Serverless errors in the logs
I am having a lot of these errors in our logs lately.
In our app we have nothing that indicates a problem in our backend.
We have a lot of good requests going through though.
Any idea what this could be related to?...
max workers set to 2 but endpoint page shows ‘5 idle’
Is this the way it should be?
Solution:
Yes, we cache a couple extra for you. You will never have more than the max workers running however.
Debugging Failed Serverless Requests
How to debug failed serverless requests
I have a an automat111 serverless endpoint and everything is working well However on Saturday between 17:00 and 21:00 it looks like requests started to fail and then everything returned to normal again. Is there anyway to get more information on what happened or get the logs for this period ?...
Solution:
Found that the logs tab gives the option to filter logs using a datetime range 👍
in serverless GPU Is Delay Time also Charged or not??
Solution:
^Yeah so there is:
Delay time which consists of:
(sitting in the queue + cold start (the machine starting up + maybe some setup code u might have outside the handler.py such as:
model = load(modelname) or whatever) + imports of libraries)
...
Unit for Pricing
I never pay attention to this on the internet: what is the unit here? second or minute?
Solution:
