Fix issue using count/min/max of inference-accelerators

[dims]

Issue #, if available: #413

Description of changes: Do exactly what we do for GpuMemoryRange as that one works fine. which means we use the Int32RangeFilter

By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license.

Here's the output:

❯ ./build/ec2-instance-selector --vcpus 8 --gpus 0 --memory 16GiB -a x86_64 --inference-accelerators 1
inf1.2xlarge

[dims]

Hola @bwagner5 long time no see :)

[bwagner5]

lgtm

I added a conversion if an in32 is passed to convert to an int64 to be checked if the instance spec value is an in64.

[dims]

thanks @bwagner5 :)