Question about concurrent limits for On-Demand instances
Hello,
I am currently testing the On-Demand API for a project I'm working on.
I haven't hit any limits yet, but I noticed the dashboard shows "2 max" or similar per GPU.
Before I fully commit to integrating On-Demand into my workflow, I want to clarify:
Is it possible to increase the concurrent instance limit later if I need to run multiple pods simultaneously? Or is On-Demand strictly limited to a few instances per account?
I'd appreciate some info on how the limit works. Thanks.
I am currently testing the On-Demand API for a project I'm working on.
I haven't hit any limits yet, but I noticed the dashboard shows "2 max" or similar per GPU.
Before I fully commit to integrating On-Demand into my workflow, I want to clarify:
Is it possible to increase the concurrent instance limit later if I need to run multiple pods simultaneously? Or is On-Demand strictly limited to a few instances per account?
I'd appreciate some info on how the limit works. Thanks.
