Ben Browning
Ben Browning
@Tomcli You need to `minikube ssh` and `sudo ip link set docker0 promisc on` I believe. Several members of my team have successfully run OpenWhisk on both minikube and minishift...
@mlangbehn Yes - I'm not aware of any way to get virtual machines running on top of Travis CI. That may be a blocker for running minikube itself in a...
Just as a note, we haven't maintained this kwsk experiment for quite some time now. It's not officially part of Apache OpenWhisk. But no, I don't think there was any...
I believe this is still relevant, although I also haven't seen any other recent user reports of it. So, commenting here to keep this from being automatically closed quite yet...
Hi @jinan-zhou - I'm not a maintainer here with any power to approve, but just a couple of comments and things to consider that may lower the burden on other...
This was fixed some time back by #1704
This is a large list, and something we'll have to tackle over time with each provider. So, consider this issue a tracker for the overall problem as its exists today....
There's a fairly easy way to approach this which is to just drop anything after the first tool call when sending the responses back if `parallel_tool_calls` is `False`. It's a...
Once #26233 merges, `parallel_tool_calls=False` will work with vLLM, and should make using vLLM with frameworks like LangGraph easier since you'll be able to restrict any model to only a single...
> > This is missing the actual implementation of `delete_openai_response` in the provider. > > Yeah I have done that too, I will update the PR with that. I also...