Hugging Face 发布 Olmo-core 3 框架，支持万亿参数 MoE 训练

1. 23:01
   Hugging Face Blog精选

   Olmo-core 3 发布：面向大规模 MoE 的开放可扩展训练框架

   AllenAI 发布 Olmo-core 3，重设计 MoE 训练系统以支持万亿参数规模。在专家池从 8 扩至 128、每 token 仅选 4 个专家的配置下，总参数从 4.6B 增至 47B，训练吞吐下降不到 5%；在 8 块 NVIDIA B300 上，47B MoE 吞吐约 2.7 倍提升。

Current heat 9·Comparable peak 10（Oct 2）·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.