2601.05047v3
CC BY 4.0
Google DeepMind
大型語言模型推論硬體的挑戰與研究方向
Challenges and Research Directions for Large Language Model Inference Hardware
Xiaoyu Ma, David Patterson
LLM InferenceHardwareMemory WallHBMHBFProcessing-Near-Memory3D StackingDatacenter AITCO
Teds Lin 許願