---
format: "aidr-story-markdown/v1"
id: "daa5b2afd1c7092cf88a127db80d519000d73e50c9f56d72995066553951148c"
canonical_url: "https://aidr.today/daa5b2af?lang=en"
title: "Buoyant Releases Kinference: An Open Source Inference Control Plane for Kubernetes and vLLM"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-11-07T08:16:33.000Z"
category: "Open Source"
topics: ["inference","open-source"]
source_urls: ["https://www.marktechpost.com/2026/11/07/buoyant-kinference-open-source-inference-control-plane-kubernetes-vllm/"]
summary: "Buoyant has released Kinference, an Apache 2.0 inference control plane for vLLM on Kubernetes. It includes declarative routing policies, KV-cache-aware load balancing, and per-tenant metrics, and reportedly cut median TTFT by 95% in Buoyant’s own benchmark."
---

# Buoyant Releases Kinference: An Open Source Inference Control Plane for Kubernetes and vLLM

> [Open the canonical story](<https://aidr.today/daa5b2af?lang=en>)

**Published:** 2026-11-07T08:16:33.000Z
**Category:** Open Source
**Topics:** inference, open\-source

## Summary

Buoyant has released Kinference, an Apache 2\.0 inference control plane for vLLM on Kubernetes\. It includes declarative routing policies, KV\-cache\-aware load balancing, and per\-tenant metrics, and reportedly cut median TTFT by 95% in Buoyant’s own benchmark\.

## Sources

- [Story source](<https://www.marktechpost.com/2026/11/07/buoyant-kinference-open-source-inference-control-plane-kubernetes-vllm/>)