11-19 更新 实时
首页/ 技术栈/ 正文

Vera Rubin NVL72 领跑 MLPerf Endpoints v1.0 智能体推理

技术栈 来源:NVIDIA Developer 2026-11-16 23:23 0 阅读 机器翻译
Vera Rubin NVL72 领跑 MLPerf Endpoints v1.0 智能体推理

智能体式工作负载对推理系统提出了更高要求。AI 智能体在多轮交互中携带不断增长的对话历史,并生成推理、工具调用与响应交织的内容。推理系统必须在支持规模化用户的同时保持响应能力。MLPerf Endpoints v1.0 通过 API,使用编码与企业工作流来评估服务容量与响应能力之间的这种平衡……

译文由英文原文机器翻译,术语按行业惯例统一,可在文末展开原文核对。

查看英文原文(NVIDIA Vera Rubin NVL72 Leads Agentic Inference Performance on MLPerf Endpoints v1.0)
Two rows of black data center racks with gold-colored server components against a black background.Agentic workloads are demanding more from inference systems. AI agents carry growing conversation histories across turns and generate a mix of reasoning, tool...Two rows of black data center racks with gold-colored server components against a black background.

Agentic workloads are demanding more from inference systems. AI agents carry growing conversation histories across turns and generate a mix of reasoning, tool calls, and responses. Inference systems must support users at scale while remaining responsive. MLPerf Endpoints v1.0 evaluates this balance between serving capacity and responsiveness using coding and enterprise workflows through API…

Source

正文保留英文原文,标题与摘要由机器翻译。

本文由采集器自动同步

原文发布于 NVIDIA Developer(NVIDIA Vera Rubin NVL72 Leads Agentic Inference Performance on MLPerf Endpoints v1.0),标题、摘要与正文由机器翻译,术语按行业惯例统一,未经人工逐句校订。

阅读原文 ↗