MoA测量单token充分计算量并优化路由与投机解码

1. 12:00
   arXiv · Artificial Intelligence

   一个 token 的成本是多少？用 Mixture-of-Agents 测量每个 token 的充分计算量

   论文用 Mixture-of-Agents（MoA）方法测量大语言模型每个 token 实际所需的推理计算量，定义能复现该 token 的最小 agent 的推理成本为“充分计算量”。

Current heat 7·Comparable peak 10（Oct 5）·Comparable change over 24 hours –

The trend compares only the same participants observed continuously; its range may be smaller than the current heat count. Move or click on the chart to inspect hourly heat; use the left and right arrow keys to switch.