KubeAI: Private Open AI on K8s
Serve LLMs privately with an OpenAI API compatible API
Mô tả
✅️ Drop-in replacement for OpenAI with API compatibility 🚀 Serve OSS LLMs on CPUs or GPUs ⚖️ Autoscaling with scale from 0 🛠️ Zero dependencies (no Istio, Knative, etc.) 🤖 Operates OSS model servers (vLLM and Ollama) 🔋 Chat UI included
