# Buoyant launches Kinference, an open-source inference control plane for vLLM

> Original title: Introducing Kinference: An Open Source Inference Control Plane for vLLM and Kubernetes

- Source: vLLM Blog
- Published: 2026-11-04T00:00:00.000Z
- Bad Influence: https://badinfluence.news/items/tlobscpimonodi9q34we5go6u
- Original: https://vllm.ai/blog/2026-11-04-introducing-kinference

## Summary

Buoyant has released Kinference, an open-source Apache v2 inference control plane for vLLM and Kubernetes, available on GitHub. It adds token rate limiting, per-tenant usage and cost tracking, KV-cache-aware load balancing, and YAML inference policies for routing or bursting requests. In Buoyant's benchmarks, Kinference cut median TTFT by 95% on one workload and served 7.4× the goodput on a shared-prefix workload compared with standard Kubernetes load balancing.

## Why it matters

The post benchmarks cache-aware routing against standard Kubernetes load balancing, with TTFT and goodput figures that show how routing choices affect serving performance.