Why too long delay time even if I have active worker ?
I have set the active worker to 1.
I am manually testing the response delay. I submit the next task only after the previous task is completed, so there is no waiting time.
However, many times, the delay time is still very long, sometimes even reaching more than 4 seconds.
Why is this?
In my code, the model has been loaded before runpod.serverless.start({"handler": run})
7 Replies
I find when downgrade to runpod==1.6.2, it is much better
I believe there is something wrong with runpod==1.7.2, cause the too long delay time even when there is active worker
We are releasing 1.7.3 to address this issue.
really, I will try
@yhlong00000 when is the release of 1.7.3 planned?
should be in 1-2 days.
do we need to do anything to update it or is it automatic for our endpoints?
You can update the runpod pip package