HyperAccel

HyperAccel 是一家無晶圓廠半導體公司，專注於開發 AI 晶片，推動生成式 AI 的普及應用。我們鎖定 推論 (Inference) 而非訓練，並聚焦於 大型語言模型 (LLMs)，因為 LLM 推論具備獨特的序列運算特性，使傳統 GPU 的設計過度規格、成本高昂。HyperAccel 透過專為生成式 AI 打造的硬體設計，突破成本與效能瓶頸，推動 GenAI 更快、更廣地落地。

HyperAccel is a fabless company developing AI chips to enable widespread deployment of Generative AI. Therefore, we target inference over training and focus on LLMs instead of traditional AI models. Due to distinct sequential characteristic of LLM inference, GPU designed for other compute-intensive AI workloads is over-specified and thus costly. We overcome the cost barrier by designing the most efficient hardware solution catered to GenAI.