Today for AI
HOT RADAR
toolsHEAT 10.6°

AI CURATED HOT STORY · 11/4/2026

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

1 reports archived1 independent sourcesupdated 11/4/2026, 08:00:00
Synthesis & Latest Updates
1 Sources Cross-Validated

Buoyant has released Kinference, an open-source control plane designed to build scalable inference platforms using vLLM on Kubernetes. It supports OpenAI/Anthropic-compatible APIs and features like token rate limiting, tenant cost tracking, and intelligent load balancing, achieving approximately 3.5x goodput improvement in multiturn workloads.

LATEST/Buoyant has released Kinference, an open-source control plane designed to build scalable inference platforms using vLLM on Kubernetes. It supports OpenAI/Anthropic-compatible APIs and features like token rate limiting, tenant cost tracking, and intelligent load balancing, achieving approximately 3.5x goodput improvement in multiturn workloads.

Hourly heat curve

2 fully observed hours
Fewer than 3 fully observed hours; trend not plotted yet.

Coverage timeline

Total 1 reports · Latest first
  1. vLLM 官方博客T1·68 pts

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

    • Kinference acts as a control plane for vLLM, simplifying the deployment of large-scale inference platforms on Kubernetes.
    • It includes built-in token rate limiting, tenant usage billing, and inference policy management for enterprise multi-tenancy needs.
    • Benchmarks show significant improvements in goodput for shared-prefix and multiturn workloads compared to traditional kube-proxy approaches.
Buoyant Releases Kinference: Open Source Inference Control Plane for vLLM and Kubernetes | Today for AI