the efficency between the muse as service and the original "hub.load" method, and see a noticeable slow reponse in the former, both running separately on my Quadro RTX 5000. Can I safely assume this slowness is due to the very nature of the web service? If so, is there any way to improve it?

[dayyass]

Hi, @jiangweiatgithub!
Thanks for interest to MUSE-as-Service!

There is an interesting behavior. I'm not sure about reasons, but I will do some experiments to figure it out.