Ram Janovski

Hi @ktarplee it looks like nvidia will not take ownership of this code. I was thinking maybe it can be revised as an independent device-plugin on top of the official...

cool! so sidecar was a better fit than device-plugin framework? simpler to use? generic solution seems fine although I'd settle for just nvidia gpu first :) let me know when...

@eyalhir74 this [vGPU plugin](https://github.com/4paradigm/k8s-device-plugin) seemed most promising from my testing, just make sure to configure it with virtual gpu memory as well to avoid memory issues. scheduling, however, is not...

just use --set before each term: ``` helm install stable/kubewatch \ --set rbac.create=true \ --set slack.channel='#devops-k8s' \ --set slack.token=xoxb-31XXXXXXXXXXXXXXXXXXX \ --set resourcesToWatch.pod=true \ --set resourcesToWatch.daemonset=true ``` but please update the...

also couldn't get this to work on specific namespace. the tool is quite useless without any filters.

unfortunately, see #144

hey @timduhenchanter any chance you can share the working docker in dockerhub somewhere?

so if anyone needs a snapshot version of the master with namespace filter working (still not too good, as many duplicated 'update' messages arrive with missing info): ``` helm --namespace...

Flagger [already have this](https://fluxcd.io/flagger/tutorials/gatewayapi-progressive-delivery/) #just_saying

this is a little late, but doesn't it make more sense from architecture POV to run the LLM models outside the server, and connect to the LLM serving process via...