NVIDIA 发布 Nemotron 3.5 Lightning 和 NeMo Switchyard，提升代理式 AI 效率
原标题：NVIDIA Nemotron 3.5 Lightning and NeMo Switchyard Deliver Faster, Smarter, More Efficient Agentic AI
AI 摘要
NVIDIA 发布了 Nemotron 3.5 Lightning，一个 300 亿参数的混合专家模型，专为长时间运行的代理式 AI 工作负载设计，提供高达 4 倍的输出速度和 30% 更快的任务完成速度。同时，NVIDIA 推出了 NeMo Switchyard，一个开源模型路由库，可智能地将请求路由到最合适的模型，降低成本并保持质量。这些发布旨在为企业提供对 AI 部署和运行的更大控制，并已获得多家合作伙伴的采用。
正文节选
As AI shifts from chatbots to autonomous agents, open models are serving market demands for full control over where AI runs and how it’s deployed and evolves. Today, NVIDIA is expanding its Nemotron 3 model family with Nemotron 3.5 Lightning, the highest-efficiency model in its class for long-running agentic AI workloads. This release follows Nemotron 3 Nano and reflects NVIDIA’s commitment to continually improving open models for greater accuracy and speed. Built for specialized tasks within la