Buoyant Open-Sources Kinference: An Inference Control Plane for vLLM and Kubernetes
Introducing Kinference: An Open Source Inference Control Plane for vLLM and KubernetesNov 4, 2026·7 min readKinference is a new open source inference control plane for building scalable inference platforms with vLLM and Kubernetes, providing token rate limiting, tenant usage and cost tracking, intelligent load balancing, and inference policies.
Buoyant has open-sourced Kinference, an inference control plane for vLLM and Kubernetes that provides token rate limiting, multi-tenant usage and cost tracking, KV cache-aware load balancing, and declarative inference policies.
The project brings KV cache-aware scheduling and declarative policies to Kubernetes- and vLLM-based LLM serving, helping engineering teams better control latency and compute costs.
Source:vLLM 官方博客（网页） · vllm.ai