← Back to feed

Kinference: Open-source inference control plane for vLLM

IT·开源 · 2026-11-05 10:21

Buoyant团队推出Kinference,为vLLM和Kubernetes提供策略驱动的推理负载均衡与SLO管理。

Source: vllm.ai


Auto-generated summary for reference only. RSS