1
IR3DE: A Linear Router for Large Language Models
被ICML Workshop收录,提出一种用于大语言模型的线性路由器,有望简化模型推理中的资源分配问题。
arXiv:2606.06098v1 Announce Type: new Abstract: Foundational Large Language Models (LLMs) demonstrate proficiency on a wide range of general tasks, an…