16 GB GPU availability almost always low | Runpod | Page 1

astral cave Aug 19, 2025, 10:00 AM

#

Hence very frequent throttling workers and pulling docker image again and again

low zealotBOT Aug 19, 2025, 10:00 AM

#

To help others find answers, you can mark your question as solved via Right click solution message -> Apps -> ✅ Mark Solution

tame flint Aug 20, 2025, 2:57 AM

#

Are you deploy to all data centers or you selected specific regions?

astral cave Aug 20, 2025, 7:38 AM

#

All data centres

olive robin Aug 20, 2025, 5:30 PM

#

What CUDA versions do you have selected? Is it possible for you to widen your range a little bit more?

astral cave Aug 21, 2025, 5:42 AM

#

I have allowed all CUDA versions

real plover Aug 21, 2025, 9:16 AM

#

And your max workers? set it to a larger number

#

maybe share your endpoint id?

astral cave Aug 21, 2025, 9:18 AM

#

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

real plover Aug 21, 2025, 9:18 AM

#

astral cave max workers varies per endpoint, 2-3-5 mostly but the problem is if I set all en...

and like all of them got throttled?

#

like 3 all got throttled?

astral cave Aug 21, 2025, 10:41 AM

#

yes almost all keep getting throttled , and initializing in some time gaps

fleet bisonBOT Aug 21, 2025, 12:41 PM

#

astral cave yes almost all keep getting throttled , and initializing in some time gaps

@astral cave

Escalated To Zendesk

The thread has been escalated to Zendesk!

real plover Aug 21, 2025, 12:42 PM

#

try open a ticket

#16 GB GPU availability almost always low