ray_vllm_inference
ray_vllm_inference copied to clipboard
How can we do the same, using KubeRay, RayCluster and RayServe?
So i've got a kubernetes cluster, installed with KubeRay Operator and created a RayCluster, but how do i then create a manifest for Rayserve to serve, say a Llama2 or Mistral 7b? appreciate your help and thank you in advance!
Sorry but I'm not working with Kubernetes. Please ask at the Anyscale #Kubernetes Slack channel and ask the question. There is a link to Slack on there website.
So i've got a kubernetes cluster, installed with KubeRay Operator and created a RayCluster, but how do i then create a manifest for Rayserve to serve, say a Llama2 or Mistral 7b? appreciate your help and thank you in advance!
I see he set it up as the same as instructed in the document of Anyscale. You can follow this https://docs.ray.io/en/latest/cluster/getting-started.html to try his project. I am trying to set up his project again with this