AI 导读
机器人在哪里思考 端侧推理 vs 数据中心推理 具身化难题, 规划层 vs 行动层, Glass-To-Glass 预算, 晶圆与 DRAM 约束, 一块 B300 vs 56 块 Thor 的 TCO, 从工厂到洞穴 https://t.co/ABD9HsM7B7
正文
Where Does a Robot Think
On-Device vs Datacenter Inference
The Embodiment Problem,
Planning vs Action Layers,
Glass-To-Glass Budgets,
Wafers & DRAM Constraints,
One B300 vs 56 Thors TCO,
Factories To Caves
https://t.co/ABD9HsM7B7
来源:@SemiAnalysis_ · x.com