Ben Browning

I think that nicely sums up all the challenges I'm aware of - thanks @praveenkumar . One thing I have not looked into is how the existing RHCOS AMIs get...

Here's an example of how gofmt would change the existing code - https://github.com/bbrowning/funktion/commit/076935a8bc7b09d0cbe528c4f0d6790c22407b8e It's mainly consistent whitespace and import ordering changes.

I was able to successfully test this in a vLLM 0.4.1 container running on OpenShift, both with models serialized with the Tensorizer library directly and for vLLM-serialized models. Once I...

Of the project? Or of that code? There are a couple things to do before I consider this proof-of-concept proved out enough to start taking on more code hygiene tasks....

The PRs I opened here and in the serverless-components/knative-serving repo allow the serverless CLI to deploy Knative Services to an OpenShift 4 cluster as a regular (ie not cluster admin)...

@billfine I'm happy to chat any time - I'll reach out on the serverless-contrib Slack.

We discussed this in the October 29th operations working group meeting. One of the points brought up is that we may want to think about how a user installs channel...

@houshengbo It looks like the eventing operator needs special logic to handle renaming the CRD during upgrade. One of those special places where it needs logic will be in handling...

Another thing that influenced the choice of option 1 that we have today is the idea that users should get a working setup out of the box with zero config....

I will also say that if it becomes possible to run multiple Knative control planes in a single cluster, then Option 4 would become my preference. However, since that is...