All activity
ā
ļø Drop-in replacement for OpenAI with API compatibility
š Serve OSS LLMs on CPUs or GPUs
āļø Autoscaling with scale from 0
š ļø Zero dependencies (no Istio, Knative, etc.)
š¤ Operates OSS model servers (vLLM and Ollama)
š Chat UI included
š Serve OSS LLMs on CPUs or GPUs
āļø Autoscaling with scale from 0
š ļø Zero dependencies (no Istio, Knative, etc.)
š¤ Operates OSS model servers (vLLM and Ollama)
š Chat UI included
KubeAI: Private Open AI on K8s
Serve LLMs privately with an OpenAI API compatible API