返回探索

Jev 基准测试:500 个实时智能体并行运行

初步基准测试显示,Jev 在 3D 环境中并行运行 500 个实时智能体,平均延迟 500ms,每秒 35 次 API 调用,且为朴素实现。

Jev is actually insane. We benchmarked it, and the results completely change the game for us: > 500 real-time agents > running in parallel > in a 3D environment The preliminary results are crazy: > 500ms average latency > 35 API calls/s > all with a naive implementation We

· 651 次赞在 X 打开