David Gray

Thanks @lahinson for the draft. We are expanding on the NTO functionality in HyperShift a bit in [this PR](https://github.com/openshift/hypershift/pull/1729) which should be landing in the next hours / days (it...

> Thanks for letting me know, @dagrayvid. I'll keep an eye on that PR, and after it's merged, I'll add the new info to this PR. Thanks @lahinson, the PR...

Hi @lahinson, I will try to do a review today or tomorrow... We do have one [pending change](https://github.com/openshift/hypershift/pull/1802#issue-1408554852) to rename a part of the NodePool spec which will impact the...

Thanks @lahinson, based on the guidelines I went through the changes and made my best attempt at deciding the correct formatting for the different object names (Tuned, NodePool, ConfigMap, etc...),...

@nvpohanh @vilmara Is there documentation on how to use FP16 in these benchmarks? Do we need to edit the preprocessing script?

I was able to build `inferencer`, by switching to a RHEL UBI7 container, replacing `-lcaffe2` with `-ltorch` in the `Makefile`, since the caffe2 API has moved to `libtorch`, and building...

@Jooho @ckadner, according to the [HPA docs](https://kubernetes.io/docs/tasks/run-application/horizontal-pod-autoscale/#scaling-on-custom-metrics), since k8s v1.23 the autoscaling/v2 API supports custom metrics. I'm not sure what would be involved in exposing this through modelmesh, however.