Agent Substrate: Advancing Kubernetes for Agents at Scale
AI agents spend most of their time idle, waiting on a human prompt, a tool result or a model response. Kubernetes wasnβt built for that. Running one Pod per...
AI agents spend most of their time idle, waiting on a human prompt, a tool result or a model response. Kubernetes wasnβt built for that. Running one Pod per session holds memory for sessions that arenβt doing anything, and deleting Pods between turns pays a multi-second cold start every time and loses the agentβs state. RL post-training hits the same wall. Agent Substrate, now donated to theβ¦
Many AI workloads need only a fraction of a GPU. Giving each one an entire device can leave capacity idle; sharing GPUs lets platform teams serve more workloads...
NVIDIA is making the full NVIDIA Run:ai platform available as open source software, giving customers, developers, and ecosystem partners access to...