Hi @team
Just wanted to make sure, there are no rules for how much computation for training or inference the solution can use, right?
The Onward team will run submissions on a SageMaker g5.24xlarge instance . Please follow the link for more information about the instance type.
Onward Team
@team it is a bit too late to provide this info as we have already invested and used different hardware specs for training and inference. You are responding 1 month later! This was critical information that should have been provided upfront. Your silence on this question meant we could use any hardware specs. What will happen if the used hardware specs are larger than g5.24xlarge
Hi @dscomps101
We answered a similar question on December 11th 2023 here on the forums. If your submission is unable to run on the allocated instance, we will consider testing on a g5.48xlarge instance.
I mean, my submission should run on any system with 24GB in VRAM, is there any time limit too? because that will be a crucial factor