16 GB GPU availability almost always low
Hence very frequent throttling workers and pulling docker image again and again
11 Replies
Are you deploy to all data centers or you selected specific regions?
All data centres
What CUDA versions do you have selected? Is it possible for you to widen your range a little bit more?
I have allowed all CUDA versions
Unknown User•4d ago
Message Not Public
Sign In & Join Server To View
max workers varies per endpoint, 2-3-5 mostly
but the problem is if I set all enpoints max workers to a large number i'll hit my max workers limit
many endpoints running in parallel
Unknown User•4d ago
Message Not Public
Sign In & Join Server To View
yes almost all keep getting throttled , and initializing in some time gaps
@Solidsoldier
Escalated To Zendesk
The thread has been escalated to Zendesk!
Unknown User•4d ago
Message Not Public
Sign In & Join Server To View
Kk will do