1
ThAME: 3D Memory-Enabled Heterogeneous Accelerator for LLM Mixture of Experts
针对LLM混合专家模型，提出3D内存异构加速器架构，突破内存瓶颈，显著提升推理效率与能效。
arXiv:2607.17074v1 Announce Type: cross Abstract: Mixture of Experts (MoE) architectures have emerged as a dominant paradigm for scaling Large Languag…