{"slug": "buoyant-releases-kinference-an-open-source-inference-control-plane-for-and-vllm", "title": "Buoyant Releases Kinference: An Open Source Inference Control Plane for Kubernetes and vLLM", "summary": "Buoyant released Kinference, an Apache 2.0 open-source inference control plane for running vLLM on Kubernetes, adding declarative routing policies, KV-cache-aware load balancing and per-tenant metrics. In Buoyant's own benchmark, Kinference cut median time to first token (TTFT) by 95%.", "body_md": "Buoyant has released Kinference, an Apache 2.0 inference control plane for vLLM on Kubernetes. It adds declarative routing policies, KV-cache-aware load balancing and per-tenant metrics, and cut median TTFT 95% in Buoyant’s own benchmark.\n\nThe post [Buoyant Releases Kinference: An Open Source Inference Control Plane for Kubernetes and vLLM](https://www.marktechpost.com/2026/11/07/buoyant-kinference-open-source-inference-control-plane-kubernetes-vllm/) appeared first on [MarkTechPost](https://www.marktechpost.com).", "url": "https://wpnews.pro/news/buoyant-releases-kinference-an-open-source-inference-control-plane-for-and-vllm", "canonical_source": "https://www.marktechpost.com/2026/11/07/buoyant-kinference-open-source-inference-control-plane-kubernetes-vllm/", "published_at": "2026-11-07 08:16:33+00:00", "updated_at": "2026-11-09 01:24:23.922436+00:00", "lang": "en", "topics": ["ai-infrastructure", "ai-tools", "large-language-models", "mlops", "developer-tools"], "entities": ["Buoyant", "Kinference", "Kubernetes", "vLLM"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/buoyant-releases-kinference-an-open-source-inference-control-plane-for-and-vllm", "markdown": "https://wpnews.pro/news/buoyant-releases-kinference-an-open-source-inference-control-plane-for-and-vllm.md", "text": "https://wpnews.pro/news/buoyant-releases-kinference-an-open-source-inference-control-plane-for-and-vllm.txt", "jsonld": "https://wpnews.pro/news/buoyant-releases-kinference-an-open-source-inference-control-plane-for-and-vllm.jsonld"}}