Moffett AI Secures Nearly RMB 1 Billion in Series C+ Funding to Accelerate Deployment of Dedicated Sparse Inference Chips
DeepSeek带火稀疏计算,国产芯片公司加速突围:这家公司又融近10亿
Moffett AI recently closed a Series C+ funding round of nearly RMB 1 billion, just five months after its previous round, with Q3 revenue growing several-fold. The company focuses on dedicated sparse inference chips and an algorithm-software-hardware co-design architecture; its next-generation SP200 accelerator card and upgraded SECA software stack are slated for release by year-end. Its inference clusters are already deployed at scale across four major regions including North and East China, and the company has joined emerging computing infrastructure projects such as domestic offshore computing token factories.
As MoE architectures drive sparse computing as a key lever for inference cost reduction, this development offers readers insight into the commercial deployment of dedicated chips through algorithm-hardware co-optimization.
Source:量子位 · qbitai.com