NVIDIA 机密计算支持私有高性能生产级 AI 推理
Enabling Private High-Performance Production AI Inference with NVIDIA Confidential Computing
NVIDIA 机密计算（CC）为 LLM 推理提供在可信环境中运行的路径，通过内存加密的机密虚拟机（CVM）和机密 GPU 处理个人、企业及受监管场景中的敏感信息与专有模型上下文。
As large language model (LLM) inference increasingly processes sensitive information and proprietary model context across personal, enterprise, and regulated...
As large language model (LLM) inference increasingly processes sensitive information and proprietary model context across personal, enterprise, and regulated settings, data must be processed inside a trusted environment. NVIDIA Confidential Computing (CC) provides a pathway for running these workloads securely using memory-encrypted confidential virtual machines (CVMs), confidential GPUs…
来源：NVIDIA Developer Blog · developer.nvidia.com